<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "http://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="editorial" 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">wRSxq7Fw8knZtNj6MC38XKx</article-id>
      <article-id specific-use="scielo-v2" pub-id-type="publisher-id">S0066-782X2025000800204</article-id>
      <article-id pub-id-type="other">00204</article-id>
      <article-id pub-id-type="doi">10.36660/abc.20250405</article-id>
      <article-id pub-id-type="publisher-id">abc.20250405</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Minieditorial</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Aplicabilidade de Algoritmos de Aprendizado de M&#225;quina no Diagn&#243;stico de Arritmias &#8211; Quanto Tempo At&#233; a M&#225;quina Come&#231;ar a nos Ensinar?</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-6646-1163</contrib-id>
          <name>
            <surname>Pinto</surname>
            <given-names>Marcelo Martins</given-names>
            <suffix>Filho</suffix>
          </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">Hospital das Cl&#237;nicas da Universidade Federal de Minas Gerais</institution>
          <institution content-type="orgdiv1">Centro de Telessa&#250;de</institution>
          <addr-line>
            <named-content content-type="city">Belo Horizonte</named-content>
            <named-content content-type="state">MG</named-content>
          </addr-line>
          <country country="BR">Brasil</country>
          <institution content-type="original">Hospital das Cl&#237;nicas da Universidade Federal de Minas Gerais &#8211; Centro de Telessa&#250;de, Belo Horizonte, MG &#8211; Brasil</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c1"><label>Correspond&#234;ncia:</label><bold>Marcelo Martins Pinto Filho</bold> &#8226; Faculdade de Medicina da Universidade Federal de Minas Gerais - Programa de P&#243;s-Gradua&#231;&#227;o em Infectologia e Medicina Tropical &#8211; Av. Alfredo Balena, 190. CEP <postal-code>30130-100</postal-code>, Belo Horizonte, MG &#8211; Brasil E-mail: <email>marcelo128ufmg@gmail.com</email> </corresp>
      </author-notes>
      <pub-date date-type="pub" publication-format="electronic">
        <day>19</day>
        <month>09</month>
        <year>2025</year>
      </pub-date>
      <pub-date date-type="collection" publication-format="electronic">
        <year>2025</year>
      </pub-date>
      <volume>122</volume>
      <issue>8</issue>
      <elocation-id>e20250405</elocation-id>
      <history>
        <date date-type="received">
          <day>05</day>
          <month>06</month>
          <year>2025</year>
        </date>
        <date date-type="rev-recd">
          <day>11</day>
          <month>06</month>
          <year>2025</year>
        </date>
        <date date-type="accepted">
          <day>11</day>
          <month>06</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>This is an open-access article distributed under the terms of the Creative Commons Attribution License</license-p>
        </license>
      </permissions>
      <kwd-group xml:lang="pt">
        <title>Palavras-chave</title>
        <kwd>Arritmia Card&#237;aca</kwd>
        <kwd>Intelig&#234;ncia Artificial</kwd>
        <kwd>Aprendizado de M&#225;quina</kwd>
        <kwd>Rede Neural</kwd>
        <kwd>Eletrocardiograma</kwd>
      </kwd-group>
      <counts>
        <fig-count count="0"/>
        <table-count count="0"/>
        <equation-count count="0"/>
        <ref-count count="15"/>
      </counts>
    </article-meta>
  </front>
  <body>
    <p>O eletrocardiograma (ECG), em uso cl&#237;nico desde o in&#237;cio do s&#233;culo XX, continua sendo uma ferramenta adorada por cardiologistas, cl&#237;nicos e estudantes de medicina. &#201; indiscutivelmente o instrumento de cabeceira mais importante em cardiologia, essencial para o manejo de arritmias e s&#237;ndromes isqu&#234;micas agudas, al&#233;m de orientar o tratamento eletrofisiol&#243;gico. Ainda assim, os avan&#231;os na interpreta&#231;&#227;o de eletrocardiografia foram modestos nos &#250;ltimos cem anos. Os dispositivos tornaram-se mais port&#225;teis, digitais e capazes de grava&#231;&#245;es mais longas, mas os princ&#237;pios interpretativos fundamentais permanecem enraizados nos m&#233;todos do in&#237;cio do s&#233;culo XX.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> Nos &#250;ltimos anos, isso foi remodelado pelo surgimento de tecnologias computacionais, especialmente a intelig&#234;ncia artificial (IA). Ferramentas como redes neurais profundas (DNNs) e modelos de aprendizado de m&#225;quina (MLMs) est&#227;o possibilitando uma nova era na an&#225;lise de ECG, a eletrocardiografia aprimorada por IA (ECG aprimorado por IA).<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
