<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="pt">
  <front>
    <journal-meta>
      <journal-id journal-id-type="nlm-ta">Arq Bras Cardiol</journal-id>
      <journal-id journal-id-type="publisher-id">abc</journal-id>
      <journal-title-group>
        <journal-title>Arquivos Brasileiros de Cardiologia</journal-title>
        <abbrev-journal-title abbrev-type="publisher">Arq. Bras. Cardiol.</abbrev-journal-title>
      </journal-title-group>
      <issn pub-type="ppub">0066-782X</issn>
      <issn pub-type="epub">1678-4170</issn>
      <publisher>
        <publisher-name>Sociedade Brasileira de Cardiologia - SBC</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id specific-use="scielo-v3" pub-id-type="publisher-id">5V3LvX5sWqbmYHNkRWZPHyC</article-id>
      <article-id specific-use="scielo-v2" pub-id-type="publisher-id">S0066-782X2025000600305</article-id>
      <article-id pub-id-type="other">00305</article-id>
      <article-id pub-id-type="doi">10.36660/abc.20240765</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Artigo Original</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Impacto da Reabilita&#231;&#227;o Card&#237;aca Baseada em Tecnologia na Capacidade de Exerc&#237;cio e na Ades&#227;o de Pacientes com Doen&#231;a Arterial Coronariana: Uma An&#225;lise com Suporte de Intelig&#234;ncia Artificial</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-9192-6033</contrib-id>
          <name>
            <surname>Saklica</surname>
            <given-names>Dilara</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa</role>
          <role>Obten&#231;&#227;o de dados</role>
          <role>An&#225;lise e interpreta&#231;&#227;o dos dados</role>
          <role>An&#225;lise estat&#237;stica</role>
          <role>Reda&#231;&#227;o do manuscrito</role>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-0218-140X</contrib-id>
          <name>
            <surname>Vardar-Yagli</surname>
            <given-names>Naciye</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa</role>
          <role>Obten&#231;&#227;o de dados</role>
          <role>An&#225;lise e interpreta&#231;&#227;o dos dados</role>
          <role>An&#225;lise estat&#237;stica</role>
          <role>Reda&#231;&#227;o do manuscrito</role>
          <role>Revis&#227;o cr&#237;tica do manuscrito quanto ao conte&#250;do</role>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Saglam</surname>
            <given-names>Melda</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa</role>
          <role>An&#225;lise e interpreta&#231;&#227;o dos dados</role>
          <role>An&#225;lise estat&#237;stica</role>
          <role>Revis&#227;o cr&#237;tica do manuscrito quanto ao conte&#250;do</role>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Yuce</surname>
            <given-names>Deniz</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa;</role>
          <role>An&#225;lise estat&#237;stica</role>
          <role>Revis&#227;o cr&#237;tica do manuscrito quanto ao conte&#250;do</role>
          <xref ref-type="aff" rid="aff2">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Ates</surname>
            <given-names>Ahmet Hakan</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa;</role>
          <role>Obten&#231;&#227;o de dados</role>
          <role>Revis&#227;o cr&#237;tica do manuscrito quanto ao conte&#250;do</role>
          <xref ref-type="aff" rid="aff3">
            <sup>3</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-7673-229X</contrib-id>
          <name>
            <surname>Yorgun</surname>
            <given-names>Hikmet</given-names>
          </name>
          <role>Concep&#231;&#227;o e desenho da pesquisa</role>
          <role>Obten&#231;&#227;o de dados</role>
          <role>Revis&#227;o cr&#237;tica do manuscrito quanto ao conte&#250;do</role>
          <xref ref-type="aff" rid="aff3">
            <sup>3</sup>
          </xref>
        </contrib>
      </contrib-group>
      <aff id="aff1">
        <label>1</label>
        <institution content-type="orgdiv2">Faculty of Physical Therapy and Rehabilitation</institution>
        <institution content-type="orgdiv1">Department of Cardiorespiratory Physiotherapy and Rehabilitation</institution>
        <institution content-type="orgname">Hacettepe University</institution>
        <addr-line>
          <named-content content-type="city">Ankara</named-content>
        </addr-line>
        <country country="TR">Turquia</country>
        <institution content-type="original">Faculty of Physical Therapy and Rehabilitation, Department of Cardiorespiratory Physiotherapy and Rehabilitation, Hacettepe University, Ankara &#8211; Turquia</institution>
      </aff>
      <aff id="aff2">
        <label>2</label>
        <institution content-type="orgdiv2">Faculty of Medicine</institution>
        <institution content-type="orgdiv1">Department of Preventive Oncology</institution>
        <institution content-type="orgname">Hacettepe University</institution>
        <addr-line>
          <named-content content-type="city">Ankara</named-content>
        </addr-line>
        <country country="TR">Turquia</country>
        <institution content-type="original">Faculty of Medicine, Department of Preventive Oncology, Hacettepe University, Ankara &#8211; Turquia</institution>
      </aff>
      <aff id="aff3">
        <label>3</label>
        <institution content-type="orgdiv2">Faculty of Medicine</institution>
        <institution content-type="orgdiv1">Department of Cardiology</institution>
        <institution content-type="orgname">Hacettepe University</institution>
        <addr-line>
          <named-content content-type="city">Ankara</named-content>
        </addr-line>
        <country country="TR">Turquia</country>
        <institution content-type="original">Faculty of Medicine, Department of Cardiology, Hacettepe University, Ankara &#8211; Turquia</institution>
      </aff>
      <author-notes>
        <corresp id="c01"><label>Correspond&#234;ncia</label>: Naciye Vardar-Yagli &#8226; Hacettepe University, Faculty of Physical Therapy and Rehabilitation 06100 Samanpazar&#305;/Ankara &#8211; Turquia E-mail: <email>naciyevardar@yahoo.com</email> </corresp>
        <fn fn-type="edited-by">
          <label>Editor respons&#225;vel pela revis&#227;o:</label>
          <p> Ricardo Stein</p>
        </fn>
        <fn fn-type="conflict">
          <label>Potencial conflito de interesse:</label>
          <p>N&#227;o h&#225; conflito com o presente artigo.</p>
        </fn>
      </author-notes>
      <pub-date date-type="pub" publication-format="electronic">
        <day>06</day>
        <month>06</month>
        <year>2025</year>
      </pub-date>
      <pub-date date-type="collection" publication-format="electronic">
        <month>05</month>
        <year>2025</year>
      </pub-date>
      <volume>122</volume>
      <issue>6</issue>
      <elocation-id>e20240765</elocation-id>
      <history>
        <date date-type="received">
          <day>13</day>
          <month>11</month>
          <year>2024</year>
        </date>
        <date date-type="rev-recd">
          <day>14</day>
          <month>02</month>
          <year>2025</year>
        </date>
        <date date-type="accepted">
          <day>19</day>
          <month>03</month>
          <year>2025</year>
        </date>
      </history>
      <permissions>
        <license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by/4.0/" xml:lang="en">
          <license-p>Este &#233; um artigo de acesso aberto distribu&#237;do sob os termos da licen&#231;a de atribui&#231;&#227;o pelo Creative Commons</license-p>
        </license>
      </permissions>
      <abstract>
        <title>Resumo</title>
        <sec>
          <title>Fundamento</title>
          <p> Programas de treinamento f&#237;sico melhoram a capacidade de exerc&#237;cio e a qualidade de vida (QV) em pacientes com doen&#231;a arterial coronariana (DAC). Embora a intelig&#234;ncia artificial (IA) tenha sido utilizada no desenvolvimento desses programas, ainda s&#227;o escassos os estudos que avaliam sua efic&#225;cia.</p>
        </sec>
        <sec>
          <title>Objetivo</title>
          <p> Este estudo comparou os efeitos de programas de reabilita&#231;&#227;o card&#237;aca (RC) baseados em tecnologia com os programas tradicionais sobre a capacidade de exerc&#237;cio e a participa&#231;&#227;o de pacientes com DAC utilizando IA para an&#225;lise dos dados.</p>
        </sec>
        <sec>
          <title>M&#233;todos</title>
          <p> Um total de 52 pacientes com DAC foi distribu&#237;do aleatoriamente em tr&#234;s grupos: i) grupo de telereabilita&#231;&#227;o (GTR) (n=18); ii) grupo de aplicativo m&#243;vel (GAM) (n=13); e iii) grupo controle (GC), que recebeu apenas recomenda&#231;&#245;es de atividade f&#237;sica (n=21). Os participantes do GTR e do GAM completaram um programa de 12 semanas com exerc&#237;cios calist&#234;nicos e de resist&#234;ncia, tr&#234;s vezes por semana. A capacidade de exerc&#237;cio foi avaliada por meio do <italic>Incremental Shuttle Walk Test</italic> (ISWT), e a QV foi medida com o question&#225;rio Short Form-36 (SF-36). O feedback dos pacientes foi analisado utilizando um modelo de processamento de linguagem natural (PLN) baseado em BERT ajustado. M&#233;todos de detec&#231;&#227;o de anomalias foram aplicados para identificar diverg&#234;ncias entre a ades&#227;o autorrelatada e os resultados do ISWT. O n&#237;vel de signific&#226;ncia estat&#237;stica foi fixado em p&lt;0,05.</p>
        </sec>
        <sec>
          <title>Resultados</title>
          <p> Tanto o GTR [44,4% mulheres] (&#916;=87,2&#177;15,2 m) quanto o GAM [50% mulheres] (&#916;=89,4&#177;70,4 m) apresentaram melhora significativa no ISWT em compara&#231;&#227;o com o GC [47,6% mulheres] (&#916;=10,9&#177;28,2 m) (p=0,001). A ades&#227;o foi maior no GTR (100%) e no GAM (80%) do que no GC (30%) (p&lt;0,001). A satisfa&#231;&#227;o relatada pelos pacientes, analisada por PLN, mostrou correla&#231;&#227;o positiva significativa com os ganhos no ISWT (r=0,75, p&lt;0,001). Os achados demonstram o potencial da IA para apoiar a avalia&#231;&#227;o de resultados na RC.</p>
        </sec>
        <sec>
          <title>Conclus&#245;es</title>
          <p> Programas de RC baseados em tecnologia melhoram a capacidade de exerc&#237;cio e a ades&#227;o de pacientes com DAC, refor&#231;ando o uso de ferramentas com suporte de IA. A an&#225;lise por PLN ajudou a relacionar o feedback dos pacientes aos resultados do exerc&#237;cio e a detectar inconsist&#234;ncias, demonstrando seu valor na avalia&#231;&#227;o da RC.</p>
        </sec>
      </abstract>
      <abstract abstract-type="graphical">
        <p>
          <fig id="f01">
            <label>Figura Central:</label>
            <caption>
              <title>Impacto da Reabilita&#231;&#227;o Card&#237;aca Baseada em Tecnologia na Capacidade de Exerc&#237;cio e na Ades&#227;o de Pacientes com Doen&#231;a Arterial Coronariana: Uma An&#225;lise com Suporte de Intelig&#234;ncia Artificial</title>
            </caption>
            <alternatives>
              <graphic xlink:href="https://minio.scielo.br/documentstore/1678-4170/5V3LvX5sWqbmYHNkRWZPHyC/ffa95f34fcf98c516cf0d1107fb14fc9734349a2.tif"/>
              <graphic xlink:href="https://minio.scielo.br/documentstore/1678-4170/5V3LvX5sWqbmYHNkRWZPHyC/bca6f6734f73637b6d2f75d8924204dee82098b6.png" specific-use="scielo-web"/>
              <graphic xlink:href="https://minio.scielo.br/documentstore/1678-4170/5V3LvX5sWqbmYHNkRWZPHyC/2e3c9a2522bb2c175a8e627eee0f8e4e2e2d892b.jpg" specific-use="scielo-web" content-type="scielo-267x140"/>
            </alternatives>
          </fig>
        </p>
      </abstract>
      <kwd-group xml:lang="pt">
        <kwd>Intelig&#234;ncia Artificial</kwd>
        <kwd>Reabilita&#231;&#227;o Card&#237;aca</kwd>
        <kwd>Doen&#231;a da Art&#233;ria Coronariana</kwd>
        <kwd>Exerc&#237;cio F&#237;sico</kwd>
      </kwd-group>
      <counts>
        <fig-count count="8"/>
        <table-count count="6"/>
        <equation-count count="0"/>
        <ref-count count="41"/>
      </counts>
    </article-meta>
  </front>
  <body>
    <sec sec-type="intro">
      <title>Introdu&#231;&#227;o</title>
      <p>Programas de telereabilita&#231;&#227;o card&#237;aca (TRC) demonstraram oferecer benef&#237;cios e validade compar&#225;veis aos da reabilita&#231;&#227;o tradicional presencial para pacientes.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Beatty et al. confirmaram que a tecnologia m&#243;vel &#233; tanto confi&#225;vel quanto aceit&#225;vel para uso na reabilita&#231;&#227;o card&#237;aca (RC) de pacientes com doen&#231;a isqu&#234;mica do cora&#231;&#227;o.<sup><xref ref-type="bibr" rid="B2">2</xref></sup> O uso de tecnologia na RC contribui para melhorar o acesso e a participa&#231;&#227;o. Estudos demonstram que programas de RC baseados em exerc&#237;cios podem aumentar a capacidade de exerc&#237;cio, fortalecer a musculatura perif&#233;rica e melhorar a qualidade de vida (QV) de pacientes com doen&#231;a arterial coronariana (DAC).<sup><xref ref-type="bibr" rid="B3">3</xref>,<xref ref-type="bibr" rid="B4">4</xref></sup> Diretrizes cl&#237;nicas tamb&#233;m apoiam o uso seguro de treinamento aer&#243;bico e de resist&#234;ncia nessa popula&#231;&#227;o.<sup><xref ref-type="bibr" rid="B1">1</xref>,<xref ref-type="bibr" rid="B5">5</xref></sup> Calistenia &#233; outro m&#233;todo de exerc&#237;cio comumente utilizado em programas de RC.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
      <p>Nos &#250;ltimos anos, a RC tem adotado cada vez mais tecnologias como dispositivos de eletrocardiografia (ECG) para monitoramento remoto, sensores de frequ&#234;ncia card&#237;aca (FC) e press&#227;o arterial (PA), algoritmos para testes de capacidade funcional e rastreadores de atividade.<sup><xref ref-type="bibr" rid="B7">7</xref>,<xref ref-type="bibr" rid="B8">8</xref></sup> A TRC, a realidade virtual e as interven&#231;&#245;es em RC baseadas em telefone &#8212; que permitem o cuidado ao paciente sem supervis&#227;o direta &#8212; tamb&#233;m v&#234;m ganhando destaque na literatura.<sup><xref ref-type="bibr" rid="B9">9</xref>,<xref ref-type="bibr" rid="B10">10</xref></sup></p>
      <p>A intelig&#234;ncia artificial (IA) tem avan&#231;ado rapidamente na &#225;rea da sa&#250;de, especialmente em &#225;reas como interpreta&#231;&#227;o de imagens radiol&#243;gicas, previs&#227;o de desfechos e detec&#231;&#227;o precoce de eventos card&#237;acos.<sup><xref ref-type="bibr" rid="B11">11</xref>-<xref ref-type="bibr" rid="B15">15</xref></sup> O aprendizado de m&#225;quina tamb&#233;m demonstrou potencial para auxiliar na elabora&#231;&#227;o e avalia&#231;&#227;o da seguran&#231;a de programas de exerc&#237;cios para RC.<sup><xref ref-type="bibr" rid="B16">16</xref></sup> Al&#233;m disso, desafios t&#233;cnicos como a transpar&#234;ncia dos algoritmos, a seguran&#231;a dos dados e preocupa&#231;&#245;es &#233;ticas relacionadas &#224; privacidade dos pacientes continuam limitando o uso mais amplo da IA na TRC.<sup><xref ref-type="bibr" rid="B17">17</xref></sup> S&#227;o necess&#225;rias mais pesquisas e o desenvolvimento de melhores modelos de IA para aprimorar o uso cl&#237;nico e garantir desfechos seguros e centrados no paciente. Embora muitos estudos se concentrem no uso de dados dos pacientes para personalizar programas de exerc&#237;cios para indiv&#237;duos com DAC, poucos exploraram como a IA pode analisar as pr&#243;prias descri&#231;&#245;es dos pacientes sobre os benef&#237;cios percebidos com os programas.</p>
      <p>O processamento de linguagem natural (PLN) oferece uma abordagem promissora para extrair insights relevantes a partir de textos n&#227;o estruturados encontrados em prontu&#225;rios eletr&#244;nicos de sa&#250;de.<sup><xref ref-type="bibr" rid="B18">18</xref></sup> At&#233; o momento, nenhum estudo utilizou IA para interpretar as experi&#234;ncias subjetivas de pacientes com DAC em rela&#231;&#227;o aos benef&#237;cios de programas de RC baseados em exerc&#237;cios.</p>
      <p>A participa&#231;&#227;o em programas de RC continua baixa em todo o mundo. Um dos maiores desafios &#233; a n&#227;o ades&#227;o e a evas&#227;o por parte dos pacientes.<sup><xref ref-type="bibr" rid="B19">19</xref></sup> A pandemia de COVID-19 agravou esse problema, levando os profissionais de sa&#250;de a buscar solu&#231;&#245;es inovadoras para aumentar a participa&#231;&#227;o, a acessibilidade, a efici&#234;ncia e o custo-benef&#237;cio dos programas de RC.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> Nos Estados Unidos, apenas 20% a 30% dos pacientes eleg&#237;veis participam dos programas de RC. Entre aqueles que iniciam o programa, as taxas de evas&#227;o variam de 24% a 50%, o que significa que muitos pacientes n&#227;o recebem todos os benef&#237;cios da RC.<sup><xref ref-type="bibr" rid="B21">21</xref></sup> Para melhorar a participa&#231;&#227;o e a ades&#227;o, profissionais de sa&#250;de t&#234;m testado diversas estrat&#233;gias. Interven&#231;&#245;es bem-sucedidas incluem sistemas automatizados de encaminhamento e o uso de profissionais de refer&#234;ncia em RC para auxiliar os pacientes na transi&#231;&#227;o do hospital para o cuidado ambulatorial. Esses m&#233;todos demonstraram aumentar significativamente as taxas de ingresso e conclus&#227;o dos programas.<sup><xref ref-type="bibr" rid="B22">22</xref></sup></p>
      <p>No entanto, a pandemia de COVID-19 tornou ainda mais dif&#237;cil a participa&#231;&#227;o dos pacientes na RC, levando &#224; busca por novas formas de melhorar a acessibilidade, a efici&#234;ncia e o custo-benef&#237;cio desses programas. Uma solu&#231;&#227;o promissora &#233; o uso de modelos de RC domiciliares e h&#237;bridos, que combinam a reabilita&#231;&#227;o tradicional, realizada em centros especializados, com componentes remotos realizados em casa. Esses modelos t&#234;m se mostrado t&#227;o seguros e eficazes quanto a RC tradicional, oferecendo aos pacientes maior flexibilidade.<sup><xref ref-type="bibr" rid="B23">23</xref></sup></p>
      <p>Estudos recentes demonstraram que a IA pode ser integrada com sucesso &#224; cardiologia, especialmente em &#225;reas como a an&#225;lise de ECG e a imagem em cardiologia nuclear.<sup><xref ref-type="bibr" rid="B24">24</xref>,<xref ref-type="bibr" rid="B25">25</xref></sup> No entanto, at&#233; onde sabemos, este &#233; o primeiro estudo a aplicar m&#233;todos baseados em PLN no contexto da RC, representando uma contribui&#231;&#227;o in&#233;dita para a crescente interse&#231;&#227;o entre IA e cuidado cardiovascular.</p>
      <p>Este estudo teve como objetivo comparar os efeitos de programas de RC baseados em tecnologia com os programas tradicionais sobre a capacidade de exerc&#237;cio e a participa&#231;&#227;o de pacientes com DAC utilizando IA para a an&#225;lise dos dados.</p>
    </sec>
    <sec sec-type="methods">
      <title>M&#233;todos</title>
      <p>Este ensaio cl&#237;nico controlado, prospectivo e randomizado foi realizado entre abril de 2022 e maio de 2024 no the Department of Cardiorespiratory Physiotherapy and Rehabilitation, Faculty of Physiotherapy and Rehabilitation, Hacettepe University.</p>
      <p>Pacientes com diagn&#243;stico de DAC que compareceram ao ambulat&#243;rio de cardiologia foram avaliados quanto &#224; elegibilidade. Aqueles com diagn&#243;stico de DAC confirmado por angioplastia coronariana, com n&#237;veis de troponina negativos, estado cl&#237;nico est&#225;vel e teste de esfor&#231;o em esteira (protocolo de Bruce modificado) limitado por sintomas, sem sintomas card&#237;acos ou altera&#231;&#245;es no ECG, foram encaminhados a um fisioterapeuta para RC e inclu&#237;dos em um programa de exerc&#237;cios.</p>
      <p>Os crit&#233;rios de inclus&#227;o foram: i) estado cl&#237;nico est&#225;vel; ii) idade entre 40 e 70 anos; iii) acesso a treinamento f&#237;sico online; e iv) posse de um smartphone compat&#237;vel com iOS ou Android.</p>
      <p>Os crit&#233;rios de exclus&#227;o foram: i) diagn&#243;stico de insufici&#234;ncia card&#237;aca cr&#244;nica (classe III ou IV da <italic>New York Heart Association</italic> [NYHA]); ii) estenose &#8805;50% de qualquer art&#233;ria coron&#225;ria principal; qualquer evento coronariano ou revasculariza&#231;&#227;o cir&#250;rgica nos &#250;ltimos 12 meses; iv) fra&#231;&#227;o de eje&#231;&#227;o do ventr&#237;culo esquerdo (FEVE) &lt;40%; v) insufici&#234;ncia renal terminal; vi) miocardite ou pericardite aguda; vii) hipertens&#227;o n&#227;o controlada; viii) doen&#231;a pulmonar cr&#244;nica; ix) condi&#231;&#245;es ortop&#233;dicas ou neurol&#243;gicas que impe&#231;am a participa&#231;&#227;o em exerc&#237;cios ou testes; x) taquicardia ventricular sustentada; xi) fibrila&#231;&#227;o atrial de dif&#237;cil controle; ou xii) bloqueio atrioventricular de alto grau.</p>
      <p>Os participantes foram avaliados no in&#237;cio e ao final do programa de exerc&#237;cios de 12 semanas. Todas as avalia&#231;&#245;es seguiram a mesma ordem e foram realizadas de acordo com os padr&#245;es estabelecidos pelo fisioterapeuta respons&#225;vel. Dados demogr&#225;ficos, cl&#237;nicos e relacionados ao exerc&#237;cio foram coletados.</p>
      <p>Ap&#243;s as avalia&#231;&#245;es iniciais, os pacientes que atendiam aos crit&#233;rios de inclus&#227;o e concordaram em participar foram randomizados para um dos tr&#234;s grupos por meio da ferramenta online dispon&#237;vel em https://www.graphpad.com/quickcalcs/randomize1.cfm. O grupo de telereabilita&#231;&#227;o (GTR) realizou exerc&#237;cios calist&#234;nicos e de resist&#234;ncia sob supervis&#227;o remota de um fisioterapeuta por videoconfer&#234;ncia. O grupo de aplicativo m&#243;vel (GAM) seguiu os mesmos exerc&#237;cios individualmente, guiado por v&#237;deos em um aplicativo m&#243;vel. O grupo controle (GC) seguiu um programa padr&#227;o de exerc&#237;cios domiciliares sem supervis&#227;o.</p>
      <p>O <italic>Incremental Shuttle Walk Test</italic> (ISWT) foi utilizado para medir a capacidade de exerc&#237;cio devido &#224; sua validade e confiabilidade comprovadas em pacientes com DAC.<sup><xref ref-type="bibr" rid="B26">26</xref></sup> O teste &#233; composto por 12 n&#237;veis, durante os quais os participantes aumentam gradualmente a velocidade da caminhada a cada minuto. Um sinal sonoro os orienta a caminhar de um cone ao outro, posicionados a dez metros de dist&#226;ncia, e a dist&#226;ncia total percorrida &#233; registrada.</p>
      <p>O n&#250;mero total de sess&#245;es de exerc&#237;cio conclu&#237;das pelos participantes do GTR foi registrado. No caso do GAM, a presen&#231;a nas sess&#245;es foi monitorada por meio de notifica&#231;&#245;es enviadas automaticamente aos fisioterapeutas ap&#243;s cada sess&#227;o de exerc&#237;cio. Os participantes do GC foram orientados a manter um di&#225;rio de treinos para registrar os dias em que realizaram atividade f&#237;sica.</p>
      <p>Para avaliar QV, o question&#225;rio <italic>Short Form-36</italic> (SF-36) foi aplicado por meio de entrevista. O SF-36 &#233; um instrumento de autorrelato composto por 36 itens, desenvolvido para avaliar o estado geral de sa&#250;de do indiv&#237;duo. Ele abrange oito dom&#237;nios: capacidade funcional (CF), aspectos f&#237;sicos (AF), dor (D), estado geral de sa&#250;de (SG), vitalidade, aspectos sociais (AS), aspectos emocionais (AE) e sa&#250;de mental (SM).<sup><xref ref-type="bibr" rid="B27">27</xref></sup></p>
      <sec>
        <title>Protocolo de treinamento f&#237;sico</title>
        <p>Os participantes do GTR seguiram um programa de exerc&#237;cios online sob a supervis&#227;o de um fisioterapeuta. Aqueles do grupo GAM realizaram os exerc&#237;cios de forma independente, utilizando v&#237;deos disponibilizados por meio de um aplicativo m&#243;vel instalado em seus dispositivos pelo fisioterapeuta. Cada sess&#227;o inclu&#237;a um per&#237;odo de aquecimento e outro de desaquecimento.</p>
        <p>Durante as primeiras 4 semanas, os participantes realizaram exerc&#237;cios calist&#234;nicos e posturais. Entre as semanas 4 e 8, o treinamento de resist&#234;ncia para membros superiores e inferiores foi adicionado &#224; rotina calist&#234;nica. Os exerc&#237;cios de resist&#234;ncia foram realizados com faixas el&#225;sticas selecionadas de acordo com a for&#231;a muscular de cada indiv&#237;duo. A intensidade dos exerc&#237;cios foi ajustada por meio da varia&#231;&#227;o no n&#250;mero de repeti&#231;&#245;es e s&#233;ries, sendo permitido um intervalo de descanso de pelo menos 1 minuto entre as s&#233;ries.</p>
