<!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="letter" 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">CX4sLDpKGxfJx8cwNSwBZXn</article-id>
      <article-id specific-use="scielo-v2" pub-id-type="publisher-id">S0066-782X2026000504204</article-id>
      <article-id pub-id-type="other">04204</article-id>
      <article-id pub-id-type="doi">10.36660/abc.20260179</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Carta ao Editor</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Reabilita&#231;&#227;o Card&#237;aca Baseada em Tecnologia e Capacidade de Exerc&#237;cio na Doen&#231;a Arterial Coronariana: Uma An&#225;lise de Intelig&#234;ncia Artificial</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-0900-0069</contrib-id>
          <name>
            <surname>Ata</surname>
            <given-names>Benil Nesli</given-names>
          </name>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
          <xref ref-type="corresp" rid="c1"/>
        </contrib>
        <aff id="aff1">
          <label>1</label>
          <institution content-type="orgname">Ministry of Health</institution>
          <institution content-type="orgdiv1">Izmir City Hospital</institution>
          <institution content-type="orgdiv2">Department of Physical Medicine and Rehabilitation</institution>
          <addr-line>
            <named-content content-type="city">Izmir</named-content>
          </addr-line>
          <country country="TR">Turquia</country>
          <institution content-type="original">Ministry of Health, Izmir City Hospital, Department of Physical Medicine and Rehabilitation, Izmir &#8211; Turquia</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c1"><label>Correspond&#234;ncia:</label><bold>Benil Nesli Ata</bold> &#8226; Ministry of Health, Izmir City Hospital, Department of Physical Medicine and Rehabilitation &#8211; &#304;zmir, <postal-code>35540</postal-code> &#8211; Turquia E-mail: <email>drbenilnesli@gmail.com</email> </corresp>
      </author-notes>
      <pub-date date-type="pub" publication-format="electronic">
        <day>20</day>
        <month>07</month>
        <year>2026</year>
      </pub-date>
      <pub-date date-type="collection" publication-format="electronic">
        <month>06</month>
        <year>2026</year>
      </pub-date>
      <volume>123</volume>
      <issue>5</issue>
      <elocation-id>e20260179</elocation-id>
      <history>
        <date date-type="received">
          <day>04</day>
          <month>03</month>
          <year>2026</year>
        </date>
        <date date-type="rev-recd">
          <day>13</day>
          <month>03</month>
          <year>2026</year>
        </date>
        <date date-type="accepted">
          <day>13</day>
          <month>03</month>
          <year>2026</year>
        </date>
      </history>
      <permissions>
        <license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by/4.0/" xml:lang="en">
          <license-p>This is an open-access article distributed under the terms of the Creative Commons Attribution License</license-p>
        </license>
      </permissions>
      <related-article related-article-type="article" id="r1" xlink:href="10.36660/abc.20240765" ext-link-type="doi"/>
      <kwd-group xml:lang="pt">
        <title>Palavras-chave</title>
        <kwd>Reabilita&#231;&#227;o Card&#237;aca</kwd>
        <kwd>Doen&#231;a da Art&#233;ria Coronariana</kwd>
        <kwd>Intelig&#234;ncia Artificial</kwd>
        <kwd>Exerc&#237;cio F&#237;sico</kwd>
        <kwd>Sa&#250;de Digital</kwd>
      </kwd-group>
      <counts>
        <fig-count count="0"/>
        <table-count count="0"/>
        <equation-count count="0"/>
        <ref-count count="4"/>
      </counts>
    </article-meta>
  </front>
  <body>
    <p>Li com grande interesse o artigo de Saklica et al. intitulado "O 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", publicado recentemente nos Arquivos Brasileiros de Cardiologia. O estudo aborda um tema importante e oportuno ao examinar o papel potencial de programas de reabilita&#231;&#227;o card&#237;aca com suporte tecnol&#243;gico e explorar a integra&#231;&#227;o de an&#225;lises baseadas em intelig&#234;ncia artificial (IA) na avalia&#231;&#227;o dos resultados da reabilita&#231;&#227;o.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Considerando a persistente subutiliza&#231;&#227;o global de programas de reabilita&#231;&#227;o card&#237;aca, estudos que exploram estrat&#233;gias de reabilita&#231;&#227;o inovadoras e acess&#237;veis s&#227;o de clara import&#226;ncia cl&#237;nica.</p>