    <p>Nesta edi&#231;&#227;o do ABC Cardiol, Guimar&#227;es do Nascimento et al. relatam uma revis&#227;o sistem&#225;tica de estudos que avaliam a aplicabilidade do ECG com IA no diagn&#243;stico de arritmias card&#237;acas.<sup><xref ref-type="bibr" rid="B3">3</xref></sup> Eles inclu&#237;ram estudos de diferentes metodologias que abordaram o papel do ECG aprimorado por IA na detec&#231;&#227;o da s&#237;ndrome do QT longo (SQTL) (um estudo), intervalo QT corrigido (QTc) (um estudo) e fibrila&#231;&#227;o atrial (FA) (onze estudos).</p>
    <p>Para a detec&#231;&#227;o de SQTL oculta entre os tipos gen&#233;ticos 1, 2 e 3, um modelo DNN superou a avalia&#231;&#227;o tradicional (baseada apenas no QTc) com uma AUC de 0,900 (IC de 95%, 0,876-0,925) versus 0,824 (IC de 95%, 0,79-0,858), respectivamente. O modelo tamb&#233;m foi capaz de identificar corretamente o tipo gen&#233;tico com uma AUC de 0,863 (IC de 95%, 0,792-0,934) a 0,944 (IC de 95%, 0,918-0,970), dependendo do tipo gen&#233;tico.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
    <p>No &#250;nico estudo que avaliou o QTc <italic>per se</italic>, apenas a precis&#227;o da medi&#231;&#227;o foi avaliada, com concord&#226;ncia razo&#225;vel entre o QTc calculado por IA por um smartwatch e o ECG.<sup><xref ref-type="bibr" rid="B5">5</xref></sup> &#201; importante destacar que a aferi&#231;&#227;o autom&#225;tica do ECG &#233; uma meta alcan&#231;ada desde a d&#233;cada de 1970 com a implanta&#231;&#227;o do software Glasgow e sua consolida&#231;&#227;o na d&#233;cada de 1980.<sup><xref ref-type="bibr" rid="B6">6</xref></sup> A novidade deste estudo reside em mostrar a precis&#227;o da medi&#231;&#227;o em diferentes hardwares (o smartwatch) e a possibilidade de auto (ou cont&#237;nua) medi&#231;&#227;o do QTc.</p>
    <p>Entre os artigos que avaliaram modelos de IA na detec&#231;&#227;o de FA, os m&#233;todos foram diversos; no entanto, no geral, os algoritmos de IA e os modelos DNN/ML demonstraram boa sensibilidade e especificidade. &#201; importante destacar que esses estudos relataram a detec&#231;&#227;o de FA prevalente, com apenas um relatando a an&#225;lise de ECG em participantes com ritmo sinusal para prever FA, resultando em desempenho modesto (AUM 0,64).<sup><xref ref-type="bibr" rid="B7">7</xref></sup> Entre as arritmias card&#237;acas, a FA tem ganhado particular interesse devido &#224; sua relev&#226;ncia epidemiol&#243;gica, &#224; diversidade de op&#231;&#245;es de tratamento e &#224; crescente variedade de estrat&#233;gias de rastreamento. Embora os benef&#237;cios da detec&#231;&#227;o e do tratamento da FA subcl&#237;nica ainda sejam discut&#237;veis,<sup><xref ref-type="bibr" rid="B8">8</xref></sup> os benef&#237;cios do controle precoce do ritmo da FA cl&#237;nica foram demonstrados.<sup><xref ref-type="bibr" rid="B9">9</xref></sup></p>
    <p>Este estudo analisa como a IA est&#225; sendo aplicada &#224; eletrocardiografia, particularmente na &#225;rea de arritmias, apresentando desempenho compar&#225;vel aos m&#233;todos tradicionais, e se espera um r&#225;pido progresso no curto prazo. No entanto, v&#225;rias ressalvas devem ser consideradas. A revis&#227;o inclui estudos publicados apenas at&#233; 2022 e, dado o crescimento exponencial da pesquisa nessa &#225;rea, estudos importantes podem ter sido perdidos. Por exemplo, em julho de 2023, Yuan et al. relataram o uso de uma rede neural convolucional (CNN) para prever FA a partir de 907.858 ECGs em seis centros de Assuntos de Veteranos, alcan&#231;ando uma AUC de 0,86 e uma precis&#227;o de 0,78.<sup><xref ref-type="bibr" rid="B10">10</xref></sup> No mesmo ano, Hygreaal et al. usaram um modelo semelhante em 478.963 ECGs de deriva&#231;&#227;o &#250;nica de 14.831 adultos mais velhos, alcan&#231;ando uma AUC de 0,80.<sup><xref ref-type="bibr" rid="B11">11</xref></sup> Al&#233;m disso, Habineza et al. tamb&#233;m usaram CNN para prever FA em 1.230.809 ECGs (AUC 0,845).<sup><xref ref-type="bibr" rid="B12">12</xref></sup> A valida&#231;&#227;o externa dos resultados dos estudos prim&#225;rios tamb&#233;m &#233; um ponto preocupante, visto que a explicabilidade dos modelos de IA, em geral, n&#227;o &#233; satisfat&#243;ria. A extra&#231;&#227;o e a avalia&#231;&#227;o de dados de um &#250;nico operador tamb&#233;m levantam preocupa&#231;&#245;es sobre vi&#233;s de sele&#231;&#227;o.</p>