        <p>Da semana 9 &#224; 12, a dificuldade dos exerc&#237;cios foi aumentada progressivamente de acordo com o n&#237;vel de condicionamento f&#237;sico de cada participante. Todos os participantes dos grupos GTR e GAM realizaram os exerc&#237;cios tr&#234;s vezes por semana durante 12 semanas (<xref ref-type="fig" rid="f02">Figura 1</xref>, Arquivo Suplementar S1). Os participantes do GC foram orientados a seguir as Diretrizes de Atividade F&#237;sica da Organiza&#231;&#227;o Mundial da Sa&#250;de, que recomendam de 150-300 minutos de atividade f&#237;sica de moderada intensidade ou de 75-150 minutos de vigorosa intensidade por semana.<sup><xref ref-type="bibr" rid="B28">28</xref></sup></p>
        <p>
          <fig id="f02">
            <label>Figura 1</label>
            <caption>
              <title>&#8211; Diagrama de fluxo da inclus&#227;o dos pacientes no estudo. IA: intelig&#234;ncia artificial; FT: fisioterapeuta; GC: grupo controle; GAM: grupo aplicativo m&#243;vel; GTR: grupo de telereabilita&#231;&#227;o; ISWT: Incremental Shuttle Walk Test; PLN: processamento de linguagem natural; SF-36: Short-Form-36; TRC: telereabilita&#231;&#227;o card&#237;aca.</title>
            </caption>
            <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf01.tif"/></fig>
        </p>
        <p>Os participantes do GTR foram monitorados quanto &#224; fadiga, fadiga nas pernas e falta de ar por meio da escala de Borg modificada (mBS), juntamente com a aferi&#231;&#227;o da pr&#243;pria PA antes e ap&#243;s cada sess&#227;o de exerc&#237;cio. A intensidade do exerc&#237;cio foi ajustada para manter um n&#237;vel de esfor&#231;o percebido entre 4 e 6 na mBS. A FC foi monitorada continuamente por meio de um smartwatch (Mi Smart Band 4, Anhui Huami Information Technology Co., Ltd.), garantindo que os participantes atingissem de 60% a 75% da FC m&#225;xima (FCm&#225;x) e mantivessem um escore entre 4 e 6 na mBS durante o exerc&#237;cio.<sup><xref ref-type="bibr" rid="B29">29</xref></sup> Todos os dispositivos foram calibrados antes de serem entregues aos participantes.</p>
        <p>Os participantes do GAM autorrelataram fadiga, fadiga nas pernas e falta de ar utilizando a mBS antes e ap&#243;s cada sess&#227;o, seguindo as instru&#231;&#245;es em v&#237;deo dispon&#237;veis em seus celulares. Tamb&#233;m mediram e registraram a FC e a PA utilizando um <italic>smartwatch</italic> e um monitor de press&#227;o fornecidos. O aplicativo m&#243;vel inclu&#237;a um sistema de login seguro para proteger a privacidade dos pacientes.</p>
      </sec>
      <sec>
        <title>Intelig&#234;ncia artificial</title>
        <p>A efetividade dos exerc&#237;cios prescritos foi avaliada por meio do feedback regular dos pacientes sobre sua experi&#234;ncia com os exerc&#237;cios. Perguntas abertas em um question&#225;rio foram utilizadas para coletar respostas subjetivas, que, em seguida, foram analisadas com t&#233;cnicas de IA e aprendizado de m&#225;quina para extrair informa&#231;&#245;es quantitativas.</p>
        <p>Para identificar poss&#237;veis <italic>outliers</italic>, m&#233;todos de detec&#231;&#227;o de anomalias foram aplicados nos casos em que os pacientes relataram participa&#231;&#227;o consistente, mas apresentaram melhora limitada no desempenho no ISWT &#8212; por exemplo, um aumento inferior a 70 metros, mesmo quando 95% dos participantes aderentes apresentaram melhora de pelo menos essa dist&#226;ncia.</p>
        <p>Um modelo transformer pr&#233;-treinado &#8212; <italic>NLPtown/BERT-base-multilingual-uncased-sentiment</italic> &#8212; foi utilizado para avaliar o tom emocional do feedback de cada paciente (BERT = <italic>Bidirectional Encoder Representations from Transformers</italic>).<sup><xref ref-type="bibr" rid="B30">30</xref></sup> As respostas &#224;s perguntas abertas foram processadas com t&#233;cnicas de IA e PLN.</p>
        <p>A an&#225;lise por PLN foi realizada utilizando o modelo BERT para avaliar as respostas abertas dos pacientes.<sup><xref ref-type="bibr" rid="B31">31</xref></sup> O modelo foi ajustado com um conjunto de dados de sentimentos espec&#237;fico da &#225;rea da sa&#250;de, focado em feedback de pacientes. Esse conjunto inclu&#237;a avalia&#231;&#245;es subjetivas sobre a dificuldade dos exerc&#237;cios, benef&#237;cios percebidos, desafios relacionados &#224; ades&#227;o e satisfa&#231;&#227;o geral com o programa de CR. Foi constru&#237;do a partir de relatos an&#244;nimos de pacientes e feedbacks estruturados de estudos cl&#237;nicos anteriores, garantindo um conjunto diversificado de express&#245;es de sentimento.</p>
        <p>O desempenho do modelo foi validado por meio de valida&#231;&#227;o cruzada <italic>k-fold</italic>, alcan&#231;ando uma pontua&#231;&#227;o F1 m&#233;dia de 0,89, o que indica alta confiabilidade na classifica&#231;&#227;o de sentimentos. A an&#225;lise por PLN concentrou-se em dois aspectos principais: satisfa&#231;&#227;o geral com o programa e relatos sobre a dificuldade ou facilidade dos exerc&#237;cios.</p>
        <p>Para cada resposta dos pacientes, o pipeline de an&#225;lise de sentimentos atribuiu um r&#243;tulo de sentimento e uma pontua&#231;&#227;o correspondente de 1 a 5 (1 = altamente negativo, 5 = altamente positivo), representando a intensidade do tom emocional.</p>
        <p>Todas as medidas foram adotadas para proteger os dados contra acesso de terceiros. Todas as medidas de compliance foram monitoradas regularmente.</p>
      </sec>
      <sec>
        <title>An&#225;lise estat&#237;stica</title>
        <p>A an&#225;lise estat&#237;stica foi realizada utilizando o software IBM SPSS (vers&#227;o 20.0, IBM Inc.). Um estudo piloto indicou que seriam necess&#225;rios pelo menos 11 participantes por grupo para alcan&#231;ar um poder estat&#237;stico de 95%, com uma chance de erro tipo I de 5% e tamanho de efeito de 1,76 para o desfecho prim&#225;rio (dist&#226;ncia no ISWT).</p>
        <p>O teste de Shapiro-Wilk foi utilizado para verificar se os dados seguiam uma distribui&#231;&#227;o normal. Vari&#225;veis cont&#237;nuas com distribui&#231;&#227;o normal foram expressas como m&#233;dia &#177; desvio padr&#227;o (DP), enquanto aquelas sem distribui&#231;&#227;o normal foram apresentadas como mediana e intervalo interquartil. Vari&#225;veis categ&#243;ricas foram apresentadas como frequ&#234;ncias absolutas (contagens) e relativas (percentuais).</p>
        <p>Para compara&#231;&#245;es dentro de cada grupo, foi utilizado o teste t pareado para dados com distribui&#231;&#227;o normal e o teste de Wilcoxon para dados sem distribui&#231;&#227;o normal. Para compara&#231;&#227;o entre grupos, foi utilizada a an&#225;lise de vari&#226;ncia (ANOVA) unidirecional para vari&#225;veis com distribui&#231;&#227;o normal, com o teste de Tukey (<italic>honestly significant difference</italic> [HSD]) para compara&#231;&#245;es p&#243;s-hoc entre pares. Para dados sem distribui&#231;&#227;o normal, utilizou-se o teste de Kruskal-Wallis, seguido pelo teste de Dunn para compara&#231;&#245;es entre pares. Vari&#225;veis categ&#243;ricas foram analisadas por meio do teste do qui-quadrado ou, quando as contagens esperadas foram inferiores a 5, pelo teste exato de Fisher.</p>
        <p>O coeficiente de correla&#231;&#227;o de Pearson foi utilizado para avaliar a rela&#231;&#227;o entre o feedback em linguagem natural dos pacientes sobre os benef&#237;cios do treinamento f&#237;sico e as mudan&#231;as no desempenho no ISWT. Foi aplicada uma an&#225;lise por inten&#231;&#227;o de tratar, incluindo os dados pr&#233;vios ao exerc&#237;cio dos participantes que n&#227;o completaram o programa. Um valor p igual ou inferior a 0,05 foi considerado estatisticamente significativo.</p>
      </sec>
    </sec>
    <sec sec-type="results">
      <title>Resultados</title>
      <p>Dos 147 pacientes com DAC avaliados no ambulat&#243;rio de cardiologia da Faculty of Medicine, Hacettepe University, 55 atenderam aos crit&#233;rios de inclus&#227;o e concordaram em participar do estudo. Tr&#234;s participantes do grupo GAM desistiram, e o estudo foi conclu&#237;do com um total de 52 participantes. A <xref ref-type="fig" rid="f03">Figura 2</xref> apresenta o diagrama de fluxo do estudo.</p>
      <p>
        <fig id="f03">
          <label>Figura 2</label>
          <caption>
            <title>&#8211; Diagrama de fluxo CONSORT da inclus&#227;o dos pacientes no estudo. CONSORT: Consolidated Standards of Reporting Trials; GAM: grupo aplicativo m&#243;vel; GC: grupo controle; GTR: grupo de telereabilita&#231;&#227;o.</title>
          </caption>
          <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf02.tif"/></fig>
      </p>
      <p>A <xref ref-type="table" rid="t1">Tabela 1</xref> apresenta as caracter&#237;sticas demogr&#225;ficas e cl&#237;nicas dos pacientes. N&#227;o houve diferen&#231;as estatisticamente significativas entre os grupos em rela&#231;&#227;o &#224; idade, peso corporal, estatura, &#237;ndice de massa corporal (IMC), rela&#231;&#227;o cintura-quadril, fatores de risco cardiovascular ou valores de equivalente metab&#243;lico de tarefa (MET) obtidos no teste de esfor&#231;o.</p>
      <p>
        <table-wrap id="t1">
          <label>Tabela 1</label>
          <caption>
            <title>&#8211; Caracter&#237;sticas demogr&#225;ficas dos pacientes inclu&#237;dos no estudo</title>
          </caption>
          <table frame="hsides" rules="groups">
            <colgroup>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
            </colgroup>
            <thead>
              <tr>
                <th align="left">Vari&#225;veis</th>
                <th>GTR (n=18)</th>
                <th>GAM (n=16)</th>
                <th>GC (n=21)</th>
                <th>Valor p</th>
              </tr>
            </thead>
            <tbody>
              <tr>
                <td>Idade (anos)</td>
                <td align="center">60,1&#177;7,2</td>
                <td align="center">56,9&#177;5,8</td>
                <td align="center">61,6&#177;1,5</td>
                <td align="center">0,12</td>
              </tr>
              <tr>
                <td>Mulheres/homens</td>
                <td align="center">8 (44,4%)/10 (55,6%)</td>
                <td align="center">8 (50%)/8 (50%)</td>
                <td align="center">10 (47,6%)/11 (52,4%)</td>
                <td align="center">0,95</td>
              </tr>
              <tr>
                <td>Peso (kg)</td>
                <td align="center">76,9&#177;3,1</td>
                <td align="center">80,9&#177;10,3</td>
                <td align="center">79,7&#177;2,7</td>
                <td align="center">0,61</td>
              </tr>
              <tr>
                <td>IMC (kg/m<sup>2</sup>)</td>
                <td align="center">26,2&#177;0,6</td>
                <td align="center">27,3&#177;1,9</td>
                <td align="center">28,5&#177;1,1</td>
                <td align="center">0,12</td>
              </tr>
              <tr>
                <td>Rela&#231;&#227;o cintura-quadril</td>
                <td align="center">0,9&#177;0,1</td>
                <td align="center">0,9&#177;0,1</td>
                <td align="center">0,9&#177;0,1</td>
                <td align="center">0,54</td>
              </tr>
              <tr>
                <td>N&#250;mero de passos por dia</td>
                <td align="center">3,578.5 (2,622,5-4,345,5)</td>
                <td align="center">3,981.5 (3,418-4,744.25)</td>
                <td align="center">3,177 (3,962-2,585)</td>
                <td align="center">0,15</td>
              </tr>
              <tr>
                <td>Teste de esfor&#231;o (METs)</td>
                <td align="center">11,05 (10,3-13,2)</td>
                <td align="center">10,9 (10,1-12,8)</td>
                <td align="center">10,5 (9,5-11,4)</td>
                <td align="center">0,35</td>
              </tr>
              <tr>
                <td colspan="5">
                  <bold>Fatores de risco cardiovascular</bold>
                </td>
              </tr>
              <tr>
                <td colspan="5">
                  <bold>Tabagismo</bold>
                </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>N&#227;o fumante</td>
                <td align="center">8 (44,4%)</td>
                <td align="center">7 (43,75%)</td>
                <td align="center">10 (47,6%)</td>
                <td align="center" rowspan="3">0,91</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Fumante</td>
                <td align="center">4 (22,2%)</td>
                <td align="center">3 (18,75%)</td>
                <td align="center">6 (28,6%)</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Ex-fumante</td>
                <td align="center">6 (33,3%)</td>
                <td align="center">6 (37,5%)</td>
                <td align="center">5 (23,8%)</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Tabagismo (ma&#231;os-ano)</td>
                <td align="center">14,8&#177;15,9</td>
                <td align="center">13,4&#177;13,6</td>
                <td align="center">16,1&#177;17,4</td>
                <td align="center">0,93</td>
              </tr>
              <tr>
                <td>
                  <bold>Hipertens&#227;o</bold>
                </td>
                <td align="center">10 (55,6%)</td>
                <td align="center">8 (50,0%)</td>
                <td align="center">9 (42,9%)</td>
                <td align="center">0,73</td>
              </tr>
              <tr>
                <td>
                  <bold>Diabetes melito</bold>
                </td>
                <td align="center">4 (22,2%)</td>
                <td align="center">4 (25,0%)</td>
                <td align="center">5 (23,8%)</td>
                <td align="center">0,98</td>
              </tr>
              <tr>
                <td>
                  <bold>Dislipidemia</bold>
                </td>
                <td align="center">14 (77,8%)</td>
                <td align="center">13 (81,25%)</td>
                <td align="center">18 (85,7%)</td>
                <td align="center">0,81</td>
              </tr>
              <tr>
                <td>
                  <bold>Inatividade f&#237;sica</bold>
                </td>
                <td align="center">17 (94,4%)</td>
                <td align="center">13 (81,25%)</td>
                <td align="center">20 (95,2%)</td>
                <td align="center">0,28</td>
              </tr>
            </tbody>
          </table>
          <table-wrap-foot>
            <fn id="TFN1">
              <p>*p&lt;0,05, teste do qui-quadrado, teste exato de Fisher, an&#225;lise de vari&#226;ncia (ANOVA) ou teste de Kruskal-Wallis. Os dados s&#227;o apresentados como m&#233;dia&#177;DP, mediana (IIQ [Q1&#8211;Q3]) ou n (%). GAM: grupo aplicativo m&#243;vel; GC: grupo controle; GTR: grupo de telereabilita&#231;&#227;o; IIQ: intervalo interquartil; IMC: &#237;ndice de massa corporal; MET: equivalente metab&#243;lico de tarefa.</p>
            </fn>
          </table-wrap-foot>
        </table-wrap>
      </p>
      <p>N&#227;o foram encontradas diferen&#231;as estatisticamente significativas entre os grupos quanto &#224; dist&#226;ncia no ISWT, FC, PA sist&#243;lica e diast&#243;lica, dispneia ou n&#237;veis de fadiga geral (avaliados pela escala de Borg modificada) antes do in&#237;cio do treinamento f&#237;sico (<xref ref-type="table" rid="t2">Tabela 2</xref>). Tanto o GTR quanto o GAM apresentaram melhorias semelhantes em diversas subescalas de QV do SF-36 (ou seja, CF, D, SG, AS, vitalidade, AE e SM) em compara&#231;&#227;o com o grupo controle. Ambos os grupos tamb&#233;m apresentaram melhores resultados na porcentagem da dist&#226;ncia esperada no ISWT em rela&#231;&#227;o ao grupo controle.</p>
      <p>
        <table-wrap id="t2">
          <label>Tabela 2</label>
          <caption>
            <title>&#8211; RC de tr&#234;s meses: compara&#231;&#227;o entre grupos quanto aos desfechos</title>
          </caption>
          <table frame="hsides" rules="groups">
            <colgroup>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
            </colgroup>
            <thead>
              <tr>
                <th align="left" rowspan="2">Par&#226;metros de capacidade de exerc&#237;cio</th>
                <th colspan="3">GTR (n=18)</th>
                <th colspan="3">GAM (n=13)</th>
                <th colspan="3">GC (n=21)</th>
              </tr>
              <tr>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>&#916;</th>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>P&#243;s-interven&#231;&#227;o</th>
                <th>&#916;</th>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>P&#243;s-interven&#231;&#227;o</th>
                <th>&#916;</th>
              </tr>
            </thead>
            <tbody>
              <tr>
                <td>
                  <bold>FC (bpm)</bold>
                </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Pr&#233;-teste</td>
                <td align="center">79,2&#177;10,5</td>
                <td align="center">
                  <bold>76,8&#177;10,9</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">-2,4&#177;3,1</td>
                <td align="center">74,8&#177;11,7</td>
                <td align="center">72,6&#177;7,9</td>
                <td align="center">-2,2&#177;5,9</td>
                <td align="center">85,1&#177;13,9</td>
                <td align="center">84,6&#177;11,9</td>
                <td align="center">-0,5&#177;4,3</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>P&#243;s-teste</td>
                <td align="center">135,6&#177;6,6</td>
                <td align="center">
                  <bold>132,1&#177;6,3</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">-3,5&#177;5,3</td>
                <td align="center">136,9&#177;5,5</td>
                <td align="center">137,9&#177;4,5</td>
                <td align="center">0,9&#177;3,4</td>
                <td align="center">133,3&#177;5,9</td>
                <td align="center">134,4&#177;4,5</td>
                <td align="center">1,1&#177;4,3</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>%FCm&#225;x</td>
                <td align="center">84,8&#177;1,6</td>
                <td align="center">
                  <bold>82,6&#177;2,9</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>-2,2&#177;3,3</bold>
                  <sup>
                    <bold>b,d</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">84&#177;1,6</td>
                <td align="center">84,2&#177;13</td>
                <td align="center">0,2&#177;1,2</td>
                <td align="center">84,2&#177;2,1</td>
                <td align="center">84,9&#177;2,6</td>
                <td align="center">0,7&#177;2,7</td>
              </tr>
              <tr>
                <td>
                  <bold>PAD (mmHg)</bold>
                </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Pr&#233;-teste</td>
                <td align="center">73,3&#177;7,7</td>
                <td align="center">70,6&#177;6,4</td>
                <td align="center">-2,8&#177;6,7</td>
                <td align="center">70,6&#177;7,7</td>
                <td align="center">70&#177;5,2</td>
                <td align="center">-0,6&#177;5,7</td>
                <td align="center">70&#177;7,7</td>
                <td align="center">70&#177;6,3</td>
                <td align="center">0&#177;5,5</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>P&#243;s-teste</td>
                <td align="center">82,2&#177;7,3</td>
                <td align="center">80&#177;6,9</td>
                <td align="center">-2,2&#177;7,3</td>
                <td align="center">80&#177;8,2</td>
                <td align="center">79,2&#177;5,7</td>
                <td align="center">-0,8&#177;6,8</td>
                <td align="center">76,2&#177;8,1</td>
                <td align="center">78,6&#177;7,3</td>
                <td align="center">2,4&#177;5,4</td>
              </tr>
              <tr>
                <td>
                  <bold>PAS (mmHg)</bold>
                </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Pr&#233;-teste</td>
                <td align="center">118,3&#177;8,6</td>
                <td align="center">118,9&#177;8,3</td>
                <td align="center">0,6&#177;4,2</td>
                <td align="center">118,1&#177;9,8</td>
                <td align="center">118,5&#177;8,1</td>
                <td align="center">0,3&#177;5,8</td>
                <td align="center">118,6&#177;7,3</td>
                <td align="center">121,9&#177;8,1</td>
                <td align="center">3,3&#177;8</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>P&#243;s-teste</td>
                <td align="center">148,3&#177;9,9</td>
                <td align="center">148,3&#177;2,4</td>
                <td align="center">0&#177;12,4</td>
                <td align="center">145&#177;6,3</td>
                <td align="center">146,2&#177;12,4</td>
                <td align="center">1,2&#177;12,8</td>
                <td align="center">146,2&#177;9,2</td>
                <td align="center">149,5&#177;8,6</td>
                <td align="center">3,3&#177;11,1</td>
              </tr>
              <tr>
                <td>
                  <bold>Fadiga geral (mBorg)</bold>
                </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Pr&#233;-teste</td>
                <td align="center">0,5 (0-1)</td>
                <td align="center">0,5 (0-0,8)</td>
                <td align="center">0 (-0,5, 0)</td>
                <td align="center">0,5 (0-1)</td>
                <td align="center">0,5 (0,5-1)</td>
                <td align="center">0 (-0,5, 0,5)</td>
                <td align="center">1 (0-1)</td>
                <td align="center">0,5 (0-1)</td>
                <td align="center">0 (-1, 0)</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>P&#243;s-teste</td>
                <td align="center">4 (3-5,75)</td>
                <td align="center">4,5 (3-5)</td>
                <td align="center">0 (-0,75, 1,75)</td>
                <td align="center">4 (3-5)</td>
                <td align="center">5 (4-5)</td>
                <td align="center">1 (-1, 2)</td>
                <td align="center">5 (3-5)</td>
                <td align="center">3 (3-4)</td>
                <td align="center">1 (-2, 0)</td>
              </tr>
              <tr>
                <td>
                  <bold>Dispneia (mBorg)</bold>
                </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
                <td colspan="3"> </td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>Pr&#233;-teste</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0, 0)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0, 0)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td><italic><bold> </bold></italic>P&#243;s-teste</td>
                <td align="center">0 (0-1)</td>
                <td align="center">1 (0-2)</td>
                <td align="center">0 (0, 2)</td>
                <td align="center">0 (0-0)</td>
                <td align="center">0 (0-1)</td>
                <td align="center">0 (0, 1)</td>
                <td align="center">0 (0-0,5)</td>
                <td align="center">0 (0-0,5)</td>
                <td align="center">0 (0, 0,5)</td>
              </tr>
              <tr>
                <td>
                  <bold>Dist&#226;ncia no ISWT (m)</bold>
                </td>
                <td align="center">508,9&#177;105,5</td>
                <td align="center">
                  <bold>596,1&#177;109,3</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>87,2&#177;15,3</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">537,5&#177;119,1</td>
                <td align="center">
                  <bold>626,9&#177;92,1</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>89,4&#177;70,4</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">500,5&#177;98,4</td>
                <td align="center">511,4&#177;102</td>
                <td align="center">11&#177;28,3</td>