    <p>Um aspecto metodol&#243;gico que merece maior aten&#231;&#227;o &#233; a avalia&#231;&#227;o da capacidade de exerc&#237;cio. No presente estudo, a melhora funcional foi avaliada utilizando o teste de caminhada incremental (TCI). Embora o TCI seja um teste de campo pr&#225;tico e validado, frequentemente utilizado em contextos de reabilita&#231;&#227;o, ele permanece uma medida subm&#225;xima e dependente do esfor&#231;o. Em pacientes com doen&#231;a arterial coronariana, o teste cardiopulmonar de exerc&#237;cio (TCPE) &#233; geralmente considerado o padr&#227;o de refer&#234;ncia para avaliar a capacidade de exerc&#237;cio, pois fornece par&#226;metros fisiol&#243;gicos objetivos, como o pico de consumo de oxig&#234;nio e os limiares ventilat&#243;rios. A inclus&#227;o de vari&#225;veis derivadas do TCPE poderia, portanto, ter oferecido uma avalia&#231;&#227;o mais abrangente das adapta&#231;&#245;es cardiopulmonares e fortalecido a interpreta&#231;&#227;o das melhorias observadas na capacidade funcional.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
    <p>Outra quest&#227;o metodol&#243;gica diz respeito &#224; avalia&#231;&#227;o da ades&#227;o ao exerc&#237;cio entre os grupos de estudo. Nos grupos de interven&#231;&#227;o, a ades&#227;o foi monitorada por meio de sess&#245;es supervisionadas por terapeutas ou registros em aplicativos, enquanto no grupo controle, baseou-se em di&#225;rios de exerc&#237;cios preenchidos pelos pr&#243;prios participantes. Sabe-se que as medidas de atividade f&#237;sica autorrelatadas s&#227;o suscet&#237;veis a vi&#233;s de mem&#243;ria e superestima&#231;&#227;o sistem&#225;tica, o que pode influenciar a precis&#227;o das estimativas de ades&#227;o.<sup><xref ref-type="bibr" rid="B3">3</xref></sup> Portanto, as diferen&#231;as observadas na ades&#227;o entre os grupos podem refletir, em parte, varia&#231;&#245;es nos m&#233;todos de mensura&#231;&#227;o, e n&#227;o diferen&#231;as comportamentais reais. O uso de monitoramento de ades&#227;o padronizado e objetivo em todos os grupos fortaleceria a validade das compara&#231;&#245;es em futuros ensaios de reabilita&#231;&#227;o card&#237;aca.</p>
    <p>Outro aspecto que merece maior discuss&#227;o &#233; a interpretabilidade cl&#237;nica das an&#225;lises baseadas em IA empregadas no estudo. O uso de processamento de linguagem natural e an&#225;lise de sentimentos para avaliar o feedback dos pacientes representa uma adi&#231;&#227;o metodol&#243;gica inovadora &#224; pesquisa em reabilita&#231;&#227;o card&#237;aca. No entanto, a tradu&#231;&#227;o desses resultados derivados de IA em informa&#231;&#245;es clinicamente acion&#225;veis permanece menos clara. Na pesquisa em sa&#250;de digital, se enfatiza cada vez mais que as ferramentas de IA n&#227;o devem apenas identificar padr&#245;es em grandes conjuntos de dados, mas tamb&#233;m fornecer resultados que possam informar de forma significativa a tomada de decis&#245;es cl&#237;nicas e o manejo do paciente. Esclarecer como os insights gerados por IA se relacionam com comportamentos de ades&#227;o, resultados funcionais ou estrat&#233;gias de reabilita&#231;&#227;o individualizadas fortaleceria ainda mais a relev&#226;ncia cl&#237;nica dessa abordagem tecnol&#243;gica promissora.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
    <p>Apesar dessas considera&#231;&#245;es, o estudo de Saklica et al.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> fornece informa&#231;&#245;es valiosas sobre o papel crescente das tecnologias digitais na reabilita&#231;&#227;o card&#237;aca e destaca o potencial de programas com suporte tecnol&#243;gico para aumentar o engajamento e a acessibilidade dos pacientes. Abordar aspectos metodol&#243;gicos, como avalia&#231;&#227;o fisiol&#243;gica abrangente, monitoramento padronizado da ades&#227;o e integra&#231;&#227;o cl&#237;nica mais clara de an&#225;lises baseadas em IA, pode fortalecer ainda mais futuras investiga&#231;&#245;es nessa &#225;rea. A continuidade das pesquisas que integram tecnologias de sa&#250;de digital com estrat&#233;gias de reabilita&#231;&#227;o baseadas em evid&#234;ncias pode contribuir para ampliar o alcance e a efic&#225;cia dos programas de reabilita&#231;&#227;o card&#237;aca em todo o mundo.</p>
  </body>
  <back>
    <ref-list>
      <title>Refer&#234;ncias</title>
      <ref id="B1">
        <label>1</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Saklica</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Vardar-Yagli</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Saglam</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Yuce</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Ates</surname>
              <given-names>AH</given-names>
            </name>
            <name>
              <surname>Yorgun</surname>
              <given-names>H</given-names>
            </name>
          </person-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>
          <source>Arq Bras Cardiol</source>
          <year>2025</year>
          <volume>122</volume>
          <issue>6</issue>
          <elocation-id>e20240765</elocation-id>
          <pub-id pub-id-type="doi">10.36660/abc.20240765</pub-id>
        </element-citation>
