<!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="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">kyfNmqY5QN7BMPwMMC7MGRF</article-id>
      <article-id specific-use="scielo-v2" pub-id-type="publisher-id">S0066-782X2026000201009</article-id>
      <article-id pub-id-type="other">01009</article-id>
      <article-id pub-id-type="doi">10.36660/abc.20260254</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Minieditorial</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Validando a Intelig&#234;ncia Artificial antes do Uso &#224; Beira do Leito: ChatGPT-4 versus Mini em Conte&#250;do sobre Hipertens&#227;o Baseado em Diretrizes</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-1466-9413</contrib-id>
          <name>
            <surname>Mesquita</surname>
            <given-names>Cl&#225;udio Tinoco</given-names>
          </name>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff2">
            <sup>2</sup>
          </xref>
          <xref ref-type="aff" rid="aff3">
            <sup>3</sup>
          </xref>
          <xref ref-type="aff" rid="aff4">
            <sup>4</sup>
          </xref>
          <xref ref-type="corresp" rid="c1"/>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Silva</surname>
            <given-names>Fernanda Azevedo</given-names>
          </name>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff2">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0004-1751-7089</contrib-id>
          <name>
            <surname>Couto</surname>
            <given-names>Ana Beatriz Costa do</given-names>
          </name>
          <xref ref-type="aff" rid="aff2">
            <sup>2</sup>
          </xref>
          <xref ref-type="aff" rid="aff3">
            <sup>3</sup>
          </xref>
        </contrib>
        <aff id="aff1">
          <label>1</label>
          <institution content-type="orgname">Universidade Federal Fluminense</institution>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brasil</country>
          <institution content-type="original">Universidade Federal Fluminense, Niter&#243;i, RJ &#8211; Brasil</institution>
        </aff>
        <aff id="aff2">
          <label>2</label>
          <institution content-type="orgname">Hospital Universit&#225;rio Ant&#244;nio Pedro</institution>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brasil</country>
          <institution content-type="original">Hospital Universit&#225;rio Ant&#244;nio Pedro, EBSERH, Health, Science &amp; Education Lab, Niter&#243;i, RJ &#8211; Brasil</institution>
        </aff>
        <aff id="aff3">
          <label>3</label>
          <institution content-type="orgname">Universidade Federal Fluminense</institution>
          <institution content-type="orgdiv1">Programa de P&#243;s-Gradua&#231;&#227;o em Ci&#234;ncias Cardiovasculares</institution>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brasil</country>
          <institution content-type="original">Programa de P&#243;s-Gradua&#231;&#227;o em Ci&#234;ncias Cardiovasculares &#8211; Universidade Federal Fluminense, Niter&#243;i, RJ &#8211; Brasil</institution>
        </aff>
        <aff id="aff4">
          <label>4</label>
          <institution content-type="orgname">Hospital Pr&#243;-Card&#237;aco</institution>
          <addr-line>
            <named-content content-type="city">Rio de Janeiro</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brasil</country>
          <institution content-type="original">Hospital Pr&#243;-Card&#237;aco, Rio de Janeiro, RJ &#8211; Brasil</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c1"><label>Correspond&#234;ncia:</label><bold>Claudio Tinoco Mesquita</bold> &#8226; Universidade Federal Fluminense, Hospital Universit&#225;rio Ant&#244;nio Pedro &#8211; Health, Science &amp; Education Lab &#8211; Av. Marqu&#234;s do Paran&#225;, 303. CEP <postal-code>24033-900</postal-code>. Niter&#243;i, RJ &#8211; Brasil E-mail: <email>claudiotinocomesquita@id.uff.br</email> </corresp>
      </author-notes>
      <pub-date date-type="pub" publication-format="electronic">
        <day>05</day>
        <month>06</month>
        <year>2026</year>
      </pub-date>
      <pub-date date-type="collection" publication-format="electronic">