              </tr>
              <tr>
                <td>
                  <bold>Dist&#226;ncia no ISWT (%)</bold>
                </td>
                <td align="center">70,8&#177;9,3</td>
                <td align="center">
                  <bold>83,3&#177;10,4</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>12,5&#177;3,4</bold>
                  <sup>
                    <bold>b,d</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">72,6&#177;8,4</td>
                <td align="center">
                  <bold>83,1&#177;9</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10,5&#177;3,6</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">73,2&#177;8,7</td>
                <td align="center">74,6&#177;7,5</td>
                <td align="center">1,5&#177;4,1</td>
              </tr>
            </tbody>
          </table>
          <table-wrap-foot>
            <fn id="TFN2">
              <p>*p&lt;0,05, an&#225;lise de vari&#226;ncia (ANOVA) ou teste de Kruskal-Wallis. Os dados s&#227;o apresentados como m&#233;dia&#177;DP ou mediana (IIQ [Q1&#8211;Q3]). %FCm&#225;x: porcentagem da frequ&#234;ncia card&#237;aca m&#225;xima; DP: desvio padr&#227;o; FC: frequ&#234;ncia card&#237;aca; GAM: grupo aplicativo m&#243;vel; GC: grupo controle; GTR: grupo de telereabilita&#231;&#227;o; IIQ: intervalo interquartil; ISWT: Incremental Shuttle Walk Test; mBorg: escala de Borg modificada; PA: press&#227;o arterial; PAD: press&#227;o arterial diast&#243;lica; PAS: press&#227;o arterial sist&#243;lica; RC: reabilita&#231;&#227;o card&#237;aca; SpO<sub>2</sub>: satura&#231;&#227;o de oxig&#234;nio. a: Diferen&#231;a significativa entre o pr&#233; e o p&#243;s-exerc&#237;cio dentro do mesmo grupo; b: Diferen&#231;a significativa entre GTR e GC. c: Diferen&#231;a significativa entre GAM e GC; d: Diferen&#231;a significativa entre GTR e GAM.</p>
            </fn>
          </table-wrap-foot>
        </table-wrap>
      </p>
      <p>Esses achados sugerem que as interven&#231;&#245;es nos grupos GTR e GAM proporcionaram benef&#237;cios semelhantes na melhora da QV e da capacidade funcional. Al&#233;m disso, o GTR apresentou um aumento percentual significativamente maior na dist&#226;ncia esperada no ISWT em compara&#231;&#227;o com o grupo GAM (<xref ref-type="table" rid="t2">Tabela 2</xref>).</p>
      <p>Os escores de fadiga geral e dispneia, avaliados pela escala de Borg modificada, n&#227;o apresentaram diferen&#231;as significativas entre ou dentro dos grupos antes e ap&#243;s o programa de exerc&#237;cios. Da mesma forma, a PA sist&#243;lica e diast&#243;lica permaneceu inalterada entre e dentro dos grupos (<xref ref-type="table" rid="t2">Tabela 2</xref>). Esses resultados sugerem que essas medidas fisiol&#243;gicas se mantiveram est&#225;veis ao longo da interven&#231;&#227;o em todos os grupos.</p>
      <p>As varia&#231;&#245;es na FC (&#916;FC) antes e ap&#243;s o exerc&#237;cio, assim como a porcentagem da FCm&#225;x (%FCm&#225;x), foram significativamente menores no GTR ap&#243;s o programa de exerc&#237;cios e tamb&#233;m em compara&#231;&#227;o com os grupos GAM e GC (<xref ref-type="table" rid="t2">Tabela 2</xref>). O GC n&#227;o apresentou altera&#231;&#245;es significativas nas medidas de capacidade de exerc&#237;cio (<xref ref-type="table" rid="t2">Tabela 2</xref>).</p>
      <p>O GTR completou 100% das sess&#245;es planejadas, o GAM completou 80% e o GC completou 30%. Tanto o GTR quanto o GAM apresentaram taxas de comparecimento significativamente maiores em compara&#231;&#227;o ao GC.</p>
      <p>Os escores iniciais das subescalas do SF-36 foram semelhantes entre todos os grupos (<xref ref-type="table" rid="t3">Tabela 3</xref>). Ap&#243;s o programa de exerc&#237;cios, tanto o GTR quanto o GAM apresentaram melhorias significativas nas subescalas do SF-36 para CF, AF, D, SG, vitalidade, AS, AE e SM em compara&#231;&#227;o aos seus escores iniciais (<xref ref-type="table" rid="t3">Tabela 3</xref>). O GC n&#227;o apresentou altera&#231;&#245;es significativas em nenhuma subescala do SF-36 ap&#243;s a interven&#231;&#227;o (<xref ref-type="table" rid="t3">Tabela 3</xref>).</p>
      <p>
        <table-wrap id="t3">
          <label>Tabela 3</label>
          <caption>
            <title>&#8211; Compara&#231;&#227;o das subescalas de QV do SF-36 entre os grupos antes e ap&#243;s o treinamento f&#237;sico</title>
          </caption>
          <table frame="hsides" rules="groups">
            <colgroup>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
              <col/>
            </colgroup>
            <thead>
              <tr>
                <th align="left" rowspan="2">Subescalas do SF-36</th>
                <th colspan="3">GTR (n=18)</th>
                <th colspan="3">GAM (n=13)</th>
                <th colspan="3">GC (n=21)</th>
              </tr>
              <tr>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>P&#243;s-interven&#231;&#227;o</th>
                <th>&#916;</th>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>P&#243;s-interven&#231;&#227;o</th>
                <th>&#916;</th>
                <th>Pr&#233;-interven&#231;&#227;o</th>
                <th>P&#243;s-interven&#231;&#227;o</th>
                <th>&#916;</th>
              </tr>
            </thead>
            <tbody>
              <tr>
                <td>Capacidade funcional</td>
                <td align="center">85 (75-88,8)</td>
                <td align="center">
                  <bold>90 (86,3-95)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>5 (0, 15)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">80 (65-90)</td>
                <td align="center">
                  <bold>95 (85-95)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>5 (0, 10)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">90 (75-90)</td>
                <td align="center">80 (75-90)</td>
                <td align="center">0 (-5, 5)</td>
              </tr>
              <tr>
                <td>Aspectos f&#237;sicos</td>
                <td align="center">100 (75-100)</td>
                <td align="center">100 (100-100)</td>
                <td align="center">0 (0, 0)</td>
                <td align="center">100 (50-100)</td>
                <td align="center">100 (50-100)</td>
                <td align="center">0 (0, 0)</td>
                <td align="center">100 (75-100)</td>
                <td align="center">100 (75-100)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Aspectos emocionais</td>
                <td align="center">67 (33-100)</td>
                <td align="center">
                  <bold>100 (72,3-100)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>0 (0, 67)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">67 (33-67)</td>
                <td align="center">
                  <bold>100 (67-100)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>33 (0, 34)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">67 (33-100)</td>
                <td align="center">67 (33-100)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Vitalidade</td>
                <td align="center">67,5 (61,3-75)</td>
                <td align="center">
                  <bold>75 (70-78,8)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>5 (0, 13,8)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">65 (50-75)</td>
                <td align="center">
                  <bold>75 (75-90)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (10, 35)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">65 (50-75)</td>
                <td align="center">55 (35-75)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Sa&#250;de mental</td>
                <td align="center">76 (62-79)</td>
                <td align="center">
                  <bold>87 (76-96)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (0, 20)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">68 (44-80)</td>
                <td align="center">
                  <bold>80 (76-92)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>8 (0, 32)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">64 (44-76)</td>
                <td align="center">60 (40-68)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Aspectos sociais</td>
                <td align="center">75 (66-88)</td>
                <td align="center">
                  <bold>88 (75-100)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>0 (0, 12,8)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">75 (63-100)</td>
                <td align="center">
                  <bold>88 (75-100)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>0 (0, 12)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">88 (75-100)</td>
                <td align="center">75 (75-88)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Dor</td>
                <td align="center">75 (49,8-90)</td>
                <td align="center">
                  <bold>85 (68-97,5)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (0, 12,3)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">70 (55-80)</td>
                <td align="center">
                  <bold>80 (68-90)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (3, 13)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">80 (68-100)</td>
                <td align="center">80 (68-100)</td>
                <td align="center">0 (0, 0)</td>
              </tr>
              <tr>
                <td>Estado geral de sa&#250;de</td>
                <td align="center">60 (46,3-70)</td>
                <td align="center">
                  <bold>75 (56,3-78,8)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (0, 18)</bold>
                  <sup>
                    <bold>b</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">60 (45-75)</td>
                <td align="center">
                  <bold>75 (75-85)</bold>
                  <sup>
                    <bold>a</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">
                  <bold>10 (5, 15)</bold>
                  <sup>
                    <bold>c</bold>
                  </sup>
                  <bold>*</bold>
                </td>
                <td align="center">60 (45-70)</td>
                <td align="center">50 (45-75)</td>
                <td align="center">0 (0, 5)</td>
              </tr>
            </tbody>
          </table>
          <table-wrap-foot>
            <fn id="TFN3">
              <p>*p&lt;0,05, teste de Kruskal&#8211;Wallis. Os dados s&#227;o apresentados como mediana (IIQ [Q1&#8211;Q3]). GAM: grupo aplicativo m&#243;vel; GC: grupo controle; GTR: grupo de telereabilita&#231;&#227;o; IIQ: intervalo interquartil; SF-36: Short Form-36; QV: qualidade de vida. a: Diferen&#231;a significativa entre pr&#233; e p&#243;s-exerc&#237;cio dentro do mesmo grupo; b: Diferen&#231;a significativa entre GTR e GC; c: Diferen&#231;a significativa entre GAM e GC; d: Diferen&#231;a significativa entre GTR e GAM.</p>
            </fn>
          </table-wrap-foot>
        </table-wrap>
      </p>
      <p>Ao comparar as varia&#231;&#245;es entre os grupos, tanto o GTR quanto o GAM apresentaram melhorias significativamente maiores que o GC nas subescalas CF, D, SG, vitalidade, AS, AE e SM (<xref ref-type="table" rid="t3">Tabela 3</xref>). N&#227;o foram encontradas diferen&#231;as estatisticamente significativas entre o GTR e o GAM em nenhuma das subescalas do SF-36 (<xref ref-type="table" rid="t3">Tabela 3</xref>, <xref ref-type="fig" rid="f01">Figura Central</xref>).</p>
      <sec>
        <title>Processamento de linguagem natural com intelig&#234;ncia artificial</title>
        <p>Um total de 52 pacientes com DAC compartilhou feedback subjetivo sobre os benef&#237;cios do programa de exerc&#237;cios. As pontua&#231;&#245;es de sentimento foram distribu&#237;das da seguinte forma: 55% atribu&#237;ram nota 5; 2%, nota 4; 12%, nota 3; 12%, nota 2; e 19%, nota 1.</p>
        <p>De acordo com o ISWT, uma melhora m&#237;nima de 70,0 metros (IC 95%: 51,5&#8211;88,5 m) foi considerada um desfecho positivo.<sup><xref ref-type="bibr" rid="B32">32</xref></sup> Neste estudo, 59,62% dos participantes ultrapassaram esse limite, sendo 51,5 metros o valor de refer&#234;ncia utilizado. Entre os que superaram o limiar, 75% relataram alta satisfa&#231;&#227;o (pontua&#231;&#227;o 5), enquanto apenas 25% dos que ficaram abaixo desse valor relataram alta satisfa&#231;&#227;o.</p>
        <p>Houve uma correla&#231;&#227;o positiva forte entre a satisfa&#231;&#227;o autorrelatada pelos pacientes e a melhora no desempenho no ISWT (r=0,75; p&lt;0,001). Tamb&#233;m foi observada uma correla&#231;&#227;o positiva moderada entre o n&#250;mero de sess&#245;es de exerc&#237;cio conclu&#237;das e as pontua&#231;&#245;es de satisfa&#231;&#227;o (r=0,410).</p>
        <p>Para aprofundar a an&#225;lise da satisfa&#231;&#227;o dos pacientes e das melhorias observadas por meio da PLN, as tend&#234;ncias de sentimento foram examinadas entre subgrupos com base na ades&#227;o ao exerc&#237;cio e no desempenho no ISWT. Uma an&#225;lise mais detalhada dos casos at&#237;picos revelou que alguns pacientes que relataram alta satisfa&#231;&#227;o, apesar de apresentarem ganhos limitados no ISWT, frequentemente destacaram benef&#237;cios psicol&#243;gicos (como aumento da motiva&#231;&#227;o, redu&#231;&#227;o da ansiedade e maior sensa&#231;&#227;o de bem-estar) em vez de melhorias f&#237;sicas.</p>
        <p>O modelo identificou uma rela&#231;&#227;o significativa entre a satisfa&#231;&#227;o autorrelatada pelos pacientes e os desfechos do exerc&#237;cio medidos objetivamente, com IC 95%. T&#233;cnicas de detec&#231;&#227;o de anomalias, incluindo m&#233;todos baseados em agrupamento e em dist&#226;ncia, foram utilizadas para identificar discrep&#226;ncias entre a satisfa&#231;&#227;o subjetiva e o desempenho real. O modelo sinalizou anomalias em 10% dos pacientes que relataram alta satisfa&#231;&#227;o, apesar de apresentarem melhora m&#237;nima nos resultados do ISWT.</p>
        <p>A <xref ref-type="fig" rid="f04">Figura 3</xref> apresenta o mapa de emo&#231;&#245;es gerado por meio da detec&#231;&#227;o de anomalias e a distribui&#231;&#227;o das pontua&#231;&#245;es de satisfa&#231;&#227;o dos pacientes em rela&#231;&#227;o ao valor de refer&#234;ncia.</p>
        <p>
          <fig id="f04">
            <label>Figura 3</label>
            <caption>
              <title>&#8211; Gr&#225;fico de dispers&#227;o mostrando a rela&#231;&#227;o entre os resultados da an&#225;lise por PLN e as varia&#231;&#245;es na dist&#226;ncia do ISWT. &#916;ISWT: varia&#231;&#227;o na dist&#226;ncia do Incremental Shuttle Walk Test. Pontua&#231;&#245;es de avalia&#231;&#227;o: 1 = N&#227;o teve nenhum benef&#237;cio, 2 = N&#227;o teve benef&#237;cio, 3 = Nem teve nem deixou de ter benef&#237;cio, 4 = Teve benef&#237;cio, 5 = Teve grande benef&#237;cio. Os valores dentro dos c&#237;rculos representam anomalias. O modelo identificou como anomalias os pacientes que relataram alta satisfa&#231;&#227;o, apesar de apresentarem pouca melhora no ISWT, correspondendo a 10% da amostra.</title>
            </caption>
            <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf03.tif"/></fig>
        </p>
      </sec>
    </sec>
    <sec sec-type="discussion">
      <title>Discuss&#227;o</title>
      <p>Uma revis&#227;o de literatura pr&#233;via mostra que a integra&#231;&#227;o da IA na TRC tem potencial para apoiar a detec&#231;&#227;o precoce de eventos card&#237;acos, melhorar o monitoramento de programas domiciliares e aprimorar a tomada de decis&#227;o cl&#237;nica.<sup><xref ref-type="bibr" rid="B33">33</xref></sup> Por exemplo, dispositivos vest&#237;veis utilizados na TRC podem avaliar com precis&#227;o a capacidade funcional do paciente por meio de algoritmos baseados em IA.<sup><xref ref-type="bibr" rid="B34">34</xref></sup></p>
      <p>Neste estudo, a PLN foi aplicada para demonstrar a efetividade da RC baseada em tecnologia. A forte correla&#231;&#227;o entre a capacidade de exerc&#237;cio e os resultados da an&#225;lise por IA com base em PLN sugere que os benef&#237;cios do programa para os pacientes se refletem tanto no feedback subjetivo quanto nos desfechos objetivos. No entanto, a an&#225;lise por PLN tamb&#233;m identificou algumas anomalias &#8212; casos em que as experi&#234;ncias relatadas pelos pacientes n&#227;o se alinharam &#224;s melhorias f&#237;sicas mensuradas. Essas discrep&#226;ncias podem ser explicadas por percep&#231;&#245;es individuais, fatores psicol&#243;gicos ou limita&#231;&#245;es atuais dos modelos de PLN em compreender plenamente a complexidade dos relatos dos pacientes.</p>
      <p>Reconhecer e interpretar essas anomalias &#233; fundamental para aprimorar as ferramentas de avalia&#231;&#227;o baseadas em IA e promover um cuidado mais personalizado. Pesquisas futuras devem n&#227;o apenas explorar de forma mais ampla a efetividade da PLN na TRC, mas tamb&#233;m investigar mais profundamente o significado cl&#237;nico das anomalias detectadas, a fim de aumentar a precis&#227;o e a aplicabilidade pr&#225;tica da avalia&#231;&#227;o de desfechos com suporte de IA.</p>
      <p>O treinamento f&#237;sico por meio da TRC tem demonstrado melhorar a capacidade de exerc&#237;cio em pacientes com DAC.<sup><xref ref-type="bibr" rid="B35">35</xref></sup> De forma semelhante, em nosso estudo, tanto o GTR quanto o GAM apresentaram aumentos significativos na dist&#226;ncia do ISWT ap&#243;s 12 semanas de treinamento. Isso refor&#231;a as diretrizes atuais que recomendam a TRC como uma abordagem eficaz para melhorar a capacidade de exerc&#237;cio em pacientes com DAC.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Em conson&#226;ncia com nossos achados, Brouwers et al. tamb&#233;m relataram aumento da capacidade de exerc&#237;cio e dos n&#237;veis de atividade f&#237;sica em pacientes com DAC ap&#243;s a TRC.<sup><xref ref-type="bibr" rid="B36">36</xref></sup></p>
      <p>Essas melhorias s&#227;o provavelmente decorrentes de altera&#231;&#245;es fisiol&#243;gicas nos sistemas cardiovascular e musculoesquel&#233;tico.<sup><xref ref-type="bibr" rid="B37">37</xref></sup> Especificamente, as redu&#231;&#245;es na FC ao final do exerc&#237;cio e na %FCm&#225;x observadas no GTR sugerem adapta&#231;&#245;es cardiovasculares positivas. Esses resultados est&#227;o de acordo com estudos anteriores que demonstram que o treinamento f&#237;sico melhora a efici&#234;ncia card&#237;aca, permitindo que os pacientes realizem a mesma carga de trabalho com uma FC mais baixa.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> A redu&#231;&#227;o da FC ap&#243;s o exerc&#237;cio reflete uma melhor adapta&#231;&#227;o cardiovascular.</p>
      <p>Acreditamos que a alta ades&#227;o observada no GTR pode estar relacionada ao aumento da motiva&#231;&#227;o proporcionado pelo feedback em tempo real durante as sess&#245;es supervisionadas.</p>
      <p>Al&#233;m da fun&#231;&#227;o f&#237;sica, a melhora da QV tamb&#233;m &#233; um objetivo importante para pacientes com DAC.<sup><xref ref-type="bibr" rid="B38">38</xref></sup> Melhorias no bem-estar f&#237;sico, energia, fadiga e funcionamento no dia a dia podem contribuir para um melhor manejo da doen&#231;a e melhores desfechos em longo prazo.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> Em nosso estudo, tanto o GTR quanto o GAM apresentaram melhorias significativas na QV, o que est&#225; em concord&#226;ncia com os achados de Golbus et al., que relataram que programas de RC digitais e h&#237;bridos melhoram a QV em pacientes card&#237;acos.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
      <p>No entanto, nem todos os estudos encontraram resultados semelhantes. Um estudo relatou aus&#234;ncia de mudan&#231;a nos escores do SF-36, apesar da melhora na capacidade funcional em um programa h&#237;brido de TRC.<sup><xref ref-type="bibr" rid="B39">39</xref></sup> Essa discrep&#226;ncia pode ser atribu&#237;da a diferen&#231;as na forma como a QV &#233; mensurada nas pesquisas cardiovasculares e ao n&#250;mero limitado de estudos que focam especificamente nos desfechos relacionados &#224; QV na TRC. Tamb&#233;m acreditamos que a maior dura&#231;&#227;o do nosso programa de exerc&#237;cios pode ter contribu&#237;do para as melhorias mais evidentes observadas.</p>
      <p>Nosso estudo tamb&#233;m identificou melhorias significativas no dom&#237;nio de aspectos emocionais em ambos os grupos de interven&#231;&#227;o, sugerindo um impacto positivo no bem-estar psicol&#243;gico. Esse resultado est&#225; em concord&#226;ncia com os achados de uma metan&#225;lise conduzida por Gong et al., que demonstrou que programas de TRC com dura&#231;&#227;o m&#237;nima de 3 meses podem reduzir sintomas de depress&#227;o e ansiedade.<sup><xref ref-type="bibr" rid="B40">40</xref></sup></p>
      <p>De modo geral, as melhorias na dist&#226;ncia do ISWT (&#916;ISWT) observadas em nosso estudo se refletiram em melhores escores em diversas subescalas de QV.</p>
      <p>A integra&#231;&#227;o da tecnologia em programas de RC desempenha um papel fundamental na melhoria da ades&#227;o e da participa&#231;&#227;o dos pacientes. Em nosso estudo, tanto o GTR quanto o GAM apresentaram taxas de comparecimento superiores &#224;s do GC, sugerindo que abordagens baseadas em tecnologia s&#227;o mais acess&#237;veis e de uso mais amig&#225;vel. A flexibilidade oferecida pelo GAM pode ter favorecido ainda mais a participa&#231;&#227;o, permitindo que os pacientes realizassem os exerc&#237;cios nos hor&#225;rios mais adequados &#224; sua rotina di&#225;ria. Pesquisas anteriores apoiam a ideia de que a tecnologia m&#243;vel pode melhorar a ades&#227;o a programas de RC.<sup><xref ref-type="bibr" rid="B3">3</xref>,<xref ref-type="bibr" rid="B41">41</xref></sup> No nosso caso, o aplicativo m&#243;vel provavelmente contribuiu para isso ao permitir o acompanhamento dos exerc&#237;cios, fornecer feedback e manter os pacientes motivados. Esses resultados s&#227;o consistentes com os achados de Maddison et al., que relataram maiores taxas de participa&#231;&#227;o em programas domiciliares de RC em compara&#231;&#227;o com os programas tradicionais realizados em centros especializados.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> A conveni&#234;ncia de realizar os exerc&#237;cios em casa, com equipamentos m&#237;nimos e sem custos de transporte, provavelmente teve um papel importante no incentivo &#224; participa&#231;&#227;o &#8212; especialmente no cen&#225;rio econ&#244;mico atual. Como os pacientes do nosso estudo apresentavam uma capacidade de exerc&#237;cio m&#233;dia superior a 10 METs, esses achados s&#227;o mais aplic&#225;veis a pacientes com DAC de baixo risco.</p>
      <p>Este estudo apresenta v&#225;rias limita&#231;&#245;es. Embora os m&#233;todos baseados em IA mostrem potencial, existem desafios importantes que devem ser reconhecidos. Uma das principais limita&#231;&#245;es &#233; a depend&#234;ncia da qualidade e da quantidade dos dados utilizados para treinar os modelos de IA. Dados insuficientes ou de baixa qualidade podem introduzir vieses e limitar a aplicabilidade dos resultados a diferentes popula&#231;&#245;es de pacientes. Al&#233;m disso, os algoritmos de PLN dependem da linguagem, que pode variar de acordo com fatores culturais e individuais na forma como os pacientes descrevem seus sintomas e experi&#234;ncias. Outro desafio &#233; a interpretabilidade dos resultados gerados por IA. Para que essas ferramentas sejam &#250;teis na pr&#225;tica cl&#237;nica, os profissionais de sa&#250;de precisam de informa&#231;&#245;es claras, compreens&#237;veis e confi&#225;veis que possam ser aplicadas na tomada de decis&#227;o. Os programas de TRC analisados neste estudo focaram exclusivamente no treinamento f&#237;sico e n&#227;o inclu&#237;ram outros componentes essenciais da RC completa, como suporte psicossocial, orienta&#231;&#227;o nutricional, manejo medicamentoso e cessa&#231;&#227;o do tabagismo. Al&#233;m disso, o aplicativo m&#243;vel utilizado para orientar os exerc&#237;cios n&#227;o permitia o monitoramento em tempo real da FC ou da PA durante as sess&#245;es. A maioria dos participantes deste estudo era composta por pacientes com DAC de baixo risco, o que limita a generaliza&#231;&#227;o dos achados para grupos de maior risco. Apesar dessas limita&#231;&#245;es, o estudo apresenta pontos fortes relevantes. A an&#225;lise por PLN e IA foi, no m&#237;nimo, t&#227;o eficaz quanto as avalia&#231;&#245;es tradicionais para demonstrar os benef&#237;cios da TRC, evidenciando o potencial inovador das ferramentas digitais na aten&#231;&#227;o card&#237;aca. O estudo tamb&#233;m demonstrou que programas de exerc&#237;cios autoguiados podem ser t&#227;o eficazes quanto os m&#233;todos tradicionais para melhorar a capacidade de exerc&#237;cio, a ades&#227;o e a QV em pacientes com DAC.</p>