    <p>Al&#233;m da detec&#231;&#227;o de arritmia, o ECG aprimorado por IA &#233; promissor para outras &#225;reas, como a previs&#227;o de insufici&#234;ncia card&#237;aca e resultados ap&#243;s eventos card&#237;acos agudos, o refinamento da estratifica&#231;&#227;o de risco e a possibilidade de permitir relat&#243;rios automatizados sem a interven&#231;&#227;o do cardiologista.<sup><xref ref-type="bibr" rid="B13">13</xref>,<xref ref-type="bibr" rid="B14">14</xref></sup> No entanto, com essa transforma&#231;&#227;o, surge a necessidade de cautela. A valida&#231;&#227;o cient&#237;fica deve preceder o uso cl&#237;nico ou comercial generalizado, e quest&#245;es &#233;ticas &#8212; como a responsabiliza&#231;&#227;o em caso de erro de IA &#8212; devem ser abordadas pelas comunidades cient&#237;fica e regulat&#243;ria.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> Ainda assim, a ascens&#227;o da IA mant&#233;m a eletrocardiografia t&#227;o inovadora e intrigante quanto era h&#225; mais de um s&#233;culo.</p>
  </body>
  <back>
    <fn-group>
      <fn fn-type="other" id="fn1">
        <p>
          <italic>Minieditorial referente ao artigo: Aplicabilidade de Algoritmos de Machine Learning no Diagn&#243;stico de Fibrila&#231;&#227;o Atrial e SQTL por Interpreta&#231;&#227;o de Eletrocardiograma: Uma Revis&#227;o Sistem&#225;tica</italic>
        </p>
      </fn>
    </fn-group>
    <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>Stracina</surname>
              <given-names>T</given-names>
            </name>
            <name>
              <surname>Ronzhina</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Redina</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Novakova</surname>
              <given-names>M</given-names>
            </name>
          </person-group>
          <article-title>Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context</article-title>
          <source>Front Physiol</source>
          <year>2022;</year>
          <volume>13</volume>
          <fpage>867033</fpage>
          <lpage>867033</lpage>
          <pub-id pub-id-type="doi">10.3389/fphys.2022.867033</pub-id>
        </element-citation>
        <mixed-citation>1 Stracina T, Ronzhina M, Redina R, Novakova M. Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context. Front Physiol. 2022;13:867033. doi: 10.3389/fphys.2022.867033.</mixed-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Rafie</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Kashou</surname>
              <given-names>AH</given-names>
            </name>
            <name>
              <surname>Noseworthy</surname>
              <given-names>PA</given-names>
            </name>
          </person-group>
          <article-title>ECG Interpretation: Clinical Relevance, Challenges, and Advances</article-title>
          <source>Hearts</source>
          <year>2021</year>
          <volume>2</volume>
          <issue>4</issue>
          <fpage>505113</fpage>
          <lpage>505113</lpage>
          <pub-id pub-id-type="doi">10.3390/hearts2040039</pub-id>
        </element-citation>
        <mixed-citation>2 Rafie N, Kashou AH, Noseworthy PA. ECG Interpretation: Clinical Relevance, Challenges, and Advances. Hearts. 2021;2(4):505113. doi: 10.3390/hearts2040039.</mixed-citation>
      </ref>
      <ref id="B3">
        <label>3</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Nascimento</surname>
              <given-names>PCG</given-names>
            </name>
            <name>
              <surname>Martins</surname>
              <given-names>MS</given-names>
            </name>
            <name>
              <surname>Improta-Caria</surname>
              <given-names>AC</given-names>
            </name>
            <name>
              <surname>Aras</surname>
              <given-names>R</given-names>
              <suffix>Junior</suffix>
            </name>
          </person-group>
          <article-title>Applicability of Machine Learning Algorithms in Diagnosis of Atrial Fibrillation and LQTS by Electrocardiogram Interpretation: A Systematic Review</article-title>
          <source>Arq Bras Cardiol</source>
          <year>2025</year>
          <volume>122</volume>
          <issue>8</issue>
          <elocation-id>e20240843</elocation-id>
          <comment>
            <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.36660/abc.20240843i">https://doi.org/10.36660/abc.20240843i</ext-link>
          </comment>
        </element-citation>
        <mixed-citation>3 Nascimento PCG, Martins MS, Improta-Caria AC, Aras Junior R. Applicability of Machine Learning Algorithms in Diagnosis of Atrial Fibrillation and LQTS by Electrocardiogram Interpretation: A Systematic Review. Arq Bras Cardiol. 2025; 122(8):e20240843. DOI: <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.36660/abc.20240843i">https://doi.org/10.36660/abc.20240843i</ext-link>.</mixed-citation>
      </ref>
      <ref id="B4">
        <label>4</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Bos</surname>
              <given-names>JM</given-names>
            </name>
            <name>
              <surname>Attia</surname>
              <given-names>ZI</given-names>
            </name>
            <name>