        <mixed-citation>1 Saklica D, Vardar-Yagli N, Saglam M, Yuce D, Ates AH, Yorgun H. The Impact of Technology-Based Cardiac Rehabilitation on Exercise Capacity and Adherence in Patients with Coronary Artery Disease: An Artificial Intelligence Analysis. Arq Bras Cardiol. 2025;122(6):e20240765. doi: 10.36660/abc.20240765.</mixed-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Guazzi</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Arena</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Halle</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Piepoli</surname>
              <given-names>MF</given-names>
            </name>
            <name>
              <surname>Myers</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Lavie</surname>
              <given-names>CJ</given-names>
            </name>
          </person-group>
          <article-title>2016 Focused Update: Clinical Recommendations for Cardiopulmonary Exercise Testing Data Assessment in Specific Patient Populations</article-title>
          <source>Eur Heart J</source>
          <year>2018</year>
          <volume>39</volume>
          <issue>14</issue>
          <fpage>1144</fpage>
          <lpage>1161</lpage>
          <pub-id pub-id-type="doi">10.1093/eurheartj/ehw180</pub-id>
        </element-citation>
        <mixed-citation>2 Guazzi M, Arena R, Halle M, Piepoli MF, Myers J, Lavie CJ. 2016 Focused Update: Clinical Recommendations for Cardiopulmonary Exercise Testing Data Assessment in Specific Patient Populations. Eur Heart J. 2018;39(14):1144-61. doi: 10.1093/eurheartj/ehw180.</mixed-citation>
      </ref>
      <ref id="B3">
        <label>3</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Prince</surname>
              <given-names>SA</given-names>
            </name>
            <name>
              <surname>Cardilli</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Reed</surname>
              <given-names>JL</given-names>
            </name>
            <name>
              <surname>Saunders</surname>
              <given-names>TJ</given-names>
            </name>
            <name>
              <surname>Kite</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Douillette</surname>
              <given-names>K</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>A Comparison of Self-Reported and Device Measured Sedentary Behaviour in Adults: A Systematic Review and Meta-Analysis</article-title>
          <source>Int J Behav Nutr Phys Act</source>
          <year>2020</year>
          <volume>17</volume>
          <issue>1</issue>
          <fpage>31</fpage>
          <lpage>31</lpage>
          <pub-id pub-id-type="doi">10.1186/s12966-020-00938-3</pub-id>
        </element-citation>
        <mixed-citation>3 Prince SA, Cardilli L, Reed JL, Saunders TJ, Kite C, Douillette K, et al. A Comparison of Self-Reported and Device Measured Sedentary Behaviour in Adults: A Systematic Review and Meta-Analysis. Int J Behav Nutr Phys Act. 2020;17(1):31. doi: 10.1186/s12966-020-00938-3.</mixed-citation>
      </ref>
      <ref id="B4">
        <label>4</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Topol</surname>
              <given-names>EJ</given-names>
            </name>
          </person-group>
          <article-title>High-Performance Medicine: The Convergence of Human and Artificial Intelligence</article-title>
          <source>Nat Med</source>
          <year>2019</year>
          <volume>25</volume>
          <issue>1</issue>
          <fpage>44</fpage>
          <lpage>56</lpage>
          <pub-id pub-id-type="doi">10.1038/s41591-018-0300-7</pub-id>
        </element-citation>
        <mixed-citation>4 Topol EJ. High-Performance Medicine: The Convergence of Human and Artificial Intelligence. Nat Med. 2019;25(1):44-56. doi: 10.1038/s41591-018-0300-7.</mixed-citation>
      </ref>
    </ref-list>
  </back>
  <sub-article article-type="translation" id="S1" xml:lang="en">
    <front-stub>
      <article-id pub-id-type="doi">10.36660/abc.20260179i</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Letter to the Editor</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Technology-Based Cardiac Rehabilitation and Exercise Capacity in Coronary Artery Disease: An Artificial Intelligence Analysis</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-0900-0069</contrib-id>
          <name>
            <surname>Ata</surname>
            <given-names>Benil Nesli</given-names>
          </name>
          <xref ref-type="aff" rid="aff2">
            <sup>1</sup>
          </xref>
          <xref ref-type="corresp" rid="c2"/>
        </contrib>
        <aff id="aff2">
          <label>1</label>
          <addr-line>
            <named-content content-type="city">Izmir</named-content>
          </addr-line>
          <country country="TR">T&#252;rkiye</country>
          <institution content-type="original">Ministry of Health, Izmir City Hospital, Department of Physical Medicine and Rehabilitation, Izmir &#8211; T&#252;rkiye</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c2"><label>Mailing Address:</label><bold>Benil Nesli Ata</bold> &#8226; Ministry of Health, Izmir City Hospital, Department of Physical Medicine and Rehabilitation &#8211; Izmir, <postal-code>35540</postal-code> &#8211; T&#252;rkiye E-mail: <email>drbenilnesli@gmail.com</email> </corresp>