    </sec>
    <sec sec-type="conclusions">
      <title>Conclus&#227;o</title>
      <p>Este estudo destaca a efetividade da an&#225;lise baseada em IA na avalia&#231;&#227;o do impacto do exerc&#237;cio f&#237;sico em pacientes com DAC de baixo risco. Tanto o GTR quanto o GAM mostraram-se eficazes e vi&#225;veis, podendo oferecer benef&#237;cios superiores aos m&#233;todos tradicionais na melhora da capacidade de exerc&#237;cio, participa&#231;&#227;o e QV. &#192; medida que a IA continua a evoluir, o papel do fisioterapeuta permanece essencial, especialmente na oferta de um cuidado centrado no paciente. Com o apoio de estudos multic&#234;ntricos, abordagens baseadas em PLN podem se tornar uma ferramenta valiosa na RC. S&#227;o necess&#225;rias pesquisas adicionais para avaliar a viabilidade cl&#237;nica e a seguran&#231;a da RC com suporte de IA, explorar outros m&#233;todos baseados em IA, como o exerc&#237;cio com realidade virtual, e analisar o custo-benef&#237;cio e a integra&#231;&#227;o pr&#225;tica dos programas de TRC no sistema de sa&#250;de em geral.</p>
    </sec>
  </body>
  <back>
    <ack>
      <title>Agradecimentos</title>
      <p>Os autores agradecem profundamente &#224;s pessoas que participaram do estudo, bem como a Ahmet Talha Sen e Cagri Golen pelo valioso apoio durante toda a pesquisa.</p>
    </ack>
    <ref-list>
      <title>Refer&#234;ncias</title>
      <ref id="B1">
        <label>1</label>
        <mixed-citation>1. Piepoli MF, Hoes AW, Agewall S, Albus C, Brotons C, Catapano AL, et al. 2016 European Guidelines on Cardiovascular Disease Prevention in Clinical Practice: The Sixth Joint Task Force of the European Society of Cardiology and Other Societies on Cardiovascular Disease Prevention in Clinical Practice (Constituted by Representatives of 10 Societies and by Invited Experts)Developed with the Special Contribution of the European Association for Cardiovascular Prevention &amp; Rehabilitation (EACPR). Eur Heart J. 2016;37(29):2315-81. doi: 10.1093/eurheartj/ehw106.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Piepoli</surname>
              <given-names>MF</given-names>
            </name>
            <name>
              <surname>Hoes</surname>
              <given-names>AW</given-names>
            </name>
            <name>
              <surname>Agewall</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Albus</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Brotons</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Catapano</surname>
              <given-names>AL</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>2016 European Guidelines on Cardiovascular Disease Prevention in Clinical Practice: The Sixth Joint Task Force of the European Society of Cardiology and Other Societies on Cardiovascular Disease Prevention in Clinical Practice (Constituted by Representatives of 10 Societies and by Invited Experts)Developed with the Special Contribution of the European Association for Cardiovascular Prevention &amp; Rehabilitation (EACPR)</article-title>
          <source>Eur Heart J</source>
          <year>2016</year>
          <volume>37</volume>
          <issue>29</issue>
          <fpage>2315</fpage>
          <lpage>2381</lpage>
          <pub-id pub-id-type="doi">10.1093/eurheartj/ehw106</pub-id>
        </element-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <mixed-citation>2. Beatty AL, Fukuoka Y, Whooley MA. Using Mobile Technology for Cardiac Rehabilitation: A Review and Framework for Development and Evaluation. J Am Heart Assoc. 2013;2(6):e000568. doi: 10.1161/JAHA.113.000568.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Beatty</surname>
              <given-names>AL</given-names>
            </name>
            <name>
              <surname>Fukuoka</surname>
              <given-names>Y</given-names>
            </name>
            <name>
              <surname>Whooley</surname>
              <given-names>MA</given-names>
            </name>
          </person-group>
          <article-title>Using Mobile Technology for Cardiac Rehabilitation: A Review and Framework for Development and Evaluation</article-title>
          <source>J Am Heart Assoc</source>
          <year>2013</year>
          <volume>2</volume>
          <issue>6</issue>
          <elocation-id>e000568</elocation-id>
          <pub-id pub-id-type="doi">10.1161/JAHA.113.000568</pub-id>
        </element-citation>
      </ref>
      <ref id="B3">
        <label>3</label>
        <mixed-citation>3. Imran TF, Wang N, Zombeck S, Balady GJ. Mobile Technology Improves Adherence to Cardiac Rehabilitation: A Propensity Score-Matched Study. J Am Heart Assoc. 2021;10(15):e020482. doi: 10.1161/JAHA.120.020482.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Imran</surname>
              <given-names>TF</given-names>
            </name>
            <name>
              <surname>Wang</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Zombeck</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Balady</surname>
              <given-names>GJ</given-names>
            </name>
          </person-group>
          <article-title>Mobile Technology Improves Adherence to Cardiac Rehabilitation: A Propensity Score-Matched Study</article-title>
          <source>J Am Heart Assoc</source>
          <year>2021</year>
          <volume>10</volume>
          <issue>15</issue>
          <elocation-id>e020482</elocation-id>
          <comment>doi: 10.1161/JAHA.120.020482</comment>
        </element-citation>
      </ref>
      <ref id="B4">
        <label>4</label>
        <mixed-citation>4. Golbus JR, Lopez-Jimenez F, Barac A, Cornwell WK 3rd, Dunn P, Forman DE, et al. Digital Technologies in Cardiac Rehabilitation: A Science Advisory from the American Heart Association. Circulation. 2023;148(1):95-107. doi: 10.1161/CIR.0000000000001150.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Golbus</surname>
              <given-names>JR</given-names>
            </name>
            <name>
              <surname>Lopez-Jimenez</surname>
              <given-names>F</given-names>
            </name>
            <name>
              <surname>Barac</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Cornwell</surname>
              <given-names>WK</given-names>
              <suffix>3rd</suffix>
            </name>
            <name>
              <surname>Dunn</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Forman</surname>
              <given-names>DE</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Digital Technologies in Cardiac Rehabilitation: A Science Advisory from the American Heart Association</article-title>
          <source>Circulation</source>
          <year>2023</year>
          <volume>148</volume>
          <issue>1</issue>
          <fpage>95</fpage>
          <lpage>107</lpage>
          <pub-id pub-id-type="doi">10.1161/CIR.0000000000001150</pub-id>
        </element-citation>
      </ref>
      <ref id="B5">
        <label>5</label>
        <mixed-citation>5. Fihn SD, Gardin JM, Abrams J, Berra K, Blankenship JC, Dallas AP, et al. 2012 ACCF/AHA/ACP/AATS/PCNA/SCAI/STS Guideline for the Diagnosis and Management of Patients with Stable Ischemic Heart Disease: Executive Summary: A Report of the American College of Cardiology Foundation/American Heart Association task Force on Practice Guidelines, and the American College of Physicians, American Association for Thoracic Surgery, Preventive Cardiovascular Nurses Association, Society for Cardiovascular Angiography and Interventions, and Society of Thoracic Surgeons. Circulation. 2012;126(25):3097-137. doi: 10.1161/CIR.0b013e3182776f83.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Fihn</surname>
              <given-names>SD</given-names>
            </name>
            <name>
              <surname>Gardin</surname>
              <given-names>JM</given-names>
            </name>
            <name>
              <surname>Abrams</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Berra</surname>
              <given-names>K</given-names>
            </name>
            <name>
              <surname>Blankenship</surname>
              <given-names>JC</given-names>
            </name>
            <name>
              <surname>Dallas</surname>
              <given-names>AP</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>2012 ACCF/AHA/ACP/AATS/PCNA/SCAI/STS Guideline for the Diagnosis and Management of Patients with Stable Ischemic Heart Disease: Executive Summary: A Report of the American College of Cardiology Foundation/American Heart Association task Force on Practice Guidelines, and the American College of Physicians, American Association for Thoracic Surgery, Preventive Cardiovascular Nurses Association, Society for Cardiovascular Angiography and Interventions, and Society of Thoracic Surgeons</article-title>
          <source>Circulation</source>
          <year>2012</year>
          <volume>126</volume>
          <issue>25</issue>
          <fpage>3097</fpage>
          <lpage>3137</lpage>
          <pub-id pub-id-type="doi">10.1161/CIR.0b013e3182776f83</pub-id>
        </element-citation>
      </ref>
      <ref id="B6">
        <label>6</label>
        <mixed-citation>6. Gleeson PB, Protas EJ. Oxygen Consumption During Calisthenic Exercise in Women with Coronary Artery Disease. Phys Ther. 1989;69(4):260-3. doi: 10.1093/ptj/69.4.260.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Gleeson</surname>
              <given-names>PB</given-names>
            </name>
            <name>
              <surname>Protas</surname>
              <given-names>EJ</given-names>
            </name>
          </person-group>
          <article-title>Oxygen Consumption During Calisthenic Exercise in Women with Coronary Artery Disease</article-title>
          <source>Phys Ther</source>
          <year>1989</year>
          <volume>69</volume>
          <issue>4</issue>
          <fpage>260</fpage>
          <lpage>263</lpage>
          <pub-id pub-id-type="doi">10.1093/ptj/69.4.260</pub-id>
        </element-citation>
      </ref>
      <ref id="B7">
        <label>7</label>
        <mixed-citation>7. Scherrenberg M, Bonneux C, Mahmood DY, Hansen D, Dendale P, Coninx K. A Mobile Application to Perform the Six-Minute Walk Test (6MWT) at Home: A Random Walk in the Park is as Accurate as a Standardized 6MWT. Sensors. 2022;22(11):4277. doi: 10.3390/s22114277.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Scherrenberg</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Bonneux</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Mahmood</surname>
              <given-names>DY</given-names>
            </name>
            <name>
              <surname>Hansen</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Dendale</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Coninx</surname>
              <given-names>K</given-names>
            </name>
          </person-group>
          <article-title>A Mobile Application to Perform the Six-Minute Walk Test (6MWT) at Home: A Random Walk in the Park is as Accurate as a Standardized 6MWT</article-title>
          <source>Sensors</source>
          <year>2022</year>
          <volume>22</volume>
          <issue>11</issue>
          <size units="pages">4277</size>
          <pub-id pub-id-type="doi">10.3390/s22114277</pub-id>
        </element-citation>
      </ref>
      <ref id="B8">
        <label>8</label>
        <mixed-citation>8. Dafny HA, Champion S, Gebremichael LG, Pearson V, Hendriks JM, Clark RA, et al. Cardiac Rehabilitation, Physical Activity, and the Effectiveness of Activity Monitoring Devices on Cardiovascular Patients: An Umbrella Review of Systematic Reviews. Eur Heart J Qual Care Clin Outcomes. 2023;9(4):323-30. doi: 10.1093/ehjqcco/qcad005.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Dafny</surname>
              <given-names>HA</given-names>
            </name>
            <name>
              <surname>Champion</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Gebremichael</surname>
              <given-names>LG</given-names>
            </name>
            <name>
              <surname>Pearson</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Hendriks</surname>
              <given-names>JM</given-names>
            </name>
            <name>
              <surname>Clark</surname>
              <given-names>RA</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Cardiac Rehabilitation, Physical Activity, and the Effectiveness of Activity Monitoring Devices on Cardiovascular Patients: An Umbrella Review of Systematic Reviews</article-title>
          <source>Eur Heart J Qual Care Clin Outcomes</source>
          <year>2023</year>
          <volume>9</volume>
          <issue>4</issue>
          <fpage>323</fpage>
          <lpage>330</lpage>
          <pub-id pub-id-type="doi">10.1093/ehjqcco/qcad005</pub-id>
        </element-citation>
      </ref>
      <ref id="B9">
        <label>9</label>
        <mixed-citation>9. Micheluzzi V, Navarese EP, Merella P, Talanas G, Viola G, Bandino S, et al. Clinical Application of Virtual Reality in Patients with Cardiovascular Disease: State of the Art. Front Cardiovasc Med. 2024;11:1356361. doi: 10.3389/fcvm.2024.1356361.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Micheluzzi</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Navarese</surname>
              <given-names>EP</given-names>
            </name>
            <name>
              <surname>Merella</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Talanas</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>Viola</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>Bandino</surname>
              <given-names>S</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Clinical Application of Virtual Reality in Patients with Cardiovascular Disease: State of the Art</article-title>
          <source>Front Cardiovasc Med</source>
          <year>2024</year>
          <volume>11</volume>
          <size units="pages">1356361</size>
          <pub-id pub-id-type="doi">10.3389/fcvm.2024.1356361</pub-id>
        </element-citation>
      </ref>
      <ref id="B10">
        <label>10</label>
        <mixed-citation>10. Snoek JA, Prescott EI, van der Velde AE, Eijsvogels TMH, Mikkelsen N, Prins LF, et al. Effectiveness of Home-Based Mobile Guided Cardiac Rehabilitation as Alternative Strategy for Nonparticipation in Clinic-Based Cardiac Rehabilitation among Elderly Patients in Europe: A Randomized Clinical Trial. JAMA Cardiol. 2021;6(4):463-8. doi: 10.1001/jamacardio.2020.5218.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Snoek</surname>
              <given-names>JA</given-names>
            </name>
            <name>
              <surname>Prescott</surname>
              <given-names>EI</given-names>
            </name>
            <name>
              <surname>van der Velde</surname>
              <given-names>AE</given-names>
            </name>
            <name>
              <surname>Eijsvogels</surname>
              <given-names>TMH</given-names>
            </name>
            <name>
              <surname>Mikkelsen</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Prins</surname>
              <given-names>LF</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Effectiveness of Home-Based Mobile Guided Cardiac Rehabilitation as Alternative Strategy for Nonparticipation in Clinic-Based Cardiac Rehabilitation among Elderly Patients in Europe: A Randomized Clinical Trial</article-title>
          <source>JAMA Cardiol</source>
          <year>2021</year>
          <volume>6</volume>
          <issue>4</issue>
          <fpage>463</fpage>
          <lpage>468</lpage>
          <pub-id pub-id-type="doi">10.1001/jamacardio.2020.5218</pub-id>
        </element-citation>
      </ref>
      <ref id="B11">
        <label>11</label>
        <mixed-citation>11. Chessa M, van de Bruaene A, Farooqi K, Valverde I, Jung C, Votta E, et al. Three-Dimensional Printing, Holograms, Computational Modelling, and Artificial Intelligence for Adult Congenital Heart Disease Care: An Exciting Future. Eur Heart J. 2022;43(28):2672-84. doi: 10.1093/eurheartj/ehac266.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Chessa</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>van de Bruaene</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Farooqi</surname>
              <given-names>K</given-names>
            </name>
            <name>
              <surname>Valverde</surname>
              <given-names>I</given-names>
            </name>
            <name>
              <surname>Jung</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Votta</surname>
              <given-names>E</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Three-Dimensional Printing, Holograms, Computational Modelling, and Artificial Intelligence for Adult Congenital Heart Disease Care: An Exciting Future</article-title>
          <source>Eur Heart J</source>
          <year>2022</year>
          <volume>43</volume>
          <issue>28</issue>
          <fpage>2672</fpage>
          <lpage>2684</lpage>
          <pub-id pub-id-type="doi">10.1093/eurheartj/ehac266</pub-id>
        </element-citation>
      </ref>
      <ref id="B12">
        <label>12</label>
        <mixed-citation>12. Sherman E, Alejo D, Wood-Doughty Z, Sussman M, Schena S, Ong CS, et al. Leveraging Machine Learning to Predict 30-Day Hospital Readmission after Cardiac Surgery. Ann Thorac Surg. 2022;114(6):2173-9. doi: 10.1016/j.athoracsur.2021.11.011.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Sherman</surname>
              <given-names>E</given-names>
            </name>
            <name>
              <surname>Alejo</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Wood-Doughty</surname>
              <given-names>Z</given-names>
            </name>
            <name>
              <surname>Sussman</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Schena</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Ong</surname>
              <given-names>CS</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Leveraging Machine Learning to Predict 30-Day Hospital Readmission after Cardiac Surgery</article-title>
          <source>Ann Thorac Surg</source>
          <year>2022</year>
          <volume>114</volume>
          <issue>6</issue>
          <fpage>2173</fpage>
          <lpage>2179</lpage>
          <pub-id pub-id-type="doi">10.1016/j.athoracsur.2021.11.011</pub-id>
        </element-citation>
      </ref>
      <ref id="B13">
        <label>13</label>
        <mixed-citation>13. Pepera G, Antoniou V, Su JJ, Lin R, Batalik L. Comprehensive and Personalized Approach is a Critical Area for Developing Remote Cardiac Rehabilitation Programs. World J Clin Cases. 2024;12(12):2009-15. doi: 10.12998/wjcc.v12.i12.2009.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Pepera</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>Antoniou</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Su</surname>
              <given-names>JJ</given-names>
            </name>
            <name>
              <surname>Lin</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Batalik</surname>
              <given-names>L</given-names>
            </name>
          </person-group>
          <article-title>Comprehensive and Personalized Approach is a Critical Area for Developing Remote Cardiac Rehabilitation Programs</article-title>
          <source>World J Clin Cases</source>
          <year>2024</year>
          <volume>12</volume>
          <issue>12</issue>
          <fpage>2009</fpage>
          <lpage>2015</lpage>
          <pub-id pub-id-type="doi">10.12998/wjcc.v12.i12.2009</pub-id>
        </element-citation>
      </ref>
      <ref id="B14">
        <label>14</label>
        <mixed-citation>14. Mor-Avi V, Khandheria B, Klempfner R, Cotella JI, Moreno M, Ignatowski D, et al. Real-Time Artificial Intelligence-Based Guidance of Echocardiographic Imaging by Novices: Image Quality and Suitability for Diagnostic Interpretation and Quantitative Analysis. Circ Cardiovasc Imaging. 2023;16(11):e015569. doi: 10.1161/CIRCIMAGING.123.015569.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Mor-Avi</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Khandheria</surname>
              <given-names>B</given-names>
            </name>
            <name>
              <surname>Klempfner</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Cotella</surname>
              <given-names>JI</given-names>
            </name>
            <name>
              <surname>Moreno</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Ignatowski</surname>
              <given-names>D</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Real-Time Artificial Intelligence-Based Guidance of Echocardiographic Imaging by Novices: Image Quality and Suitability for Diagnostic Interpretation and Quantitative Analysis</article-title>
          <source>Circ Cardiovasc Imaging</source>
          <year>2023</year>
          <volume>16</volume>
          <issue>11</issue>
          <elocation-id>e015569</elocation-id>
          <pub-id pub-id-type="doi">10.1161/CIRCIMAGING.123.015569</pub-id>
        </element-citation>
      </ref>
      <ref id="B15">
        <label>15</label>
        <mixed-citation>15. Silva CGS, Buginga GC, Silva EAS, Arena R, Rouleau CR, Aggarwal S, et al. Prediction of Mortality in Coronary Artery Disease: Role of Machine Learning and Maximal Exercise Capacity. Mayo Clin Proc. 2022;97(8):1472-82. doi: 10.1016/j.mayocp.2022.01.016.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Silva</surname>
              <given-names>CGS</given-names>
            </name>
            <name>
              <surname>Buginga</surname>
              <given-names>GC</given-names>
            </name>
            <name>
              <surname>Silva</surname>
              <given-names>EAS</given-names>
            </name>
            <name>
              <surname>Arena</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Rouleau</surname>
              <given-names>CR</given-names>
            </name>
            <name>
              <surname>Aggarwal</surname>
              <given-names>S</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Prediction of Mortality in Coronary Artery Disease: Role of Machine Learning and Maximal Exercise Capacity</article-title>
          <source>Mayo Clin Proc</source>
          <year>2022</year>
          <volume>97</volume>
          <issue>8</issue>
          <fpage>1472</fpage>
          <lpage>1482</lpage>
          <pub-id pub-id-type="doi">10.1016/j.mayocp.2022.01.016</pub-id>
        </element-citation>
      </ref>
      <ref id="B16">
        <label>16</label>
        <mixed-citation>16. Prabhu G, O'Connor NE, Moran K. Recognition and Repetition Counting for Local Muscular Endurance Exercises in Exercise-Based Rehabilitation: A Comparative Study Using Artificial Intelligence Models. Sensors (Basel). 2020;20(17):4791. doi: 10.3390/s20174791.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Prabhu</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>O'Connor</surname>
              <given-names>NE</given-names>
            </name>
            <name>
              <surname>Moran</surname>
              <given-names>K</given-names>
            </name>
          </person-group>
          <article-title>Recognition and Repetition Counting for Local Muscular Endurance Exercises in Exercise-Based Rehabilitation: A Comparative Study Using Artificial Intelligence Models</article-title>
          <source>Sensors (Basel)</source>
          <year>2020</year>
          <volume>20</volume>
          <issue>17</issue>
          <size units="pages">4791</size>
          <pub-id pub-id-type="doi">10.3390/s20174791</pub-id>
        </element-citation>
      </ref>
      <ref id="B17">
        <label>17</label>