              <surname>Albert</surname>
              <given-names>DE</given-names>
            </name>
            <name>
              <surname>Noseworthy</surname>
              <given-names>PA</given-names>
            </name>
            <name>
              <surname>Friedman</surname>
              <given-names>PA</given-names>
            </name>
            <name>
              <surname>Ackerman</surname>
              <given-names>MJ</given-names>
            </name>
          </person-group>
          <article-title>Use of Artificial Intelligence and Deep Neural Networks in Evaluation of Patients with Electrocardiographically Concealed Long QT Syndrome from the Surface 12-Lead Electrocardiogram</article-title>
          <source>JAMA Cardiol</source>
          <year>2021</year>
          <volume>6</volume>
          <issue>5</issue>
          <fpage>532</fpage>
          <lpage>538</lpage>
          <pub-id pub-id-type="doi">10.1001/jamacardio.2020.7422</pub-id>
        </element-citation>
        <mixed-citation>4 Bos JM, Attia ZI, Albert DE, Noseworthy PA, Friedman PA, Ackerman MJ. Use of Artificial Intelligence and Deep Neural Networks in Evaluation of Patients with Electrocardiographically Concealed Long QT Syndrome from the Surface 12-Lead Electrocardiogram. JAMA Cardiol. 2021;6(5):532-8. doi: 10.1001/jamacardio.2020.7422.</mixed-citation>
      </ref>
      <ref id="B5">
        <label>5</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Maille</surname>
              <given-names>B</given-names>
            </name>
            <name>
              <surname>Wilkin</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Million</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Ress&#233;guier</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Franceschi</surname>
              <given-names>F</given-names>
            </name>
            <name>
              <surname>Koutbi-Franceschi</surname>
              <given-names>L</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Smartwatch Electrocardiogram and Artificial Intelligence for Assessing Cardiac-Rhythm Safety of Drug Therapy in the COVID-19 Pandemic. The QT-Logs Study</article-title>
          <source>Int J Cardiol</source>
          <year>2021</year>
          <volume>331</volume>
          <fpage>333</fpage>
          <lpage>339</lpage>
          <pub-id pub-id-type="doi">10.1016/j.ijcard.2021.01.002</pub-id>
        </element-citation>
        <mixed-citation>5 Maille B, Wilkin M, Million M, Ress&#233;guier N, Franceschi F, Koutbi-Franceschi L, et al. Smartwatch Electrocardiogram and Artificial Intelligence for Assessing Cardiac-Rhythm Safety of Drug Therapy in the COVID-19 Pandemic. The QT-Logs Study. Int J Cardiol. 2021;331:333-9. doi: 10.1016/j.ijcard.2021.01.002.</mixed-citation>
      </ref>
      <ref id="B6">
        <label>6</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Macfarlane</surname>
              <given-names>PW</given-names>
            </name>
            <name>
              <surname>Kennedy</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Automated ECG interpretation &#8211; A Brief History from High Expectations to Deepest Networks</article-title>
          <source>Hearts</source>
          <year>2021</year>
          <volume>2</volume>
          <issue>4</issue>
          <fpage>433</fpage>
          <lpage>438</lpage>
          <pub-id pub-id-type="doi">10.3390/hearts2040034</pub-id>
        </element-citation>
        <mixed-citation>6 Macfarlane PW, Kennedy J. Automated ECG interpretation &#8211; A Brief History from High Expectations to Deepest Networks. Hearts. 2021;2(4):433-8. doi: 10.3390/hearts2040034.</mixed-citation>
      </ref>
      <ref id="B7">
        <label>7</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Yang</surname>
              <given-names>HW</given-names>
            </name>
            <name>
              <surname>Hsiao</surname>
              <given-names>CY</given-names>
            </name>
            <name>
              <surname>Peng</surname>
              <given-names>YQ</given-names>
            </name>
            <name>
              <surname>Lin</surname>
              <given-names>TY</given-names>
            </name>
            <name>
              <surname>Tsai</surname>
              <given-names>LW</given-names>
            </name>
            <name>
              <surname>Lin</surname>
              <given-names>C</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Identification of Patients with Potential Atrial Fibrillation during Sinus Rhythm Using Isolated P Wave Characteristics from 12-Lead ECGs</article-title>
          <source>J Pers Med</source>
          <year>2022</year>
          <volume>12</volume>
          <issue>10</issue>
          <fpage>1608</fpage>
          <lpage>1608</lpage>