      </author-notes>
      <related-article related-article-type="article" id="r1en" xlink:href="10.36660/abc.20240765i" ext-link-type="doi"/>
      <kwd-group xml:lang="en">
        <title>Keywords</title>
        <kwd>Cardiac Rehabilitation</kwd>
        <kwd>Coronary Artery Disease</kwd>
        <kwd>Artificial Intelligence</kwd>
        <kwd>Exercise</kwd>
        <kwd>Digital Health</kwd>
      </kwd-group>
    </front-stub>
    <body>
      <p>I read with great interest the article by Saklica et al. entitled "The Impact of Technology-Based Cardiac Rehabilitation on Exercise Capacity and Adherence in Patients with Coronary Artery Disease: An Artificial Intelligence Analysis," recently published in <italic>Arquivos Brasileiros de Cardiologia</italic>. The study addresses an important and timely topic by examining the potential role of technology-supported cardiac rehabilitation programs and exploring the integration of artificial intelligence (AI)&#8211;based analyses in the evaluation of rehabilitation outcomes.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Considering the persistent global underutilization of cardiac rehabilitation programs, studies exploring innovative and accessible rehabilitation strategies are of clear clinical importance.</p>
      <p>One methodological aspect that warrants further consideration is the assessment of exercise capacity. In the present study, functional improvement was evaluated using the incremental shuttle walk test (ISWT). Although the ISWT is a practical and validated field test frequently used in rehabilitation settings, it remains a submaximal and effort-dependent measure. In patients with coronary artery disease, cardiopulmonary exercise testing (CPET) is generally regarded as the reference standard for evaluating exercise capacity because it provides objective physiological parameters such as peak oxygen uptake and ventilatory thresholds. The inclusion of CPET-derived variables could therefore have offered a more comprehensive evaluation of cardiopulmonary adaptations and strengthened the interpretation of the observed improvements in functional capacity.<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
      <p>Another methodological issue concerns the assessment of exercise adherence across study groups. In the intervention groups, adherence was monitored through therapist-supervised sessions or application-based records, whereas in the control group, it relied on self-reported exercise diaries. Self-reported physical activity measures are known to be susceptible to recall bias and systematic overestimation, which may influence the accuracy of adherence estimates.<sup><xref ref-type="bibr" rid="B3">3</xref></sup> Therefore, the observed differences in adherence between groups may partly reflect variations in measurement methods rather than true behavioral differences. The use of standardized and objective adherence monitoring across all groups would strengthen the validity of comparisons in future cardiac rehabilitation trials.</p>
      <p>Another aspect that merits further discussion is the clinical interpretability of the AI&#8211;based analyses employed in the study. The use of natural language processing and sentiment analysis to evaluate patient feedback represents an innovative methodological addition to cardiac rehabilitation research. However, the translation of these AI-derived outputs into clinically actionable information remains less clearly defined. In digital health research, it is increasingly emphasized that AI tools should not only identify patterns in large datasets but also provide outputs that can meaningfully inform clinical decision-making and patient management. Clarifying how AI-generated insights relate to adherence behaviors, functional outcomes, or individualized rehabilitation strategies would further strengthen the clinical relevance of this promising technological approach.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
      <p>Despite these considerations, the study by Saklica et al.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> provides valuable insights into the expanding role of digital technologies in cardiac rehabilitation and highlights the potential of technology-supported programs to enhance patient engagement and accessibility. Addressing methodological aspects such as comprehensive physiological assessment, standardized adherence monitoring, and clearer clinical integration of AI&#8211;based analyses may further strengthen future investigations in this field. Continued research integrating digital health technologies with evidence-based rehabilitation strategies may contribute to expanding the reach and effectiveness of cardiac rehabilitation programs worldwide.</p>
    </body>
  </sub-article>
</article>