        <mixed-citation>17. Witharana P, Chang L, Maier R, Ogundimu E, Wilkinson C, Athanasiou T, et al. Feasibility Study of Rehabilitation for Cardiac Patients Aided by an Artificial Intelligence Web-Based Programme: A Randomised Controlled Trial (RECAP trial)-A Study Protocol. BMJ Open. 2024;14(4):e079404. doi: 10.1136/bmjopen-2023-079404.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Witharana</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Chang</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Maier</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Ogundimu</surname>
              <given-names>E</given-names>
            </name>
            <name>
              <surname>Wilkinson</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Athanasiou</surname>
              <given-names>T</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Feasibility Study of Rehabilitation for Cardiac Patients Aided by an Artificial Intelligence Web-Based Programme: A Randomised Controlled Trial (RECAP trial)-A Study Protocol</article-title>
          <source>BMJ Open</source>
          <year>2024</year>
          <volume>14</volume>
          <issue>4</issue>
          <elocation-id>e079404</elocation-id>
          <pub-id pub-id-type="doi">10.1136/bmjopen-2023-079404</pub-id>
        </element-citation>
      </ref>
      <ref id="B18">
        <label>18</label>
        <mixed-citation>18. Garg R, Gupta A. A Systematic Review of NLP Applications in Clinical Healthcare: Advancement and Challenges. Springer. 2024;892:31-44. doi: 10.1007/978-981-99-9521-9_3.</mixed-citation>
        <element-citation publication-type="book">
          <person-group person-group-type="author">
            <name>
              <surname>Garg</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Gupta</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <source>A Systematic Review of NLP Applications in Clinical Healthcare: Advancement and Challenges</source>
          <publisher-name>Springer</publisher-name>
          <year>2024</year>
          <volume>892</volume>
          <fpage>31</fpage>
          <lpage>44</lpage>
          <pub-id pub-id-type="doi">10.1007/978-981-99-9521-9_3</pub-id>
        </element-citation>
      </ref>
      <ref id="B19">
        <label>19</label>
        <mixed-citation>19. Pio CSA, Chaves GS, Davies P, Taylor RS, Grace SL. Interventions to Promote Patient Utilisation of Cardiac Rehabilitation. Cochrane Database Syst Rev. 2019;2(2):CD007131. doi: 10.1002/14651858.CD007131.pub4.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Pio</surname>
              <given-names>CSA</given-names>
            </name>
            <name>
              <surname>Chaves</surname>
              <given-names>GS</given-names>
            </name>
            <name>
              <surname>Davies</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Taylor</surname>
              <given-names>RS</given-names>
            </name>
            <name>
              <surname>Grace</surname>
              <given-names>SL</given-names>
            </name>
          </person-group>
          <article-title>Interventions to Promote Patient Utilisation of Cardiac Rehabilitation</article-title>
          <source>Cochrane Database Syst Rev</source>
          <year>2019</year>
          <volume>2</volume>
          <issue>2</issue>
          <size units="pages">CD007131</size>
          <pub-id pub-id-type="doi">10.1002/14651858.CD007131.pub4</pub-id>
        </element-citation>
      </ref>
      <ref id="B20">
        <label>20</label>
        <mixed-citation>20. Maddison R, Rawstorn JC, Stewart RAH, Benatar J, Whittaker R, Rolleston A, et al. Effects and Costs of Real-Time Cardiac Telerehabilitation: Randomised Controlled Non-Inferiority Trial. Heart. 2019;105(2):122-9. doi: 10.1136/heartjnl-2018-313189.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Maddison</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Rawstorn</surname>
              <given-names>JC</given-names>
            </name>
            <name>
              <surname>Stewart</surname>
              <given-names>RAH</given-names>
            </name>
            <name>
              <surname>Benatar</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Whittaker</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Rolleston</surname>
              <given-names>A</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Effects and Costs of Real-Time Cardiac Telerehabilitation: Randomised Controlled Non-Inferiority Trial</article-title>
          <source>Heart</source>
          <year>2019</year>
          <volume>105</volume>
          <issue>2</issue>
          <fpage>122</fpage>
          <lpage>129</lpage>
          <pub-id pub-id-type="doi">10.1136/heartjnl-2018-313189</pub-id>
        </element-citation>
      </ref>
      <ref id="B21">
        <label>21</label>
        <mixed-citation>21. Aharon KB, Gershfeld-Litvin A, Amir O, Nabutovsky I, Klempfner R. Improving Cardiac Rehabilitation Patient Adherence via Personalized Interventions. PLoS One. 2022;17(8):e0273815. doi: 10.1371/journal.pone.0273815.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Aharon</surname>
              <given-names>KB</given-names>
            </name>
            <name>
              <surname>Gershfeld-Litvin</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Amir</surname>
              <given-names>O</given-names>
            </name>
            <name>
              <surname>Nabutovsky</surname>
              <given-names>I</given-names>
            </name>
            <name>
              <surname>Klempfner</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>Improving Cardiac Rehabilitation Patient Adherence via Personalized Interventions</article-title>
          <source>PLoS One</source>
          <year>2022</year>
          <volume>17</volume>
          <issue>8</issue>
          <elocation-id>e0273815</elocation-id>
          <pub-id pub-id-type="doi">10.1371/journal.pone.0273815</pub-id>
        </element-citation>
      </ref>
      <ref id="B22">
        <label>22</label>
        <mixed-citation>22. Ades PA, Khadanga S, Savage PD, Gaalema DE. Enhancing Participation in Cardiac Rehabilitation: Focus on Underserved Populations. Prog Cardiovasc Dis. 2022;70:102-10. doi: 10.1016/j.pcad.2022.01.003.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Ades</surname>
              <given-names>PA</given-names>
            </name>
            <name>
              <surname>Khadanga</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Savage</surname>
              <given-names>PD</given-names>
            </name>
            <name>
              <surname>Gaalema</surname>
              <given-names>DE</given-names>
            </name>
          </person-group>
          <article-title>Enhancing Participation in Cardiac Rehabilitation: Focus on Underserved Populations</article-title>
          <source>Prog Cardiovasc Dis</source>
          <year>2022</year>
          <volume>70</volume>
          <fpage>102</fpage>
          <lpage>110</lpage>
          <pub-id pub-id-type="doi">10.1016/j.pcad.2022.01.003</pub-id>
        </element-citation>
      </ref>
      <ref id="B23">
        <label>23</label>
        <mixed-citation>23. Thomas RJ, Beatty AL, Beckie TM, Brewer LC, Brown TM, Forman DE, et al. Home-Based Cardiac Rehabilitation: A Scientific Statement from the American Association of Cardiovascular and Pulmonary Rehabilitation, the American Heart Association, and the American College of Cardiology. J Am Coll Cardiol. 2019;74(1):133-53. doi: 10.1016/j.jacc.2019.03.008.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Thomas</surname>
              <given-names>RJ</given-names>
            </name>
            <name>
              <surname>Beatty</surname>
              <given-names>AL</given-names>
            </name>
            <name>
              <surname>Beckie</surname>
              <given-names>TM</given-names>
            </name>
            <name>
              <surname>Brewer</surname>
              <given-names>LC</given-names>
            </name>
            <name>
              <surname>Brown</surname>
              <given-names>TM</given-names>
            </name>
            <name>
              <surname>Forman</surname>
              <given-names>DE</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Home-Based Cardiac Rehabilitation: A Scientific Statement from the American Association of Cardiovascular and Pulmonary Rehabilitation, the American Heart Association, and the American College of Cardiology</article-title>
          <source>J Am Coll Cardiol</source>
          <year>2019</year>
          <volume>74</volume>
          <issue>1</issue>
          <fpage>133</fpage>
          <lpage>153</lpage>
          <conf-loc>doi</conf-loc>
          <pub-id pub-id-type="doi">10.1016/j.jacc.2019.03.008</pub-id>
        </element-citation>
      </ref>
      <ref id="B24">
        <label>24</label>
        <mixed-citation>24. Zhang D, Geng S, Zhou Y, Xu W, Wei G, Wang K, et al. Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities Using Electrocardiogram Images. arXiv. 2023;1:1-47. doi: 10.48550/arXiv.2302.10301.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Zhang</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Geng</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Zhou</surname>
              <given-names>Y</given-names>
            </name>
            <name>
              <surname>Xu</surname>
              <given-names>W</given-names>
            </name>
            <name>
              <surname>Wei</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>Wang</surname>
              <given-names>K</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities Using Electrocardiogram Images</article-title>
          <source>arXiv</source>
          <year>2023</year>
          <volume>1</volume>
          <fpage>1</fpage>
          <lpage>47</lpage>
          <pub-id pub-id-type="doi">10.48550/arXiv.2302.10301</pub-id>
        </element-citation>
      </ref>
      <ref id="B25">
        <label>25</label>
        <mixed-citation>25. Kara&#231;avus S. Artificial Intelligence Applications in Nuclear Cardiology. Nucl Med Semin. 2024;10(1):13-8. doi: 10.4274/nts.galenos.2024.0002.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Kara&#231;avus</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Artificial Intelligence Applications in Nuclear Cardiology</article-title>
          <source>Nucl Med Semin</source>
          <year>2024</year>
          <volume>10</volume>
          <issue>1</issue>
          <fpage>13</fpage>
          <lpage>18</lpage>
          <pub-id pub-id-type="doi">10.4274/nts.galenos.2024.0002</pub-id>
        </element-citation>
      </ref>
      <ref id="B26">
        <label>26</label>
        <mixed-citation>26. Hanson LC, McBurney H, Taylor NF. Is the 10 m Incremental Shuttle Walk Test a Useful Test of Exercise Capacity for Patients Referred to Cardiac Rehabilitation? Eur J Cardiovasc Nurs. 2018;17(2):159-69. doi: 10.1177/1474515117721129.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Hanson</surname>
              <given-names>LC</given-names>
            </name>
            <name>
              <surname>McBurney</surname>
              <given-names>H</given-names>
            </name>
            <name>
              <surname>Taylor</surname>
              <given-names>NF</given-names>
            </name>
          </person-group>
          <article-title>Is the 10 m Incremental Shuttle Walk Test a Useful Test of Exercise Capacity for Patients Referred to Cardiac Rehabilitation?</article-title>
          <source>Eur J Cardiovasc Nurs</source>
          <year>2018</year>
          <volume>17</volume>
          <issue>2</issue>
          <fpage>159</fpage>
          <lpage>169</lpage>
          <pub-id pub-id-type="doi">10.1177/1474515117721129</pub-id>
        </element-citation>
      </ref>
      <ref id="B27">
        <label>27</label>
        <mixed-citation>27. Huber A, Oldridge N, H&#246;fer S. International SF-36 Reference Values in Patients with Ischemic Heart Disease. Qual Life Res. 2016;25(11):2787-98. doi: 10.1007/s11136-016-1316-4.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Huber</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Oldridge</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>H&#246;fer</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>International SF-36 Reference Values in Patients with Ischemic Heart Disease</article-title>
          <source>Qual Life Res</source>
          <year>2016</year>
          <volume>25</volume>
          <issue>11</issue>
          <fpage>2787</fpage>
          <lpage>2798</lpage>
          <pub-id pub-id-type="doi">10.1007/s11136-016-1316-4</pub-id>
        </element-citation>
      </ref>
      <ref id="B28">
        <label>28</label>
        <mixed-citation>28. World Health Organization. WHO Guidelines on Physical Activity and Sedentary Behaviour. Geneva: World Health Organization; 2020.</mixed-citation>
        <element-citation publication-type="report">
          <person-group person-group-type="author">
            <collab>World Health Organization</collab>
          </person-group>
          <source>WHO Guidelines on Physical Activity and Sedentary Behaviour</source>
          <publisher-loc>Geneva</publisher-loc>
          <publisher-name>World Health Organization</publisher-name>
          <year>2020</year>
        </element-citation>
      </ref>
      <ref id="B29">
        <label>29</label>
        <mixed-citation>29. Virani SS, Newby LK, Arnold SV, Bittner V, Brewer LC, Demeter SH, et al. 2023 AHA/ACC/ACCP/ASPC/NLA/PCNA Guideline for the Management of Patients with Chronic Coronary Disease: A Report of the American Heart Association/American College of Cardiology Joint Committee on Clinical Practice Guidelines. J Am Coll Cardiol. 2023;82(9):833-955. doi: 10.1016/j.jacc.2023.04.003.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Virani</surname>
              <given-names>SS</given-names>
            </name>
            <name>
              <surname>Newby</surname>
              <given-names>LK</given-names>
            </name>
            <name>
              <surname>Arnold</surname>
              <given-names>SV</given-names>
            </name>
            <name>
              <surname>Bittner</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Brewer</surname>
              <given-names>LC</given-names>
            </name>
            <name>
              <surname>Demeter</surname>
              <given-names>SH</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>2023 AHA/ACC/ACCP/ASPC/NLA/PCNA Guideline for the Management of Patients with Chronic Coronary Disease: A Report of the American Heart Association/American College of Cardiology Joint Committee on Clinical Practice Guidelines</article-title>
          <source>J Am Coll Cardiol</source>
          <year>2023</year>
          <volume>82</volume>
          <issue>9</issue>
          <fpage>833</fpage>
          <lpage>955</lpage>
          <pub-id pub-id-type="doi">10.1016/j.jacc.2023.04.003</pub-id>
        </element-citation>
      </ref>
      <ref id="B30">
        <label>30</label>
        <mixed-citation>30. Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv. 2019;2(1):1-16. doi: 10.48550/arXiv.1810.04805.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Devlin</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Chang</surname>
              <given-names>MW</given-names>
            </name>
            <name>
              <surname>Lee</surname>
              <given-names>K</given-names>
            </name>
            <name>
              <surname>Toutanova</surname>
              <given-names>K</given-names>
            </name>
          </person-group>
          <article-title>BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding</article-title>
          <source>ArXiv</source>
          <year>2019</year>
          <volume>2</volume>
          <issue>1</issue>
          <fpage>1</fpage>
          <lpage>16</lpage>
          <pub-id pub-id-type="doi">10.48550/arXiv.1810.04805</pub-id>
        </element-citation>
      </ref>
      <ref id="B31">
        <label>31</label>
        <mixed-citation>31. &#199;elikten A, Bulut H. Turkish Medical Text Classification Using BERT. Proceedings of the 29th Signal Processing and Communications Applications Conference (SIU); 2021 Jul. Istanbul: IEEE; 2021.</mixed-citation>
        <element-citation publication-type="confproc">
          <person-group person-group-type="author">
            <name>
              <surname>&#199;elikten</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Bulut</surname>
              <given-names>H</given-names>
            </name>
          </person-group>
          <source>Turkish Medical Text Classification Using BERT</source>
          <conf-name>Proceedings of the 29th Signal Processing and Communications Applications Conference (SIU)</conf-name>
          <conf-date>2021 Jul</conf-date>
          <publisher-loc>Istanbul</publisher-loc>
          <publisher-name>IEEE</publisher-name>
          <year>2021</year>
        </element-citation>
      </ref>
      <ref id="B32">
        <label>32</label>
        <mixed-citation>32. Houchen-Wolloff L, Boyce S, Singh S. The Minimum Clinically Important Improvement in the Incremental Shuttle Walk Test Following Cardiac Rehabilitation. Eur J Prev Cardiol. 2015;22(8):972-8. doi: 10.1177/2047487314540840.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Houchen-Wolloff</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Boyce</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Singh</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>The Minimum Clinically Important Improvement in the Incremental Shuttle Walk Test Following Cardiac Rehabilitation</article-title>
          <source>Eur J Prev Cardiol</source>
          <year>2015</year>
          <volume>22</volume>
          <issue>8</issue>
          <fpage>972</fpage>
          <lpage>978</lpage>
          <pub-id pub-id-type="doi">10.1177/2047487314540840</pub-id>
        </element-citation>
      </ref>
      <ref id="B33">
        <label>33</label>
        <mixed-citation>33. Sotirakos S, Fouda B, Razif NAM, Cribben N, Mulhall C, O'Byrne A, et al. Harnessing Artificial Intelligence in Cardiac Rehabilitation, a Systematic Review. Future Cardiol. 2022;18(2):154-64. doi: 10.2217/fca-2021-0010.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Sotirakos</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Fouda</surname>
              <given-names>B</given-names>
            </name>
            <name>
              <surname>Razif</surname>
              <given-names>NAM</given-names>
            </name>
            <name>
              <surname>Cribben</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Mulhall</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>O'Byrne</surname>
              <given-names>A</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Harnessing Artificial Intelligence in Cardiac Rehabilitation, a Systematic Review</article-title>
          <source>Future Cardiol</source>
          <year>2022</year>
          <volume>18</volume>
          <issue>2</issue>
          <fpage>154</fpage>
          <lpage>164</lpage>
          <pub-id pub-id-type="doi">10.2217/fca-2021-0010</pub-id>
        </element-citation>
      </ref>
      <ref id="B34">
        <label>34</label>
        <mixed-citation>34. Su J, Zhang Y, Ke QQ, Su JK, Yang QH. Mobilizing Artificial Intelligence to Cardiac Telerehabilitation. Rev Cardiovasc Med. 2022;23(2):45. doi: 10.31083/j.rcm2302045.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Su</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name>
              <surname>Ke</surname>
              <given-names>QQ</given-names>
            </name>
            <name>
              <surname>Su</surname>
              <given-names>JK</given-names>
            </name>
            <name>
              <surname>Yang</surname>
              <given-names>QH</given-names>
            </name>
          </person-group>
          <article-title>Mobilizing Artificial Intelligence to Cardiac Telerehabilitation</article-title>
          <source>Rev Cardiovasc Med</source>
          <year>2022</year>
          <volume>23</volume>
          <issue>2</issue>
          <fpage>45</fpage>
          <pub-id pub-id-type="doi">10.31083/j.rcm2302045</pub-id>
        </element-citation>
      </ref>
      <ref id="B35">
        <label>35</label>
        <mixed-citation>35. Coorey GM, Neubeck L, Mulley J, Redfern J. Effectiveness, Acceptability and Usefulness of Mobile Applications for Cardiovascular Disease Self-Management: Systematic Review with Meta-Synthesis of Quantitative and Qualitative Data. Eur J Prev Cardiol. 2018;25(5):505-21. doi: 10.1177/2047487317750913.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Coorey</surname>
              <given-names>GM</given-names>
            </name>
            <name>
              <surname>Neubeck</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Mulley</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Redfern</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Effectiveness, Acceptability and Usefulness of Mobile Applications for Cardiovascular Disease Self-Management: Systematic Review with Meta-Synthesis of Quantitative and Qualitative Data</article-title>
          <source>Eur J Prev Cardiol</source>
          <year>2018</year>
          <volume>25</volume>
          <issue>5</issue>
          <fpage>505</fpage>
          <lpage>521</lpage>
          <pub-id pub-id-type="doi">10.1177/2047487317750913</pub-id>
        </element-citation>
      </ref>
      <ref id="B36">
        <label>36</label>
        <mixed-citation>36. Brouwers RWM, van Exel HJ, van Hal JMC, Jorstad HT, Kluiver EP, Kraaijenhagen RA, et al. Cardiac Telerehabilitation as an Alternative to Centre-Based Cardiac Rehabilitation. Neth Heart J. 2020;28(9):443-51. doi: 10.1007/s12471-020-01432-y.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Brouwers</surname>
              <given-names>RWM</given-names>
            </name>
            <name>
              <surname>van Exel</surname>
              <given-names>HJ</given-names>
            </name>
            <name>
              <surname>van Hal</surname>
              <given-names>JMC</given-names>
            </name>
            <name>
              <surname>Jorstad</surname>
              <given-names>HT</given-names>
            </name>
            <name>
              <surname>Kluiver</surname>
              <given-names>EP</given-names>
            </name>
            <name>
              <surname>Kraaijenhagen</surname>
              <given-names>RA</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Cardiac Telerehabilitation as an Alternative to Centre-Based Cardiac Rehabilitation</article-title>
          <source>Neth Heart J</source>
          <year>2020</year>
          <volume>28</volume>
          <issue>9</issue>
          <fpage>443</fpage>
          <lpage>451</lpage>
          <pub-id pub-id-type="doi">10.1007/s12471-020-01432-y</pub-id>
        </element-citation>
      </ref>
      <ref id="B37">
        <label>37</label>
        <mixed-citation>37. Seo DY, Kwak HB, Kim AH, Park SH, Heo JW, Kim HK, et al. Cardiac Adaptation to Exercise Training in Health and Disease. Pflugers Arch. 2020;472(2):155-68. doi: 10.1007/s00424-019-02266-3.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Seo</surname>
              <given-names>DY</given-names>
            </name>
            <name>
              <surname>Kwak</surname>
              <given-names>HB</given-names>
            </name>
            <name>
              <surname>Kim</surname>
              <given-names>AH</given-names>
            </name>
            <name>
              <surname>Park</surname>
              <given-names>SH</given-names>
            </name>
            <name>
              <surname>Heo</surname>
              <given-names>JW</given-names>
            </name>
            <name>
              <surname>Kim</surname>
              <given-names>HK</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Cardiac Adaptation to Exercise Training in Health and Disease</article-title>
          <source>Pflugers Arch</source>
          <year>2020</year>
          <volume>472</volume>
          <issue>2</issue>
          <fpage>155</fpage>