        <month>02</month>
        <year>2026</year>
      </pub-date>
      <volume>123</volume>
      <issue>2</issue>
      <elocation-id>e20260254</elocation-id>
      <history>
        <date date-type="received">
          <day>25</day>
          <month>03</month>
          <year>2026</year>
        </date>
        <date date-type="rev-recd">
          <day>25</day>
          <month>03</month>
          <year>2026</year>
        </date>
        <date date-type="accepted">
          <day>01</day>
          <month>04</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>
      <kwd-group xml:lang="pt">
        <title>Palavras-chave</title>
        <kwd>Intelig&#234;ncia Artificial</kwd>
        <kwd>ChatGPT</kwd>
        <kwd>Hipertens&#227;o</kwd>
        <kwd>Diretrizes Cl&#237;nicas</kwd>
        <kwd>Valida&#231;&#227;o</kwd>
      </kwd-group>
      <counts>
        <fig-count count="2"/>
        <table-count count="0"/>
        <equation-count count="0"/>
        <ref-count count="6"/>
      </counts>
    </article-meta>
  </front>
  <body>
    <p>A integra&#231;&#227;o da intelig&#234;ncia artificial (IA) na pr&#225;tica m&#233;dica &#233; uma realidade. Desde o suporte &#224; tomada de decis&#227;o cl&#237;nica e o desenho de estudos at&#233; ferramentas de chatbots e a produ&#231;&#227;o de materiais educativos, os modelos de linguagem de grande escala (LLMs) s&#227;o cada vez mais utilizados na pr&#225;tica cl&#237;nica. Nesse contexto, estudos como o de Ata&#237;des et al.,<sup><xref ref-type="bibr" rid="B1">1</xref></sup> que avaliam a performance de materiais educacionais baseados em LLMs, s&#227;o fundamentais.</p>
    <p>A hipertens&#227;o &#233; uma das principais causas de morte prematura; sendo este um dos motivos que fazem a Organiza&#231;&#227;o Mundial da Sa&#250;de (OMS) estimular o desenvolvimento de campanhas de preven&#231;&#227;o. Trata-se de uma doen&#231;a que afeta m&#250;ltiplos &#243;rg&#227;os, causando grande impacto em todo o organismo. A condi&#231;&#227;o &#233; definida por press&#227;o arterial sist&#243;lica &#8805;140 mmHg ou press&#227;o arterial diast&#243;lica &#8805;90 mmHg, de acordo com as diretrizes da Sociedade Brasileira de Cardiologia.<sup><xref ref-type="bibr" rid="B2">2</xref></sup> O n&#250;mero de indiv&#237;duos diagnosticados com hipertens&#227;o aumenta a cada ano, e estudos indicam que h&#225; grande influ&#234;ncia dos h&#225;bitos alimentares da popula&#231;&#227;o, que atualmente s&#227;o caracterizados por alto consumo de alimentos ultraprocessados.<sup><xref ref-type="bibr" rid="B3">3</xref></sup></p>
    <p>O estudo que comparou ChatGPT-mini e ChatGPT-4.0 na gera&#231;&#227;o de conte&#250;do educacional sobre hipertens&#227;o aborda um aspecto muito importante da IA na medicina: a qualidade e a seguran&#231;a das informa&#231;&#245;es direcionadas aos pacientes. Ao avaliar sistematicamente acur&#225;cia, completude, qualidade estrutural (EQIP), consist&#234;ncia e alinhamento com diretrizes cl&#237;nicas, os autores realizaram uma avalia&#231;&#227;o abrangente dos conte&#250;dos educacionais que foram gerados por IA.<sup><xref ref-type="bibr" rid="B1">1</xref></sup></p>
    <p>&#192; primeira vista, comparar vers&#245;es de modelos de LLMs pode parecer algo sens&#237;vel ao tempo, em especial em um campo caracterizado por r&#225;pida evolu&#231;&#227;o tecnol&#243;gica. Na verdade, em fevereiro de 2026, os modelos de LLMs baseados no GPT-4 foram definitivamente descontinuados no ecossistema do ChatGPT, sendo substitu&#237;dos por gera&#231;&#245;es mais recentes (GPT-5). No entanto, isso n&#227;o diminui a relev&#226;ncia do estudo. Pelo contr&#225;rio, refor&#231;a sua mensagem central.</p>