          <pub-id pub-id-type="doi">10.3390/jpm12101608</pub-id>
        </element-citation>
        <mixed-citation>7 Yang HW, Hsiao CY, Peng YQ, Lin TY, Tsai LW, Lin C, et al. Identification of Patients with Potential Atrial Fibrillation during Sinus Rhythm Using Isolated P Wave Characteristics from 12-Lead ECGs. J Pers Med. 2022;12(10):1608. doi: 10.3390/jpm12101608.</mixed-citation>
      </ref>
      <ref id="B8">
        <label>8</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Winst&#233;n</surname>
              <given-names>AK</given-names>
            </name>
            <name>
              <surname>Lang&#233;n</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Airaksinen</surname>
              <given-names>KEJ</given-names>
            </name>
            <name>
              <surname>Teppo</surname>
              <given-names>K</given-names>
            </name>
          </person-group>
          <article-title>Net Benefit of Anticoagulation in Subclinical Device-Detected Atrial Fibrillation</article-title>
          <source>JAMA Netw Open</source>
          <year>2025</year>
          <volume>8</volume>
          <issue>5</issue>
          <elocation-id>e258461</elocation-id>
          <pub-id pub-id-type="doi">10.1001/jamanetworkopen.2025.8461</pub-id>
        </element-citation>
        <mixed-citation>8 Winst&#233;n AK, Lang&#233;n V, Airaksinen KEJ, Teppo K. Net Benefit of Anticoagulation in Subclinical Device-Detected Atrial Fibrillation. JAMA Netw Open. 2025;8(5):e258461. doi: 10.1001/jamanetworkopen.2025.8461.</mixed-citation>
      </ref>
      <ref id="B9">
        <label>9</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Kirchhof</surname>
              <given-names>P</given-names>
            </name>
            <name>
              <surname>Camm</surname>
              <given-names>AJ</given-names>
            </name>
            <name>
              <surname>Goette</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Brandes</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Eckardt</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Elvan</surname>
              <given-names>A</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Early Rhythm-Control Therapy in Patients with Atrial Fibrillation</article-title>
          <source>N Engl J Med</source>
          <year>2020</year>
          <volume>383</volume>
          <issue>14</issue>
          <fpage>1305</fpage>
          <lpage>1316</lpage>
          <pub-id pub-id-type="doi">10.1056/NEJMoa2019422</pub-id>
        </element-citation>
        <mixed-citation>9 Kirchhof P, Camm AJ, Goette A, Brandes A, Eckardt L, Elvan A, et al. Early Rhythm-Control Therapy in Patients with Atrial Fibrillation. N Engl J Med. 2020;383(14):1305-16. doi: 10.1056/NEJMoa2019422.</mixed-citation>
      </ref>
      <ref id="B10">
        <label>10</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Yuan</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Duffy</surname>
              <given-names>G</given-names>
            </name>
            <name>
              <surname>Dhruva</surname>
              <given-names>SS</given-names>
            </name>
            <name>
              <surname>Oesterle</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Pellegrini</surname>
              <given-names>CN</given-names>
            </name>
            <name>
              <surname>Theurer</surname>
              <given-names>J</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Deep Learning of Electrocardiograms in Sinus Rhythm from US Veterans to Predict Atrial Fibrillation</article-title>
          <source>JAMA Cardiol</source>
          <year>2023</year>
          <volume>8</volume>
          <issue>12</issue>
          <fpage>1131</fpage>
          <lpage>1139</lpage>
          <pub-id pub-id-type="doi">10.1001/jamacardio.2023.3701</pub-id>
        </element-citation>
        <mixed-citation>10 Yuan N, Duffy G, Dhruva SS, Oesterle A, Pellegrini CN, Theurer J, et al. Deep Learning of Electrocardiograms in Sinus Rhythm from US Veterans to Predict Atrial Fibrillation. JAMA Cardiol. 2023;8(12):1131-9. doi: 10.1001/jamacardio.2023.3701.</mixed-citation>
      </ref>
      <ref id="B11">
        <label>11</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Hygrell</surname>
              <given-names>T</given-names>
            </name>
            <name>
              <surname>Viberg</surname>
              <given-names>F</given-names>
            </name>
            <name>
              <surname>Dahlberg</surname>
              <given-names>E</given-names>
            </name>
            <name>
              <surname>Charlton</surname>
              <given-names>PH</given-names>
            </name>
            <name>
              <surname>Gudmundsdottir</surname>