          <lpage>168</lpage>
          <pub-id pub-id-type="doi">10.1007/s00424-019-02266-3</pub-id>
        </element-citation>
      </ref>
      <ref id="B38">
        <label>38</label>
        <mixed-citation>38. Zhong W, Liu R, Cheng H, Xu L, Wang L, He C, et al. Longer-Term Effects of Cardiac Telerehabilitation on Patients with Coronary Artery Disease: Systematic Review and Meta-Analysis. JMIR Mhealth Uhealth. 2023;11:e46359. doi: 10.2196/46359.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Zhong</surname>
              <given-names>W</given-names>
            </name>
            <name>
              <surname>Liu</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Cheng</surname>
              <given-names>H</given-names>
            </name>
            <name>
              <surname>Xu</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Wang</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>He</surname>
              <given-names>C</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Longer-Term Effects of Cardiac Telerehabilitation on Patients with Coronary Artery Disease: Systematic Review and Meta-Analysis</article-title>
          <source>JMIR Mhealth Uhealth</source>
          <year>2023</year>
          <volume>11</volume>
          <elocation-id>e46359</elocation-id>
          <pub-id pub-id-type="doi">10.2196/46359</pub-id>
        </element-citation>
      </ref>
      <ref id="B39">
        <label>39</label>
        <mixed-citation>39. Yang Z, Jia X, Li J, Mei Z, Yang L, Yan C, et al. Efficacy and Safety of Hybrid Comprehensive Telerehabilitation (HCTR) for Cardiac Rehabilitation in Patients with Cardiovascular Disease: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. Occup Ther Int. 2023;2023:5147805. doi: 10.1155/2023/5147805.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Yang</surname>
              <given-names>Z</given-names>
            </name>
            <name>
              <surname>Jia</surname>
              <given-names>X</given-names>
            </name>
            <name>
              <surname>Li</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Mei</surname>
              <given-names>Z</given-names>
            </name>
            <name>
              <surname>Yang</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Yan</surname>
              <given-names>C</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Efficacy and Safety of Hybrid Comprehensive Telerehabilitation (HCTR) for Cardiac Rehabilitation in Patients with Cardiovascular Disease: A Systematic Review and Meta-Analysis of Randomized Controlled Trials</article-title>
          <source>Occup Ther Int</source>
          <year>2023</year>
          <volume>2023</volume>
          <size units="pages">5147805</size>
          <pub-id pub-id-type="doi">10.1155/2023/5147805</pub-id>
        </element-citation>
      </ref>
      <ref id="B40">
        <label>40</label>
        <mixed-citation>40. Gong XY, Cheng J, Wu YT, He F, Wang SH, Liu CY, et al. Effectiveness of Home-Based Cardiac Telerehabilitation Based on Wearable ECG or Heart Rate Monitoring Devices in Patients with Heart Disease: A Meta-Analysis of Randomized Controlled Trials. Geriatr Nurs. 2024;58:238-46. doi: 10.1016/j.gerinurse.2024.05.036.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Gong</surname>
              <given-names>XY</given-names>
            </name>
            <name>
              <surname>Cheng</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Wu</surname>
              <given-names>YT</given-names>
            </name>
            <name>
              <surname>He</surname>
              <given-names>F</given-names>
            </name>
            <name>
              <surname>Wang</surname>
              <given-names>SH</given-names>
            </name>
            <name>
              <surname>Liu</surname>
              <given-names>CY</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Effectiveness of Home-Based Cardiac Telerehabilitation Based on Wearable ECG or Heart Rate Monitoring Devices in Patients with Heart Disease: A Meta-Analysis of Randomized Controlled Trials</article-title>
          <source>Geriatr Nurs</source>
          <year>2024</year>
          <volume>58</volume>
          <fpage>238</fpage>
          <lpage>246</lpage>
          <pub-id pub-id-type="doi">10.1016/j.gerinurse.2024.05.036</pub-id>
        </element-citation>
      </ref>
      <ref id="B41">
        <label>41</label>
        <mixed-citation>41. Busnatu ?S, Pana MA, Lacraru AE, Jercalau CE, Paun N, Caprino M, et al. Patient Perception When Transitioning from Classic to Remote Assisted Cardiac Rehabilitation. Diagnostics. 2022;12(4):926. doi: 10.3390/diagnostics12040926.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Busnatu</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Pana</surname>
              <given-names>MA</given-names>
            </name>
            <name>
              <surname>Lacraru</surname>
              <given-names>AE</given-names>
            </name>
            <name>
              <surname>Jercalau</surname>
              <given-names>CE</given-names>
            </name>
            <name>
              <surname>Paun</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Caprino</surname>
              <given-names>M</given-names>
            </name>
            <etal>et al</etal>
          </person-group>
          <article-title>Patient Perception When Transitioning from Classic to Remote Assisted Cardiac Rehabilitation</article-title>
          <source>Diagnostics</source>
          <year>2022</year>
          <volume>12</volume>
          <issue>4</issue>
          <size units="pages">926</size>
          <pub-id pub-id-type="doi">10.3390/diagnostics12040926</pub-id>
        </element-citation>
      </ref>
    </ref-list>
    <fn-group>
      <fn fn-type="other">
        <label>Vincula&#231;&#227;o acad&#234;mica:</label>
        <p> Este artigo &#233; parte de tese de doutorado de Dilara Saklica pelo Hacettepe University Faculty of Physical Therapy and Rehabilitation.</p>
      </fn>
      <fn fn-type="other">
        <label>Aprova&#231;&#227;o &#233;tica e consentimento informado:</label>
        <p> Este estudo foi aprovado pelo Comit&#234; de &#201;tica do Hacettepe University Clinical sob o n&#250;mero de protocolo KA-20105. Todos os procedimentos envolvidos nesse estudo est&#227;o de acordo com a Declara&#231;&#227;o de Helsinki de 1975, atualizada em 2013. O consentimento informado foi obtido de todos os participantes inclu&#237;dos no estudo. O ensaio foi registrado no ClinicalTrials.gov (c&#243;digo de registro: NCT05264701).</p>
      </fn>
      <fn fn-type="other">
        <label>Uso de Intelig&#234;ncia Artificial:</label>
        <p> Os autores n&#227;o utilizaram ferramentas de intelig&#234;ncia artificial no desenvolvimento deste trabalho.</p>
      </fn>
      <fn fn-type="data-availability" specific-use="data-not-available">
        <label>Disponibilidade de Dados:</label>
        <p> Os dados n&#227;o podem ser disponibilizados publicamente para evitar qualquer risco de reidentifica&#231;&#227;o de informa&#231;&#245;es pessoais e de acordo com as condi&#231;&#245;es da aprova&#231;&#227;o &#233;tica, os dados em n&#237;vel individual dos pacientes n&#227;o est&#227;o dispon&#237;veis para uso fora deste estudo.</p>
      </fn>
      <fn fn-type="supplementary-material" id="suppl01">
        <label>*Material suplementar</label>
        <p> Para informa&#231;&#227;o adicional, por favor, <ext-link ext-link-type="uri" xlink:href="http://abccardiol.org/supplementary-material/2025/12206/2024-0765_AO_SupplementaryFile.pdf">clique aqui</ext-link>. </p>
      </fn>
      <fn fn-type="financial-disclosure">
        <label>Fontes de financiamento:</label>
        <p> O presente estudo n&#227;o teve fontes de financiamento externas.</p>
      </fn>
    </fn-group>
  </back>
  <sub-article article-type="translation" id="TRen" xml:lang="en">
    <front-stub>
      <article-id pub-id-type="doi">10.36660/abc.20240765i</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Original Article</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>The Impact of Technology-Based Cardiac Rehabilitation on Exercise Capacity and Adherence in Patients with Coronary Artery Disease: An Artificial Intelligence Analysis</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-9192-6033</contrib-id>
          <name>
            <surname>Saklica</surname>
            <given-names>Dilara</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Acquisition of data</role>
          <role>Analysis and interpretation of the data</role>
          <role>Statistical analysis</role>
          <role>Writing of the manuscript</role>
          <xref ref-type="aff" rid="aff1001">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-0218-140X</contrib-id>
          <name>
            <surname>Vardar-Yagli</surname>
            <given-names>Naciye</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Acquisition of data</role>
          <role>Analysis and interpretation of the data</role>
          <role>Statistical analysis</role>
          <role>Writing of the manuscript</role>
          <role>Critical revision of the manuscript for content</role>
          <xref ref-type="aff" rid="aff1001">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Saglam</surname>
            <given-names>Melda</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Analysis and interpretation of the data</role>
          <role>Critical revision of the manuscript for content</role>
          <xref ref-type="aff" rid="aff1001">
            <sup>1</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Yuce</surname>
            <given-names>Deniz</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Statistical analysis</role>
          <role>Critical revision of the manuscript for content</role>
          <xref ref-type="aff" rid="aff2001">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Ates</surname>
            <given-names>Ahmet Hakan</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Acquisition of data</role>
          <role>Critical revision of the manuscript for content</role>
          <xref ref-type="aff" rid="aff3001">
            <sup>3</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-7673-229X</contrib-id>
          <name>
            <surname>Yorgun</surname>
            <given-names>Hikmet</given-names>
          </name>
          <role>Conception and design of the research</role>
          <role>Acquisition of data</role>
          <role>Critical revision of the manuscript for content</role>
          <xref ref-type="aff" rid="aff3001">
            <sup>3</sup>
          </xref>
        </contrib>
      </contrib-group>
      <aff id="aff1001">
        <label>1</label>
        <country country="&lt;br /&gt; &lt;b&gt;Notice&lt;/b&gt;: Undefined offset: 0 in &lt;b&gt;/var/www/xconv.beta.caboverde.local/xconv3/vendors/xcolor/ws_waita.php&lt;/b&gt; on line &lt;b&gt;76&lt;/b&gt;&lt;br /&gt; ">T&#252;rkiye</country>
        <institution content-type="original">Faculty of Physical Therapy and Rehabilitation, Department of Cardiorespiratory Physiotherapy and Rehabilitation, Hacettepe University, Ankara &#8211; T&#252;rkiye</institution>
      </aff>
      <aff id="aff2001">
        <label>2</label>
        <country country="&lt;br /&gt; &lt;b&gt;Notice&lt;/b&gt;: Undefined offset: 0 in &lt;b&gt;/var/www/xconv.beta.caboverde.local/xconv3/vendors/xcolor/ws_waita.php&lt;/b&gt; on line &lt;b&gt;76&lt;/b&gt;&lt;br /&gt; ">T&#252;rkiye</country>
        <institution content-type="original">Faculty of Medicine, Department of Preventive Oncology, Hacettepe University, Ankara &#8211; T&#252;rkiye</institution>
      </aff>
      <aff id="aff3001">
        <label>3</label>
        <country country="&lt;br /&gt; &lt;b&gt;Notice&lt;/b&gt;: Undefined offset: 0 in &lt;b&gt;/var/www/xconv.beta.caboverde.local/xconv3/vendors/xcolor/ws_waita.php&lt;/b&gt; on line &lt;b&gt;76&lt;/b&gt;&lt;br /&gt; ">T&#252;rkiye</country>
        <institution content-type="original">Faculty of Medicine, Department of Cardiology, Hacettepe University, Ankara &#8211; T&#252;rkiye</institution>
      </aff>
      <author-notes>
        <corresp id="c01001"><label>Mailing Address:</label> Naciye Vardar-Yagli &#8226; Hacettepe University, Faculty of Physical Therapy and Rehabilitation 06100 Samanpazar&#305;/Ankara &#8211; T&#252;rkiye E-mail: naciyevardar@yahoo.com </corresp>
        <fn fn-type="conflict">
          <label>Potential conflict of interest:</label>
          <p>No potential conflict of interest relevant to this article was reported.</p>
        </fn>
        <fn fn-type="edited-by">
          <label>Editor responsible for the review</label>
          <p> Ricardo Stein</p>
        </fn>
      </author-notes>
      <abstract>
        <title>Abstract</title>
        <sec>
          <title>Background</title>
          <p> Exercise training programs improve exercise capacity and quality of life (QoL) in patients with coronary artery disease (CAD). Although artificial intelligence (AI) has been used to design such programs, there are still few studies evaluating their effectiveness.</p>
        </sec>
        <sec>
          <title>Objectives</title>
          <p> This study compared the effects of technology-based and traditional programs for cardiac rehabilitation (CR) on exercise capacity and participation in patients with CAD using AI for data analysis.</p>
        </sec>
        <sec>
          <title>Methods</title>
          <p> A total of 52 patients with CAD were randomly assigned to three groups: i) telerehabilitation group (TRG) (n=18); ii) mobile application group (MAG) (n=13); and iii) control group (CG), which received only physical activity recommendations (n=21). TRG and MAG participants completed a 12-week program with calisthenic and resistance exercises three times a week. Exercise capacity was assessed using the Incremental Shuttle Walk Test (ISWT), and QoL was measured with the Short Form-36 (SF-36). Patient feedback was analyzed using a fine-tuned BERT-based natural language processing (NLP) model. Anomaly detection methods were applied to find mismatches between self-reported adherence and ISWT results. Statistical significance was set at p&lt;0.05.</p>
        </sec>
        <sec>
          <title>Results</title>
          <p> Both TRG [44.4% female] (&#916;=87.2&#177;15.2 m) and MAG [50% female] (&#916;=89.4&#177;70.4 m) had significant ISWT improvements compared to CG [47.6% female] (&#916;=10.9&#177;28.2 m) (p=0.001). Adherence was higher in TRG (100%) and MAG (80%) than in CG (30%) (p&lt;0.001). Patient-reported satisfaction, analyzed via NLP, showed a significant positive correlation with ISWT improvements (r=0.75, p&lt;0.001). Findings show the potential of AI to support outcome assessment in CR.</p>
        </sec>
        <sec>
          <title>Conclusions</title>
          <p> Technology-based CR programs improve exercise capacity and adherence in patients with CAD, supporting the use of AI-driven tools. NLP analysis helped link patient feedback to exercise outcomes and detect inconsistencies, showing its value in enhancing CR evaluation.</p>
        </sec>
      </abstract>
      <abstract abstract-type="graphical">
        <p>
          <fig id="f01001">
            <label>Central Illustration: </label>
            <caption>
              <title>The Impact of Technology-Based Cardiac Rehabilitation on Exercise Capacity and Adherence in Patients with Coronary Artery Disease: An Artificial Intelligence Analysis</title>
            </caption>
            <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf01-en.tif"/></fig>
        </p>
      </abstract>
      <kwd-group xml:lang="en">
        <kwd>Artificial Intelligence</kwd>
        <kwd>Cardiac Rehabilitation</kwd>
        <kwd>Coronary Artery Disease</kwd>
        <kwd>Exercise</kwd>
      </kwd-group>
    </front-stub>
    <body>
      <sec sec-type="intro">
        <title>Introduction</title>
        <p>Programs for cardiac telerehabilitation (CTR) have been shown to be of comparable benefit and validity to traditional, in-person rehabilitation for patients.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Beatty et al. confirmed that mobile technology is both reliable and acceptable for use in cardiac rehabilitation (CR) for patients with ischemic heart disease.<sup><xref ref-type="bibr" rid="B2">2</xref></sup> Using technology in CR helps improve access and participation. Research shows that exercise-based programs for CR can increase exercise capacity, strengthen peripheral muscles, and improve quality of life (QoL) in patients with coronary artery disease (CAD).<sup><xref ref-type="bibr" rid="B3">3</xref>,<xref ref-type="bibr" rid="B4">4</xref></sup> Clinical guidelines also support the safe use of both aerobic and resistance training in this population.<sup><xref ref-type="bibr" rid="B1">1</xref>,<xref ref-type="bibr" rid="B5">5</xref></sup> Calisthenics is another common exercise method used in programs for CR.<sup><xref ref-type="bibr" rid="B6">6</xref></sup></p>
        <p>In recent years, CR has increasingly adopted technologies such as electrocardiography (ECG) devices for remote monitoring, heart rate (HR) and blood pressure (BP) sensors, functional capacity testing algorithms, and activity trackers.<sup><xref ref-type="bibr" rid="B7">7</xref>,<xref ref-type="bibr" rid="B8">8</xref></sup> CTR, virtual reality, and phone-based CR interventions &#8212; which enable patient care without direct supervision &#8212; are also receiving growing attention in literature.<sup><xref ref-type="bibr" rid="B9">9</xref>,<xref ref-type="bibr" rid="B10">10</xref></sup></p>
        <p>Artificial intelligence (AI) has made rapid progress in health care, especially in areas like interpreting radiological images, predicting outcomes, and detecting cardiac events early.<sup><xref ref-type="bibr" rid="B11">11</xref>-<xref ref-type="bibr" rid="B15">15</xref></sup> Machine learning has also shown potential in helping design and evaluate the safety of exercise programs for CR.<sup><xref ref-type="bibr" rid="B16">16</xref></sup> In addition, technical challenges such as algorithm transparency, data security, and ethical concerns about patient privacy continue to limit the broader use of AI in CTR.<sup><xref ref-type="bibr" rid="B17">17</xref></sup> More research and better AI model development are needed to improve clinical use and ensure safe, patient-centered outcomes. While many studies focus on using patient data to personalize exercise programs for individuals with CAD, few have explored how AI can analyze patients&#8217; own descriptions of how the programs benefit them.</p>
        <p>Natural language processing (NLP) offers a promising way to extract meaningful insights from unstructured text found in electronic health records.<sup><xref ref-type="bibr" rid="B18">18</xref></sup> To date, no studies have leveraged AI to interpret the subjective experiences of patients with CAD regarding the advantages of exercise-based programs for CR.</p>
        <p>Participation in programs for CR remains low worldwide. One of the biggest challenges is patient nonadherence and dropout.<sup><xref ref-type="bibr" rid="B19">19</xref></sup> The COVID-19 pandemic has exacerbated this problem, prompting health care providers to seek innovative solutions to increase participation, accessibility, efficiency, and cost-effectiveness of programs for CR.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> In the United States, only 20% to 30% of eligible patients participate in programs for CR. Among those who do start enroll, dropout rates range from 24% to 50%, which means many patients do not receive the full benefits of CR.<sup><xref ref-type="bibr" rid="B21">21</xref></sup> To improve participation and adherence, health care providers have tested several strategies. Successful interventions include automated referral systems and the use of CR liaisons to help patients transition from hospital to outpatient care. These methods have been shown to significantly boost enrollment and program completion rates.<sup><xref ref-type="bibr" rid="B22">22</xref></sup></p>
        <p>However, the COVID-19 pandemic has made it even harder for patients to participate in CR, leading to the search for new ways to improve accessibility, efficiency, and cost-effectiveness of such programs. One promising solution is the use of home-based and hybrid CR models, which combine traditional center-based rehab with remote, at-home components. Such models have been shown to be just as safe and effective as traditional CR, while giving patients more flexibility.<sup><xref ref-type="bibr" rid="B23">23</xref></sup></p>
        <p>Recent studies have shown that AI can be successfully integrated into cardiology, especially in areas such as ECG analysis and nuclear cardiology imaging.<sup><xref ref-type="bibr" rid="B24">24</xref>,<xref ref-type="bibr" rid="B25">25</xref></sup> However, to the best of our knowledge, this is the first study to apply NLP-based methods in the context of CR, making it a novel contribution to the growing intersection of AI and cardiovascular care.</p>
        <p>This study aimed to compare the effects of technology-based and traditional programs for CR on exercise capacity and participation in patients with CAD using AI for data analysis.</p>
      </sec>
      <sec sec-type="methods">
        <title>Methods</title>
        <p>This prospective, randomized controlled trial was conducted between April 2022 and May 2024 at the Department of Cardiorespiratory Physiotherapy and Rehabilitation, Faculty of Physiotherapy and Rehabilitation, Hacettepe University.</p>
        <p>Patients with a diagnosis of CAD who visited the cardiology outpatient clinic were screened for eligibility. Those diagnosed with CAD by coronary angioplasty, with negative troponin levels, stable clinical status, and a symptom-limited treadmill test (modified Bruce protocol) showing no cardiac symptoms or ECG abnormalities, were referred to a physical therapist for CR and enrolled in an exercise program.</p>
        <p>Inclusion criteria were i) clinically stable status; ii) age between 40 and 70 years; iii) access to online exercise training; and iv) ownership of an iOS- or Android-compatible smartphone.</p>
        <p>Exclusion criteria were i) diagnosis of chronic heart failure (New York Heart Association [NYHA] class III or IV); ii) &#8805;50% stenosis of any major coronary artery; iii) any coronary event or surgical revascularization in the past 12 months; iv) left ventricular ejection fraction (LVEF) &lt;40%; v) end-stage renal disease; vi) acute myocarditis or pericarditis; vii) uncontrolled hypertension; viii) chronic lung disease; ix) orthopedic or neurological conditions that would prevent participation in exercise or testing; x) sustained ventricular tachycardia; xi) uncontrollable atrial fibrillation; or xii) high-grade atrioventricular block.</p>
        <p>Participants were evaluated at the beginning and at the end of the 12-week exercise program. All assessments followed the same order and were conducted according to the standards set by the lead physical therapist. Demographic, clinical, and exercise-related data were collected.</p>
        <p>After the baseline evaluations, patients who met the inclusion criteria and agreed to participate were randomly assigned to one of three groups using the online tool available from https://www.graphpad.com/quickcalcs/randomize1.cfm. The telerehabilitation group (TRG) performed calisthenic and resistance exercises under the remote supervision of a physical therapist through video conferencing. The mobile application group (MAG) followed the same exercises individually guided by videos in a mobile app. The control group (CG) followed a standard home-based exercise program without supervision.</p>
        <p>The Incremental Shuttle Walk Test (ISWT) was used to measure exercise capacity due to its proven validity and reliability in patients with CAD.<sup><xref ref-type="bibr" rid="B26">26</xref></sup> It consists of 12 levels, during which participants gradually increase their walking speed every minute. An auditory signal guides them to walk back and forth between two cones placed ten meters apart, and the total distance covered is recorded.</p>