              <given-names>KK</given-names>
            </name>
            <name>
              <surname>Mant</surname>
              <given-names>J</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>An Artificial Intelligence-Based Model for Prediction of Atrial Fibrillation from Single-Lead Sinus Rhythm Electrocardiograms Facilitating Screening</article-title>
          <source>Europace</source>
          <year>2023</year>
          <volume>25</volume>
          <issue>4</issue>
          <fpage>1332</fpage>
          <lpage>1338</lpage>
          <pub-id pub-id-type="doi">10.1093/europace/euad036</pub-id>
        </element-citation>
        <mixed-citation>11 Hygrell T, Viberg F, Dahlberg E, Charlton PH, Gudmundsdottir KK, Mant J, et al. An Artificial Intelligence-Based Model for Prediction of Atrial Fibrillation from Single-Lead Sinus Rhythm Electrocardiograms Facilitating Screening. Europace. 2023;25(4):1332-8. doi: 10.1093/europace/euad036.</mixed-citation>
      </ref>
      <ref id="B12">
        <label>12</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Habineza</surname>
              <given-names>T</given-names>
            </name>
            <name>
              <surname>Ribeiro</surname>
              <given-names>AH</given-names>
            </name>
            <name>
              <surname>Gedon</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Behar</surname>
              <given-names>JA</given-names>
            </name>
            <name>
              <surname>Ribeiro</surname>
              <given-names>ALP</given-names>
            </name>
            <name>
              <surname>Sch&#246;n</surname>
              <given-names>TB</given-names>
            </name>
          </person-group>
          <article-title>End-to-End Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks</article-title>
          <source>J Electrocardiol</source>
          <year>2023</year>
          <volume>81</volume>
          <fpage>193</fpage>
          <lpage>200</lpage>
          <pub-id pub-id-type="doi">10.1016/j.jelectrocard.2023.09.011</pub-id>
        </element-citation>
        <mixed-citation>12 Habineza T, Ribeiro AH, Gedon D, Behar JA, Ribeiro ALP, Sch&#246;n TB. End-to-End Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks. J Electrocardiol. 2023;81:193-200. doi: 10.1016/j.jelectrocard.2023.09.011.</mixed-citation>
      </ref>
      <ref id="B13">
        <label>13</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Ribeiro</surname>
              <given-names>AH</given-names>
            </name>
            <name>
              <surname>Ribeiro</surname>
              <given-names>MH</given-names>
            </name>
            <name>
              <surname>Paix&#227;o</surname>
              <given-names>GMM</given-names>
            </name>
            <name>
              <surname>Oliveira</surname>
              <given-names>DM</given-names>
            </name>
            <name>
              <surname>Gomes</surname>
              <given-names>PR</given-names>
            </name>
            <name>
              <surname>Canazart</surname>
              <given-names>JA</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Automatic Diagnosis of the 12-Lead ECG Using a Deep Neural Network</article-title>
          <source>Nat Commun</source>
          <year>2020</year>
          <volume>11</volume>
          <issue>1</issue>
          <fpage>1760</fpage>
          <lpage>1760</lpage>
          <pub-id pub-id-type="doi">10.1038/s41467-020-15432-4</pub-id>
        </element-citation>
        <mixed-citation>13 Ribeiro AH, Ribeiro MH, Paix&#227;o GMM, Oliveira DM, Gomes PR, Canazart JA, et al. Automatic Diagnosis of the 12-Lead ECG Using a Deep Neural Network. Nat Commun. 2020;11(1):1760. doi: 10.1038/s41467-020-15432-4.</mixed-citation>
      </ref>
      <ref id="B14">
        <label>14</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Santana</surname>
              <given-names>WB</given-names>
              <suffix>Jr</suffix>
            </name>
            <name>
              <surname>Pinto</surname>
              <given-names>MM</given-names>
              <suffix>Filho</suffix>
            </name>
            <name>
              <surname>Barreto</surname>
              <given-names>SM</given-names>
            </name>
            <name>
              <surname>Foppa</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Giatti</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Khera</surname>
              <given-names>R</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Use of Artificial Intelligence Applied to Electrocardiogram for Diagnosis of Left Ventricular Systolic Dysfunction</article-title>
          <source>Arq Bras Cardiol</source>
          <year>2025</year>