        <p>The total number of exercise sessions completed by participants in the TRG was recorded. For the MAG, session attendance was tracked through notifications automatically sent to the physical therapists after each exercise session. Participants in the CG were asked to keep an exercise diary to record the days they engaged in physical activity.</p>
        <p>To assess QoL, the Short Form-36 (SF-36) was administered through an interview. The SF-36 is a self-report questionnaire consisting of 36 items designed to evaluate an individual&#8217;s overall health status. It covers eight domains: physical functioning (PF), role-physical (RP), bodily pain (BP), general health (GH), vitality, social functioning (SF), role-emotional (RE), and mental health (MH).<sup><xref ref-type="bibr" rid="B27">27</xref></sup></p>
        <sec>
          <title>Exercise training protocol</title>
          <p>Participants in the TRG followed an online exercise program under the supervision of a physical therapist. Those in the MAG group exercised independently using videos provided through a mobile app installed on their devices by the physical therapist. Each session included a warm-up and cool-down period.</p>
          <p>During the first 4 weeks, participants performed calisthenic and postural exercises. Between weeks 4 and 8, upper and lower body resistance training was added to the calisthenic routine. Resistance exercises were done using elastic bands selected based on each individual&#8217;s muscle strength. Exercise intensity was adjusted by changing the number of repetitions and sets, with at least 1 min of rest allowed between sets.</p>
          <p>From weeks 9 to 12, the difficulty of the exercises increased progressively according to each participant&#8217;s fitness level. All participants in TRG and MAG completed the exercises three times per week for 12 weeks (<xref ref-type="fig" rid="f02001">Figure 1</xref>, Supplementary File S1). Participants in CG were advised to follow the World Health Organization Physical Activity Guidelines, which recommend 150-300 minutes of moderate-intensity or 75-150 minutes of vigorous-intensity physical activity per week.<sup><xref ref-type="bibr" rid="B28">28</xref></sup></p>
          <p>
            <fig id="f02001">
              <label>Figure 1</label>
              <caption>
                <title>&#8211; Flow diagram of patient inclusion in the study. AI: artificial intelligence; CG: control group; CTR: cardiac telerehabilitation; ISWT: Incremental Shuttle Walk Test; MAG: mobile application group; NLP: natural language processing; PT: physical therapist; SF-36: Short-Form-36; TRG: telerehabilitation group.</title>
              </caption>
              <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf02-en.tif"/></fig>
          </p>
          <p>Participants in the TRG were monitored for fatigue, leg fatigue, and shortness of breath using the modified Borg scale (mBS), along with self-measured BP before and after each exercise session. Exercise intensity was adjusted to maintain a perceived exertion level between 4 and 6 on the mBS. HR was continuously monitored using a smartwatch (Mi Smart Band 4, Anhui Huami Information Technology Co., Ltd.), ensuring participants reached 60%-75% of their maximum HR (HRmax) and maintained an mBS score of 4 to 6 during exercise.<sup><xref ref-type="bibr" rid="B29">29</xref></sup> All devices were calibrated before being given to participants.</p>
          <p>Participants in MAG self-reported fatigue, leg fatigue, and shortness of breath using the mBS before and after each session, following video instructions on their phones. They also measured and recorded their HR and BP using a provided smartwatch and BP monitor. The mobile app included a secure login system to protect patient privacy.</p>
        </sec>
        <sec>
          <title>Artificial intelligence</title>
          <p>The effectiveness of the prescribed exercises was evaluated through regular patient feedback about their exercise experience. Open-ended questions in a questionnaire were used to collect subjective responses, which were then analyzed using AI and machine learning techniques to extract quantitative insights.</p>
          <p>To identify potential outliers, anomaly detection methods were applied in cases where patients reported consistent participation but showed limited improvement in ISWT performance &#8212; for example, an increase of less than 70 meters, even though 95% of compliant participants improved by at least that amount.</p>
          <p>A pre-trained transformer model &#8212; NLPtown/BERT-base-multilingual-uncased-sentiment &#8212; was used to assess the emotional tone of each patient&#8217;s feedback (BERT = Bidirectional Encoder Representations from Transformers).<sup><xref ref-type="bibr" rid="B30">30</xref></sup> Responses to the open-ended questions were processed using AI and NLP techniques.</p>
          <p>NLP analysis was performed using the BERT model to evaluate open-ended feedback from patients.<sup><xref ref-type="bibr" rid="B31">31</xref></sup> It was fine-tuned with a domain-specific sentiment dataset focused on patient feedback. This dataset included subjective evaluations of exercise difficulty, perceived benefits, adherence challenges, and overall satisfaction with the CR program. It was built using anonymized patient reviews and structured feedback from previous clinical studies, ensuring a diverse set of sentiment expressions.</p>
          <p>The model&#8217;s performance was validated using k-fold cross-validation, achieving an average F1-score of 0.89, indicating strong reliability in sentiment classification. NLP analysis focused on two main aspects: overall satisfaction with the program and reports of exercise difficulty or ease.</p>
          <p>For each patient&#8217;s response, the sentiment analysis pipeline assigned a sentiment label and a corresponding score from 1 to 5 (1 = highly negative, 5 = highly positive) representing the intensity of the emotional tone.</p>
          <p>Every step was taken to protect data from third party access. Compliance was monitored regularly.</p>
        </sec>
        <sec>
          <title>Statistical analysis</title>
          <p>Statistical analysis was performed using IBM SPSS software (Version 20.0, IBM Inc.). A pilot study showed that at least 11 participants per group were needed to achieve 95% power, with a 5% chance of type I error and an effect size of 1.76 for the primary outcome (ISWT distance).</p>
          <p>The Shapiro-Wilk test was used to assess whether data followed a normal distribution. Continuous variables with normal distribution were reported as mean &#177; standard deviation (SD), while those without normal distribution were presented as median and interquartile range. Categorical variables were reported as absolute (counts) and relative frequencies (percentages).</p>
          <p>For comparisons within each group, the paired samples t-test was used for normally distributed data, and the Wilcoxon signed-rank test was used for nonnormal data. To compare data between groups, one-way analysis of variance (ANOVA) was used for normally distributed variables, with Tukey&#8217;s honestly significant difference (HSD) test for post hoc pairwise comparisons. For nonnormal data, the Kruskal-Wallis test was used, followed by the Dunn&#8217;s test for pairwise comparisons. Categorical variables were analyzed using the chi-square test, or Fisher&#8217;s exact test when expected counts were below 5.</p>
          <p>The Pearson&#8217;s correlation coefficient was used to assess the relationship between patients&#8217; natural language feedback on the benefits of exercise training and their changes in ISWT performance. An intention-to-treat analysis was applied to include pre-exercise data from participants who did not complete the program. A p-value of 0.05 or less was considered statistically significant.</p>
        </sec>
      </sec>
      <sec sec-type="results">
        <title>Results</title>
        <p>Out of 147 patients with CAD screened at the cardiology outpatient clinic of the Faculty of Medicine, Hacettepe University, 55 met the inclusion criteria and agreed to participate in the study. Three participants from the MAG group withdrew, and the study was completed with a total of 52 participants. <xref ref-type="fig" rid="f03001">Figure 2</xref> presents the study flow diagram.</p>
        <p>
          <fig id="f03001">
            <label>Figure 2</label>
            <caption>
              <title>&#8211; CONSORT flow diagram of patient inclusion in the study. CG: control group; CONSORT: Consolidated Standards of Reporting Trials; MAG: mobile application group; TRG: telerehabilitation group.</title>
            </caption>
            <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf03-en.tif"/></fig>
        </p>
        <p><xref ref-type="table" rid="t1001">Table 1</xref> shows demographic and clinical characteristics of patients. There were no statistically significant differences between groups in age, body weight, height, body mass index (BMI), waist-hip ratio, cardiovascular risk factors, or metabolic equivalent of task (MET) values from the stress test.</p>
        <p>
          <table-wrap id="t1001">
            <label>Table 1</label>
            <caption>
              <title>&#8211; Demographic characteristics of patients included in the study</title>
            </caption>
            <table frame="hsides" rules="groups">
              <colgroup>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
              </colgroup>
              <thead>
                <tr>
                  <th align="left">Variables</th>
                  <th>TRG (n=18)</th>
                  <th>MAG (n=16)</th>
                  <th>CG (n=21)</th>
                  <th>p-value</th>
                </tr>
              </thead>
              <tbody>
                <tr>
                  <td>Age (years)</td>
                  <td align="center">60.1&#177;7.2</td>
                  <td align="center">56.9&#177;5.8</td>
                  <td align="center">61.6&#177;1.5</td>
                  <td align="center">0.12</td>
                </tr>
                <tr>
                  <td>Female/male</td>
                  <td align="center">8 (44.4%)/10 (55.6%)</td>
                  <td align="center">8 (50%)/8 (50%)</td>
                  <td align="center">10 (47.6%)/11 (52.4%)</td>
                  <td align="center">0.95</td>
                </tr>
                <tr>
                  <td>Weight (kg)</td>
                  <td align="center">76.9&#177;3.1</td>
                  <td align="center">80.9&#177;10.3</td>
                  <td align="center">79.7&#177;2.7</td>
                  <td align="center">0.61</td>
                </tr>
                <tr>
                  <td>BMI (kg/m2)</td>
                  <td align="center">26.2&#177;0.6</td>
                  <td align="center">27.3&#177;1.9</td>
                  <td align="center">28.5&#177;1.1</td>
                  <td align="center">0.12</td>
                </tr>
                <tr>
                  <td>Waist-hip ratio</td>
                  <td align="center">0.9&#177;0.1</td>
                  <td align="center">0.9&#177;0.1</td>
                  <td align="center">0.9&#177;0.1</td>
                  <td align="center">0.54</td>
                </tr>
                <tr>
                  <td>Number of steps per day</td>
                  <td align="center">3578.5 (2622.5-4345.5)</td>
                  <td align="center">3981.5 (3418-4744.25)</td>
                  <td align="center">3177 (3962-2585)</td>
                  <td align="center">0.15</td>
                </tr>
                <tr>
                  <td>Exercise stress test (METs)</td>
                  <td align="center">11.05 (10.3-13.2)</td>
                  <td align="center">10.9 (10.1-12.8)</td>
                  <td align="center">10.5 (9.5-11.4)</td>
                  <td align="center">0.35</td>
                </tr>
                <tr>
                  <td colspan="5">
                    <bold>Cardiovascular risk factors</bold>
                  </td>
                </tr>
                <tr>
                  <td colspan="5">
                    <bold>Smoking</bold>
                  </td>
                </tr>
                <tr>
                  <td>Nonsmoker</td>
                  <td align="center">8 (44.4%)</td>
                  <td align="center">7 (43.75%)</td>
                  <td align="center">10 (47.6%)</td>
                  <td align="center" rowspan="3">0.91</td>
                </tr>
                <tr>
                  <td>Smoker</td>
                  <td align="center">4 (22.2%)</td>
                  <td align="center">3 (18.75%)</td>
                  <td align="center">6 (28.6%)</td>
                </tr>
                <tr>
                  <td>Quit smoking</td>
                  <td align="center">6 (33.3%)</td>
                  <td align="center">6 (37.5%)</td>
                  <td align="center">5 (23.8%)</td>
                </tr>
                <tr>
                  <td>Smoking (pack-years)</td>
                  <td align="center">14.8&#177;15.9</td>
                  <td align="center">13.4&#177;13.6</td>
                  <td align="center">16.1&#177;17.4</td>
                  <td align="center">0.93</td>
                </tr>
                <tr>
                  <td>
                    <bold>Hypertension</bold>
                  </td>
                  <td align="center">10 (55.6%)</td>
                  <td align="center">8 (50.0%)</td>
                  <td align="center">9 (42.9%)</td>
                  <td align="center">0.73</td>
                </tr>
                <tr>
                  <td>
                    <bold>Diabetes mellitus</bold>
                  </td>
                  <td align="center">4 (22.2%)</td>
                  <td align="center">4 (25.0%)</td>
                  <td align="center">5 (23.8%)</td>
                  <td align="center">0.98</td>
                </tr>
                <tr>
                  <td>
                    <bold>Dyslipidemia</bold>
                  </td>
                  <td align="center">14 (77.8%)</td>
                  <td align="center">13 (81.25%)</td>
                  <td align="center">18 (85.7%)</td>
                  <td align="center">0.81</td>
                </tr>
                <tr>
                  <td>
                    <bold>Physical inactivity</bold>
                  </td>
                  <td align="center">17 (94.4%)</td>
                  <td align="center">13 (81.25%)</td>
                  <td align="center">20 (95.2%)</td>
                  <td align="center">0.28</td>
                </tr>
              </tbody>
            </table>
            <table-wrap-foot>
              <fn id="TFN1001">
                <p>*p&lt;0.05, chi-square test, Fisher&#8217;s exact test, analysis of variance (ANOVA), or Kruskal&#8211;Wallis test. Data are presented as mean&#177;SD, median (IQR [Q1-Q3]), or n (%). CG: control group; IQR: interquartile range; MAG: mobile application group; METs: metabolic equivalent of task; TRG: telerehabilitation group.</p>
              </fn>
            </table-wrap-foot>
          </table-wrap>
        </p>
        <p>No statistically significant differences were found between groups in ISWT distance, HR, systolic and diastolic BP, dyspnea, or general fatigue levels (measured by the modified Borg scale) before the start of exercise training (<xref ref-type="table" rid="t2001">Table 2</xref>). Both TRG and MAG showed similar improvements in several SF-36 QoL subscales (ie, PF, BP, GH, SF, vitality, RE, and MH) compared to the control group. Both groups also showed better results in the percentage of expected ISWT distance than the control group.</p>
        <p>
          <table-wrap id="t2001">
            <label>Table 2</label>
            <caption>
              <title>&#8211; Three-month cardiac rehabilitation: between-group comparison of outcomes</title>
            </caption>
            <table frame="hsides" rules="groups">
              <colgroup>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
              </colgroup>
              <thead>
                <tr>
                  <th align="left" rowspan="2">Exercise capacity parameters</th>
                  <th colspan="3">TRG (n=18)</th>
                  <th colspan="3">MAG (n=13)</th>
                  <th colspan="3">CG (n=21)</th>
                </tr>
                <tr>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                </tr>
              </thead>
              <tbody>
                <tr>
                  <td>
                    <bold>HR (bpm)</bold>
                  </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                </tr>
                <tr>
                  <td>Pre-test</td>
                  <td align="center">79.2&#177;10.5</td>
                  <td align="center">
                    <bold>76.8&#177;10.9</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">-2.4&#177;3.1</td>
                  <td align="center">74.8&#177;11.7</td>
                  <td align="center">72.6&#177;7.9</td>
                  <td align="center">-2.2&#177;5.9</td>
                  <td align="center">85.1&#177;13.9</td>
                  <td align="center">84.6&#177;11.9</td>
                  <td align="center">-0.5&#177;4.3</td>
                </tr>
                <tr>
                  <td>Post-test</td>
                  <td align="center">135.6&#177;6.6</td>
                  <td align="center">
                    <bold>132.1&#177;6.3</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">-3.5&#177;5.3</td>
                  <td align="center">136.9&#177;5.5</td>
                  <td align="center">137.9&#177;4.5</td>
                  <td align="center">0.9&#177;3.4</td>
                  <td align="center">133.3&#177;5.9</td>
                  <td align="center">134.4&#177;4.5</td>
                  <td align="center">1.1&#177;4.3</td>
                </tr>
                <tr>
                  <td>%HRmax</td>
                  <td align="center">84.8&#177;1.6</td>
                  <td align="center">
                    <bold>82.6&#177;2.9</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>-2.2&#177;3.3</bold>
                    <sup>
                      <bold>b,d</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">84&#177;1.6</td>
                  <td align="center">84.2&#177;13</td>
                  <td align="center">0.2&#177;1.2</td>
                  <td align="center">84.2&#177;2.1</td>
                  <td align="center">84.9&#177;2.6</td>
                  <td align="center">0.7&#177;2.7</td>
                </tr>
                <tr>
                  <td>
                    <bold>DBP (mmHg)</bold>
                  </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                </tr>
                <tr>
                  <td>Pre-test</td>
                  <td align="center">73.3&#177;7.7</td>
                  <td align="center">70.6&#177;6.4</td>
                  <td align="center">-2.8&#177;6.7</td>
                  <td align="center">70.6&#177;7.7</td>
                  <td align="center">70&#177;5.2</td>
                  <td align="center">-0.6&#177;5.7</td>
                  <td align="center">70&#177;7.7</td>
                  <td align="center">70&#177;6.3</td>
                  <td align="center">0&#177;5.5</td>
                </tr>
                <tr>
                  <td>Post-test</td>
                  <td align="center">82.2&#177;7.3</td>
                  <td align="center">80&#177;6.9</td>
                  <td align="center">-2.2&#177;7.3</td>
                  <td align="center">80&#177;8.2</td>
                  <td align="center">79.2&#177;5.7</td>
                  <td align="center">-0.8&#177;6.8</td>
                  <td align="center">76.2&#177;8.1</td>
                  <td align="center">78.6&#177;7.3</td>
                  <td align="center">2.4&#177;5.4</td>
                </tr>
                <tr>
                  <td>
                    <bold>SBP (mmHg)</bold>
                  </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                </tr>
                <tr>
                  <td>Pre-test</td>
                  <td align="center">118.3&#177;8.6</td>
                  <td align="center">118.9&#177;8.3</td>
                  <td align="center">0.6&#177;4.2</td>
                  <td align="center">118.1&#177;9.8</td>
                  <td align="center">118.5&#177;8.1</td>
                  <td align="center">0.3&#177;5.8</td>
                  <td align="center">118.6&#177;7.3</td>
                  <td align="center">121.9&#177;8.1</td>
                  <td align="center">3.3&#177;8</td>
                </tr>
                <tr>
                  <td>Post-test</td>
                  <td align="center">148.3&#177;9.9</td>
                  <td align="center">148.3&#177;2.4</td>
                  <td align="center">0&#177;12.4</td>
                  <td align="center">145&#177;6.3</td>
                  <td align="center">146.2&#177;12.4</td>
                  <td align="center">1.2&#177;12.8</td>
                  <td align="center">146.2&#177;9.2</td>
                  <td align="center">149.5&#177;8.6</td>
                  <td align="center">3.3&#177;11.1</td>
                </tr>
                <tr>
                  <td colspan="4">
                    <bold>General fatigue (mBorg)</bold>
                  </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                </tr>
                <tr>
                  <td>Pre-test</td>
                  <td align="center">0.5 (0-1)</td>
                  <td align="center">0.5 (0-0.8)</td>
                  <td align="center">0 (-0.5, 0)</td>
                  <td align="center">0.5 (0-1)</td>
                  <td align="center">0.5 (0.5-1)</td>
                  <td align="center">0 (-0.5, 0.5)</td>
                  <td align="center">1 (0-1)</td>
                  <td align="center">0.5 (0-1)</td>
                  <td align="center">0 (-1, 0)</td>
                </tr>
                <tr>
                  <td>Post-test</td>
                  <td align="center">4 (3-5.75)</td>
                  <td align="center">4.5 (3-5)</td>
                  <td align="center">0 (-0.75, 1.75)</td>
                  <td align="center">4 (3-5)</td>
                  <td align="center">5 (4-5)</td>
                  <td align="center">1 (-1, 2)</td>
                  <td align="center">5 (3-5)</td>
                  <td align="center">3 (3-4)</td>
                  <td align="center">1 (-2, 0)</td>
                </tr>
                <tr>
                  <td>
                    <bold>Dyspnea (mBorg)</bold>
                  </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                  <td colspan="3"> </td>
                </tr>
                <tr>
                  <td>Pre-test</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0, 0)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0, 0)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Post-test</td>
                  <td align="center">0 (0-1)</td>
                  <td align="center">1 (0-2)</td>
                  <td align="center">0 (0, 2)</td>
                  <td align="center">0 (0-0)</td>
                  <td align="center">0 (0-1)</td>
                  <td align="center">0 (0, 1)</td>
                  <td align="center">0 (0-0.5)</td>
                  <td align="center">0 (0-0.5)</td>
                  <td align="center">0 (0, 0.5)</td>
                </tr>
                <tr>
                  <td>
                    <bold>ISWT distance (m)</bold>
                  </td>
                  <td align="center">508.9&#177;105.5</td>
                  <td align="center">
                    <bold>596.1&#177;109.3</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>87.2&#177;15.3</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">537.5&#177;119.1</td>
                  <td align="center">
                    <bold>626.9&#177;92.1</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>89.4&#177;70.4</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">500.5&#177;98.4</td>
                  <td align="center">511.4&#177;102</td>