          <volume>122</volume>
          <issue>4</issue>
          <elocation-id>e20240740</elocation-id>
          <pub-id pub-id-type="doi">10.36660/abc.20240740</pub-id>
        </element-citation>
        <mixed-citation>14 Santana WB Jr, Pinto MM Filho, Barreto SM, Foppa M, Giatti L, Khera R, et al. Use of Artificial Intelligence Applied to Electrocardiogram for Diagnosis of Left Ventricular Systolic Dysfunction. Arq Bras Cardiol. 2025;122(4):e20240740. doi: 10.36660/abc.20240740.</mixed-citation>
      </ref>
      <ref id="B15">
        <label>15</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Khera</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Oikonomou</surname>
              <given-names>EK</given-names>
            </name>
            <name>
              <surname>Nadkarni</surname>
              <given-names>GN</given-names>
            </name>
            <name>
              <surname>Morley</surname>
              <given-names>JR</given-names>
            </name>
            <name>
              <surname>Wiens</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Butte</surname>
              <given-names>AJ</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Transforming Cardiovascular Care with Artificial Intelligence: From Discovery to Practice: JACC State-of-the-Art Review</article-title>
          <source>J Am Coll Cardiol</source>
          <year>2024</year>
          <volume>84</volume>
          <issue>1</issue>
          <fpage>97</fpage>
          <lpage>114</lpage>
          <pub-id pub-id-type="doi">10.1016/j.jacc.2024.05.003</pub-id>
        </element-citation>
        <mixed-citation>15 Khera R, Oikonomou EK, Nadkarni GN, Morley JR, Wiens J, Butte AJ, et al. Transforming Cardiovascular Care with Artificial Intelligence: From Discovery to Practice: JACC State-of-the-Art Review. J Am Coll Cardiol. 2024;84(1):97-114. doi: 10.1016/j.jacc.2024.05.003.</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.20250405i</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Short Editorial</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Applicability of Machine Learning Algorithms in the Diagnosis of Arrhythmias &#8211; How Long Until The Machine Starts Teaching Us?</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-6646-1163</contrib-id>
          <name>
            <surname>Pinto</surname>
            <given-names>Marcelo Martins</given-names>
            <suffix>Filho</suffix>
          </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">Belo Horizonte</named-content>
            <named-content content-type="state">MG</named-content>
          </addr-line>
          <country country="BR">Brazil</country>
          <institution content-type="original">Hospital das Cl&#237;nicas da Universidade Federal de Minas Gerais &#8211; Centro de Telessa&#250;de, Belo Horizonte, MG &#8211; Brazil</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c2"><label>Mailing Address:</label><bold>Marcelo Martins Pinto Filho</bold> &#8226; Faculdade de Medicina da Universidade Federal de Minas Gerais - Programa de P&#243;s-Gradua&#231;&#227;o em Infectologia e Medicina Tropical &#8211; Av. Alfredo Balena, 190. Postal Code <postal-code>30130-100</postal-code>, Belo Horizonte, MG &#8211; Brazil E-mail: <email>marcelo128ufmg@gmail.com</email> </corresp>
      </author-notes>
      <kwd-group xml:lang="en">
        <title>Keywords</title>
        <kwd>Cardiac Arrhythmia</kwd>
        <kwd>Artificial Intelligence</kwd>
        <kwd>Machine Learning</kwd>
        <kwd>Neural Network</kwd>
        <kwd>Electrocardiogram</kwd>
      </kwd-group>
    </front-stub>
    <body>
      <p>The electrocardiogram (ECG), in clinical use since the early 1900s, remains a beloved tool for cardiologists, clinicians, and medical students. It is arguably the most important bedside instrument in cardiology, essential for managing arrhythmias and acute ischemic syndromes, as well as guiding electrophysiologic care. Still, advances in electrocardiography interpretation have been only modest in the last hundred years. Devices have become more portable, digital, and capable of longer recordings, but core interpretive principles remain rooted in early 20th-century methods.<sup><xref ref-type="bibr" rid="B1">1</xref></sup> In recent years, this has been reshaped by the rise of computational technologies, especially artificial intelligence (AI). Tools such as deep neural networks (DNNs) and machine learning models (MLMs) are enabling a new era in ECG analysis, the AI-enhanced electrocardiography (AI-enhanced ECG).<sup><xref ref-type="bibr" rid="B2">2</xref></sup></p>