                  <td align="center">11&#177;28.3</td>
                </tr>
                <tr>
                  <td>
                    <bold>ISWT distance (%)</bold>
                  </td>
                  <td align="center">70.8&#177;9.3</td>
                  <td align="center">
                    <bold>83.3&#177;10.4</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>12.5&#177;3.4</bold>
                    <sup>
                      <bold>b,d</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">72.6&#177;8.4</td>
                  <td align="center">
                    <bold>83.1&#177;9</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10.5&#177;3.6</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">73.2&#177;8.7</td>
                  <td align="center">74.6&#177;7.5</td>
                  <td align="center">1.5&#177;4.1</td>
                </tr>
              </tbody>
            </table>
            <table-wrap-foot>
              <fn id="TFN2001">
                <p>*p&lt;0.05, analysis of variance (ANOVA) or Kruskal-Wallis test. Data are presented as mean&#177;SD or median (IQR [Q1-Q3]). CG: control group; DBP: diastolic blood pressure; HR: heart rate; ISWT: Incremental Shuttle Walk Test; IQR: interquartile range; MAG: mobile application group; mBorg: modified Borg scale; SBP: systolic blood pressure; SPO<sub>2</sub>: oxygen saturation; %HRmax: percentage of maximum HR; TRG: telerehabilitation group. a: Significant difference pre- vs post-exercise within the same group. b: Significant difference between TRG and CG. c: Significant difference between MAG and CG. d: Significant difference between TRG and MAG.</p>
              </fn>
            </table-wrap-foot>
          </table-wrap>
        </p>
        <p>These findings suggest the TRG and MAG interventions provided similar benefits in improving QoL and functional capacity. In addition, TRG showed a significantly greater percentage increase in expected ISWT distance compared to the MAG group (<xref ref-type="table" rid="t2001">Table 2</xref>).</p>
        <p>General fatigue and dyspnea scores, measured by the modified Borg scale, showed no significant differences between or within groups before and after the exercise program. Likewise, systolic and diastolic BP remained unchanged across and within groups (<xref ref-type="table" rid="t2001">Table 2</xref>). Such results suggest these physiological measures stayed stable throughout the intervention in all groups.</p>
        <p>Changes in HR (&#916;HR) before and after exercise, as well as the percentage of HRmax (%HRmax), were significantly lower in the TRG after the exercise program and also compared to the MAG and CG (<xref ref-type="table" rid="t2001">Table 2</xref>). The CG showed no significant changes in exercise capacity measures (<xref ref-type="table" rid="t2001">Table 2</xref>).</p>
        <p>The TRG completed 100% of the planned sessions, the MAG completed 80%, and the CG completed 30%. Both the TRG and MAG had significantly higher attendance rates compared to the CG.</p>
        <p>Baseline SF-36 subscale scores were similar across all groups (<xref ref-type="table" rid="t3001">Table 3</xref>). After the exercise program, both the TRG and MAG showed significant improvements in the SF-36 subscales for PF, BP, GH, vitality, SF, RE, and MH compared to their baseline scores (<xref ref-type="table" rid="t3001">Table 3</xref>). The CG showed no significant changes in any SF-36 subscale after the intervention (<xref ref-type="table" rid="t3001">Table 3</xref>).</p>
        <p>
          <table-wrap id="t3001">
            <label>Table 3</label>
            <caption>
              <title>&#8211; Comparison of SF-36 QoL subscales between groups before and after exercise training</title>
            </caption>
            <table frame="hsides" rules="groups">
              <colgroup>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
                <col/>
              </colgroup>
              <thead>
                <tr>
                  <th align="left" rowspan="2">SF-36 subscales</th>
                  <th colspan="3">TRG (n=18)</th>
                  <th colspan="3">MAG (n=13)</th>
                  <th colspan="3">CG (n=21)</th>
                </tr>
                <tr>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                  <th>Pre-exercise training</th>
                  <th>Post-exercise training</th>
                  <th>&#916;</th>
                </tr>
              </thead>
              <tbody>
                <tr>
                  <td>Physical functioning</td>
                  <td align="center">85 (75-88.8)</td>
                  <td align="center">
                    <bold>90 (86.3-95)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>5 (0, 15)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">80 (65-90)</td>
                  <td align="center">
                    <bold>95 (85-95)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>5 (0, 10)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">90 (75-90)</td>
                  <td align="center">80 (75-90)</td>
                  <td align="center">0 (-5, 5)</td>
                </tr>
                <tr>
                  <td>Role-physical</td>
                  <td align="center">100 (75-100)</td>
                  <td align="center">100 (100-100)</td>
                  <td align="center">0 (0, 0)</td>
                  <td align="center">100 (50-100)</td>
                  <td align="center">100 (50-100)</td>
                  <td align="center">0 (0, 0)</td>
                  <td align="center">100 (75-100)</td>
                  <td align="center">100 (75-100)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Role-emotional</td>
                  <td align="center">67 (33-100)</td>
                  <td align="center">
                    <bold>100 (72.3-100)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>0 (0, 67)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">67 (33-67)</td>
                  <td align="center">
                    <bold>100 (67-100)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>33 (0, 34)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">67 (33-100)</td>
                  <td align="center">67 (33-100)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Vitality</td>
                  <td align="center">67.5 (61.3-75)</td>
                  <td align="center">
                    <bold>75 (70-78.8)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>5 (0, 13.8)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">65 (50-75)</td>
                  <td align="center">
                    <bold>75 (75-90)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (10, 35)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">65 (50-75)</td>
                  <td align="center">55 (35-75)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Mental health</td>
                  <td align="center">76 (62-79)</td>
                  <td align="center">
                    <bold>87 (76-96)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (0, 20)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">68 (44-80)</td>
                  <td align="center">
                    <bold>80 (76-92)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>8 (0, 32)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">64 (44-76)</td>
                  <td align="center">60 (40-68)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Social functioning</td>
                  <td align="center">75 (66-88)</td>
                  <td align="center">
                    <bold>88 (75-100)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>0 (0, 12.8)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">75 (63-100)</td>
                  <td align="center">
                    <bold>88 (75-100)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>0 (0, 12)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">88 (75-100)</td>
                  <td align="center">75 (75-88)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>Bodily pain</td>
                  <td align="center">75 (49.8-90)</td>
                  <td align="center">
                    <bold>85 (68-97.5)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (0, 12.3)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">70 (55-80)</td>
                  <td align="center">
                    <bold>80 (68-90)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (3, 13)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">80 (68-100)</td>
                  <td align="center">80 (68-100)</td>
                  <td align="center">0 (0, 0)</td>
                </tr>
                <tr>
                  <td>General health</td>
                  <td align="center">60 (46.3-70)</td>
                  <td align="center">
                    <bold>75 (56.3-78.8)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (0, 18)</bold>
                    <sup>
                      <bold>b</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">60 (45-75)</td>
                  <td align="center">
                    <bold>75 (75-85)</bold>
                    <sup>
                      <bold>a</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">
                    <bold>10 (5, 15)</bold>
                    <sup>
                      <bold>c</bold>
                    </sup>
                    <bold>*</bold>
                  </td>
                  <td align="center">60 (45-70)</td>
                  <td align="center">50 (45-75)</td>
                  <td align="center">0 (0, 5)</td>
                </tr>
              </tbody>
            </table>
            <table-wrap-foot>
              <fn id="TFN3001">
                <p>*p&lt;0.05, Kruskal-Wallis test. Data are presented as median (IQR [Q1-Q3]). CG: control group; IQR: interquartile range; MAG: mobile application group; SF-36: Short Form-36; TRG: telerehabilitation group. a: Significant difference pre- vs post-exercise within the same group. b: Significant difference between TRG and CG. c: Significant difference between MAG and CG. d: Significant difference between TRG and MAG.</p>
              </fn>
            </table-wrap-foot>
          </table-wrap>
        </p>
        <p>When comparing the changes between groups, both the TRG and MAG had significantly greater improvements than the CG in PF, BP, GH, Vitality, SF, RE, and MH (<xref ref-type="table" rid="t3001">Table 3</xref>). There were no statistically significant differences between the TRG and MAG in any of the SF-36 subscales (<xref ref-type="table" rid="t3001">Table 3</xref>, <xref ref-type="fig" rid="f01001">Central Illustration</xref>).</p>
        <sec>
          <title>Natural language processing plus artificial intelligence</title>
          <p>A total of 52 patients with CAD shared subjective feedback about the benefits of exercise program. Sentiment scores were distributed in the following way: 55% scored 5, 2% scored 4, 12% scored 3, 12% scored 2, and 19% scored 1.</p>
          <p>According to the ISWT, a minimum improvement of 70.0 meters (95% CI: 51.5-88.5 m) was considered a positive outcome.<sup><xref ref-type="bibr" rid="B32">32</xref></sup> In this study, 59.62% of participants exceeded this threshold, with 51.5 meters used as the reference value. Among those who surpassed the threshold, 75% reported high satisfaction (a score of 5), while only 25% of those below the threshold reported high satisfaction.</p>
          <p>There was a strong positive correlation between patient-reported satisfaction and improvement in ISWT performance (r=0.75, p&lt;0.001). A moderate positive correlation was also found between the number of exercise sessions completed and satisfaction scores (r=0.410).</p>
          <p>To further explore patient satisfaction and improvement using NLP analysis, sentiment trends were examined across subgroups based on exercise adherence and ISWT performance. A closer look at outlier cases showed that some patients who reported high satisfaction despite limited ISWT gains often highlighted psychological benefits (eg, as increased motivation, reduced anxiety, and a greater sense of well-being) rather than physical improvements.</p>
          <p>The model found a significant relationship between patient-reported satisfaction and objectively measured exercise outcomes with a 95% CI. Anomaly detection techniques, including clustering- and distance-based methods, were used to identify mismatches between subjective satisfaction and actual performance. The model flagged anomalies in 10% of patients who reported high satisfaction despite showing minimal improvement in ISWT results.</p>
          <p><xref ref-type="fig" rid="f04001">Figure 3</xref> shows the emotion map created through anomaly detection and the distribution of patient satisfaction scores in relation to the reference value.</p>
          <p>
            <fig id="f04001">
              <label>Figure 3</label>
              <caption>
                <title>&#8211; Scatter plot showing the relationship between NLP analysis results and changes in ISWT distance. &#916;ISWT: change in Incremental Shuttle Walk Test distance. Review scores: 1 = Did not benefit at all, 2 = Did not benefit, 3: Neither benefited nor did not benefit, 4: Benefited, 5: Benefited greatly. Values inside circles represent anomalies. The model identified patients who reported high satisfaction despite limited ISWT improvement as anomalies, which accounted for 10% of the sample.</title>
              </caption>
              <graphic xlink:href="1678-4170-abc-122-06-e20240765-40765-gf04-en.tif"/></fig>
          </p>
        </sec>
      </sec>
      <sec sec-type="discussion">
        <title>Discussion</title>
        <p>A previous review of literature shows that integrating AI into CTR has the potential to support early detection of cardiac events, improve monitoring of home-based programs, and enhance clinical decision-making.<sup><xref ref-type="bibr" rid="B33">33</xref></sup> For example, wearable devices used in CTR can accurately assess a patient&#8217;s functional capacity through AI-driven algorithms.<sup><xref ref-type="bibr" rid="B34">34</xref></sup></p>
        <p>In this study, NLP was applied to demonstrate the effectiveness of technology-based CR. The strong correlation between exercise capacity and the results of NLP-based AI analysis suggests that patients&#8217; benefits from the program are reflected in both subjective feedback and objective outcomes. However, the NLP analysis also identified some anomalies &#8212; cases where patient-reported experiences did not align with their measured physical improvements. Such mismatches may be explained by individual perception, psychological factors, or current limitations of NLP models in fully understanding the complexity of patient narratives.</p>
        <p>Recognizing and interpreting these anomalies is key to improving AI-based assessment tools and supporting more personalized care. Future research should not only explore the broader effectiveness of NLP in CTR but also take a closer look at the clinical significance of these detected anomalies to enhance the accuracy and real-world use of AI-driven outcome evaluation.</p>
        <p>Exercise training through CTR has been shown to improve exercise capacity in patients with CAD.<sup><xref ref-type="bibr" rid="B35">35</xref></sup> Similarly, in our study, both the TRG and MAG showed significant increases in ISWT distance after 12 weeks of training. This supports current guidelines that recommend CTR as an effective way to improve exercise capacity in patients with CAD.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Consistent with our findings, Brouwers et al. also reported increased exercise capacity and physical activity levels in patients with CAD following CTR.<sup><xref ref-type="bibr" rid="B36">36</xref></sup></p>
        <p>These improvements are likely due to physiological changes in both the cardiovascular and musculoskeletal systems.<sup><xref ref-type="bibr" rid="B37">37</xref></sup> Specifically, reductions in end-exercise HR and %HRmax observed in the TRG suggest positive cardiovascular adaptations. Such results align with previous studies showing that exercise training improves cardiac efficiency, thereby allowing patients to perform the same workload at a lower HR.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> A decrease in HR after exercise reflects better cardiovascular adaptation.</p>
        <p>We believe the high adherence in the TRG may be due to the increased motivation provided by real-time feedback during supervised sessions.</p>
        <p>Beyond physical function, improving QoL is also an important goal for patients with CAD.<sup><xref ref-type="bibr" rid="B38">38</xref></sup> Improvements in physical well-being, energy, fatigue, and daily functioning can contribute to better disease management and long-term outcomes.<sup><xref ref-type="bibr" rid="B23">23</xref></sup> In our study, both the TRG and MAG showed significant improvements in QoL, which aligns with findings by Golbus et al., who reported that digital and hybrid CTR programs improve QoL in cardiac patients.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
        <p>However, not all studies have found similar results. One study reported no change in SF-36 scores despite improved functional capacity in a hybrid program for CTR.<sup><xref ref-type="bibr" rid="B39">39</xref></sup> This discrepancy may be due to differences in how QoL is measured in cardiovascular research and the limited number of studies focusing on QoL outcomes in CTR. We also believe that the longer duration of our exercise program may have contributed to the more noticeable improvements.</p>
        <p>Our study also found significant improvements in emotional role functioning in both intervention groups, suggesting a positive impact on psychological well-being. This supports findings from a meta-analysis by Gong et al., which showed that programs for CTR lasting at least 3 months can reduce symptoms of depression and anxiety.<sup><xref ref-type="bibr" rid="B40">40</xref></sup></p>
        <p>Overall, the improvements in ISWT distance (&#916;ISWT) in our study were reflected in better scores across several QoL subscales.</p>
        <p>Integrating technology into programs for CR plays a key role in improving patient adherence and participation. In our study, both the TRG and the MAG had higher attendance rates compared to the CG, suggesting that technology-based approaches are more accessible and user-friendly. The flexibility offered by the MAG may have further supported participation, allowing patients to exercise at times that best fit their daily routines. Previous research supports the idea that mobile technology can improve adherence to programs for CR.<sup><xref ref-type="bibr" rid="B3">3</xref>,<xref ref-type="bibr" rid="B41">41</xref></sup> In our case, the mobile app likely helped by enabling exercise tracking, providing feedback, and keeping patients motivated. Such results are consistent with findings from Maddison et al., who reported higher participation rates in home-based CR compared to traditional center-based programs.<sup><xref ref-type="bibr" rid="B20">20</xref></sup> The convenience of exercising at home, with minimal equipment and no transportation costs, likely played a role in encouraging participation &#8212; particularly in the current economic climate. Since the patients in our study had an average exercise capacity of more than 10 METs, these findings are most applicable to low-risk patients with CAD.</p>
        <p>This study has several limitations. While AI-based methods show promise, there are important challenges that must be acknowledged. One major limitation is the reliance on the quality and quantity of data used to train AI models. Poor or limited data can introduce bias and limit how well the findings apply to different patient populations. Additionally, NLP algorithms depend on language, which can vary based on cultural and individual differences in how patients describe their symptoms and experiences. Another challenge is the interpretability of AI-generated results. For these tools to be useful in clinical practice, health care providers need clear, understandable insights they can trust and apply in decision-making. Programs for CTR in this study focused only on exercise training and did not include other essential components of comprehensive CR, such as psychosocial support, nutrition counseling, medication management, and smoking cessation. Also, the mobile app used for exercise guidance did not allow for real-time monitoring of HR or BP during sessions. Most participants in this study were low-risk patients with CAD, which limits the generalizability of the findings to higher-risk groups. Despite these limitations, the study has notable strengths. The NLP-AI analysis was at least as effective as traditional assessments in demonstrating the benefits of CTR, showing the innovative potential of digital health tools in cardiac care. It also showed that self-guided exercise programs can be just as effective as traditional methods in improving exercise capacity, adherence, and QoL in patients with CAD.</p>
      </sec>
      <sec sec-type="conclusions">
        <title>Conclusion</title>
        <p>This study highlights the effectiveness of AI-based analysis in evaluating the impact of exercise on low-risk patients with CAD. Both the TRG and MAG proved to be effective and feasible, potentially offering greater benefits than traditional methods in improving exercise capacity, participation, and QoL. As AI continues to evolve, the role of physical therapists remains essential, particularly in delivering patient-centered care. With the support of multicenter study designs, NLP-based approaches may become a valuable tool in CR. Further research is needed to assess the clinical feasibility and safety of AI-driven CR, explore other AI-powered methods such as virtual reality-based exercise, and evaluate the cost-effectiveness and practical integration of programs for CTR into the broader health care system.</p>
      </sec>
    </body>
    <back>
      <ack>
        <title>Acknowledgements</title>
        <p>The authors are deeply grateful to the individuals who participated in the study, as well as to Ahmet Talha Sen and Cagri Golen for their valuable support throughout the research.</p>
      </ack>
      <fn-group>
        <fn fn-type="other">
          <label>Study association:</label>
          <p> This article is part of the thesis of Doctoral submitted by Dilara Saklica, from Hacettepe University Faculty of Physical Therapy and Rehabilitation.</p>
        </fn>
        <fn fn-type="other">
          <label>Ethics approval and consent to participate:</label>
          <p> This study was approved by the Ethics Committee of the Hacettepe University Clinical under the protocol number KA-20105. All the procedures in this study were in accordance with the 1975 Helsinki Declaration, updated in 2013. Informed consent was obtained from all participants included in the study. The trial was also registered on ClinicalTrials.gov (registry code: NCT05264701).</p>
        </fn>
        <fn fn-type="other">
          <label>Use of Artificial Intelligence:</label>
          <p> The authors did not use any artificial intelligence tools in the development of this work.</p>
        </fn>
        <fn fn-type="data-availability" specific-use="data-not-available">
          <label>Data Availability:</label>
          <p> The data cannot be made publicly available due to prevent any risk of re-identifying personal information and in accordance with the conditions of ethical approval, patient-level data are not available for use outside this study.</p>
        </fn>
        <fn fn-type="supplementary-material" id="suppl01001">
          <label>*Supplemental Materials</label>
          <p> For additional information, please <ext-link ext-link-type="uri" xlink:href="http://abccardiol.org/supplementary-material/2025/12206/2024-0765_AO_SupplementaryFile.pdf">click here</ext-link>. </p>
        </fn>
        <fn fn-type="financial-disclosure">
          <label>Sources of funding:</label>
          <p> There were no external funding sources for this study.</p>
        </fn>
      </fn-group>
    </back>
  </sub-article>
</article>