      <p>In this issue of the <italic>ABC Cardiol</italic>, Guimar&#227;es do Nascimento et al. report on a systematic review of studies evaluating the applicability of AI-enhanced ECG in the diagnosis of cardiac arrhythmias.<sup><xref ref-type="bibr" rid="B3">3</xref></sup> They included studies of different methodologies that addressed the role of AI-enhanced ECG in the detection of long-QT syndrome (LQTS) (one study), corrected QT interval (cQTi) (one study), and atrial fibrillation (AF) (eleven studies).</p>
      <p>For the detection of concealed LQTS among genetic types 1, 2, and 3, a DNN model was able to outperform the traditional evaluation (based on QTc alone) with an AUC of 0.900 (95% CI, 0.876-0.925) versus 0.824 (95% CI, 0.79-0.858), respectively. The model was also able to correctly identify the genetic type with an AUC from 0,863 (95% CI, 0.792-0.934) to 0.944 (95% CI, 0.918-0.970), depending on the genetic type.<sup><xref ref-type="bibr" rid="B4">4</xref></sup></p>
      <p>In the one study evaluating the cQTi <italic>per se</italic>, only measurement accuracy was evaluated, with fair agreement between AI-calculated cQTi by a smartwatch and the ECG.<sup><xref ref-type="bibr" rid="B5">5</xref></sup> It is important to highlight that automatic measurement of the ECG is a goal achieved since the 1970s with the implementation of Glasgow software and its consolidation in the 1980s.<sup><xref ref-type="bibr" rid="B6">6</xref></sup> The novelty of this study resides in showing the accuracy of measurement in different hardware (the smartwatch) and the possibility of self (or continuous) measurement of the cQTi.</p>
      <p>Among the papers evaluating AI models in the detection of AF, the methods were diverse; however, overall, the AI algorithms and DNN/ML models demonstrated good sensitivity and specificity. It is important to highlight that these studies reported on the detection of prevalent AF, with only one reporting on ECG analysis in sinus rhythm participants to predict AF, resulting in modest performance (AUM 0.64).<sup><xref ref-type="bibr" rid="B7">7</xref></sup> Among cardiac arrhythmias, AF has gained particular interest due to its epidemiological relevance, diversity in treatment options, and the increasing variety of screening strategies. Although the benefits of detection and treatment of subclinical AF are still debatable,<sup><xref ref-type="bibr" rid="B8">8</xref></sup> the benefits of early rhythm control of clinical AF have been demonstrated.<sup><xref ref-type="bibr" rid="B9">9</xref></sup></p>
      <p>This study reviews how AI is being applied to electrocardiography, particularly in the field of arrhythmias, showing comparable performance to traditional methods, and rapid progress is expected in the near term. However, several caveats must be considered. The review includes studies published only up to 2022 and given the exponential growth of research in this field, key studies may have been missed. For example, in July 2023, Yuan et al. reported using a convolutional neural network (CNN) to predict AF from 907,858 ECGs across six Veterans Affairs sites, achieving an AUC of 0.86 and an accuracy of 0.78.<sup><xref ref-type="bibr" rid="B10">10</xref></sup> That same year, Hygreaal et al. used a similar model on 478,963 single-lead ECGs from 14,831 older adults, achieving an AUC of 0.80.<sup><xref ref-type="bibr" rid="B11">11</xref></sup> Additionally, Habineza et al. also used CNN to predict AF in 1,230,809 ECGs (AUC 0.845).<sup><xref ref-type="bibr" rid="B12">12</xref></sup> External validation of the findings of the primary studies is also a point of concern since the explicability of the AI models, in general, is not satisfactory. Data extraction and evaluation from a single operator also raise concerns of selection bias.</p>
      <p>Beyond arrhythmia detection, AI-enhanced ECG holds promise for other areas, such as predicting heart failure and outcomes after acute cardiac events, refining risk stratification, and potentially enabling automated reporting without cardiologist input.<sup><xref ref-type="bibr" rid="B13">13</xref>,<xref ref-type="bibr" rid="B14">14</xref></sup> However, with this transformation comes a need for caution. Scientific validation must precede widespread clinical or commercial use, and ethical questions &#8212; such as accountability in the event of AI error &#8212; must be addressed by the scientific and regulatory communities.<sup><xref ref-type="bibr" rid="B15">15</xref></sup> Still, the rise of AI keeps electrocardiography as innovative and intriguing as it was over a century ago.</p>
    </body>
    <back>
      <fn-group>
        <fn fn-type="other" id="fn2">
          <p>
            <italic>Short Editorial related to the article: Applicability of Machine Learning Algorithms in Diagnosis of Atrial Fibrillation and LQTS by Electrocardiogram Interpretation: A Systematic Review</italic>
          </p>
        </fn>
      </fn-group>
    </back>
  </sub-article>
</article>