    <p>Os autores devem ser parabenizados, pois o verdadeiro valor do trabalho n&#227;o est&#225; em determinar qual modelo apresenta melhor desempenho, mas em demonstrar que nenhum conte&#250;do gerado por IA deve ser considerado confi&#225;vel sem valida&#231;&#227;o rigorosa.<sup><xref ref-type="bibr" rid="B4">4</xref></sup> Mesmo modelos avan&#231;ados, capazes de produzir textos fluentes, coerentes e aparentemente confi&#225;veis, podem gerar imprecis&#245;es, omitir informa&#231;&#245;es cr&#237;ticas ou apresentar recomenda&#231;&#245;es desalinhadas com diretrizes estabelecidas.<sup><xref ref-type="bibr" rid="B5">5</xref></sup> De forma importante, este estudo refor&#231;a um princ&#237;pio fundamental que deve ser seguido independentemente do modelo ou vers&#227;o de LLM: a responsabilidade pelo conte&#250;do oferecido aos pacientes &#233; atribui&#231;&#227;o dos profissionais de sa&#250;de e as institui&#231;&#245;es &#8212; e n&#227;o responsabilidade do algoritmo<sup><xref ref-type="bibr" rid="B4">4</xref>,<xref ref-type="bibr" rid="B6">6</xref></sup> (<xref ref-type="fig" rid="f1">Figura 1</xref>).</p>
    <fig id="f1">
      <label>Figura 1</label>
      <caption>
        <title>Esta figura resume os principais dom&#237;nios para avaliar conte&#250;dos gerados por IA para pacientes: acur&#225;cia cient&#237;fica e base em evid&#234;ncias, revis&#227;o por especialista e responsabilidade, clareza e legibilidade, aus&#234;ncia de vieses, seguran&#231;a do paciente e privacidade de dados. Em conjunto, esses elementos refor&#231;am que os conte&#250;dos produzidos por IA exigem valida&#231;&#227;o sistem&#225;tica e supervis&#227;o humana antes do uso cl&#237;nico.</title>
      </caption>
      <graphic xlink:href="1678-4170-abc-123-02-e20260254-60254-gf01.tif"/></fig>
    <p>Por fim, nunca &#233; excessivo refor&#231;ar, o uso &#233;tico da IA &#233; essencial, especialmente quando LLMs s&#227;o utilizados no cuidado ao paciente. Os pacientes devem ser informados quando o conte&#250;do for produzido com aux&#237;lio da IA, e as institui&#231;&#245;es devem estabelecer processos claros de revis&#227;o, aprova&#231;&#227;o e atualiza&#231;&#227;o peri&#243;dica dos materiais educativos.</p>
    <p>Em conclus&#227;o, embora as tecnologias continuem a evoluir, o princ&#237;pio fundamental permanece inalterado: antes que a IA alcance o paciente, ela deve ser cuidadosamente testada, validada e contextualizada.</p>
  </body>
  <back>
    <fn-group>
      <fn fn-type="other" id="fn1">
        <p>Minieditorial referente ao artigo: Avalia&#231;&#227;o do ChatGPT-4.0 Versus ChatGPT-Mini na Gera&#231;&#227;o de Conte&#250;do sobre Hipertens&#227;o Baseado em Diretrizes</p>
      </fn>
    </fn-group>
    <ack>
      <title>Agradecimentos</title>
      <p>Dr. Cl&#225;udio Tinoco recebe os seguintes fomentos: Bolsa de Produtividade do CNPq e Bolsa de Cientista do Estado do Rio de Janeiro pela FAPERJ.</p>
    </ack>
    <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>Ata&#237;des</surname>
              <given-names>RJC</given-names>
            </name>
            <name>
              <surname>Campos</surname>
              <given-names>MAG</given-names>
            </name>
            <name>
              <surname>Souza</surname>
              <given-names>JVP</given-names>
            </name>
            <name>
              <surname>Rocha</surname>
              <given-names>RC</given-names>
            </name>
            <name>
              <surname>Lacalle</surname>
              <given-names>AA</given-names>
            </name>
            <name>
              <surname>Vieira</surname>
              <given-names>CB</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Assessment of ChatGPT-4.0 versus ChatGPT-Mini in Generating Guideline-Based Hypertension Content</article-title>
          <source>Arq Bras Cardiol</source>
          <year>2026</year>
          <volume>123</volume>
          <issue>2</issue>
          <elocation-id>e20250498</elocation-id>
          <pub-id pub-id-type="doi">10.36660/abc.20250498</pub-id>
        </element-citation>
        <mixed-citation>1 Ata&#237;des RJC, Campos MAG, Souza JVP, Rocha RC, Lacalle AA, Vieira CB, et al. Assessment of ChatGPT-4.0 versus ChatGPT-Mini in Generating Guideline-Based Hypertension Content. Arq Bras Cardiol. 2026;123(2):e20250498. doi: 10.36660/abc.20250498.</mixed-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Brand&#227;o</surname>
              <given-names>AA</given-names>
            </name>
            <name>
              <surname>Rodrigues</surname>
              <given-names>CIS</given-names>
            </name>
            <name>
              <surname>Bortolotto</surname>
              <given-names>LA</given-names>
            </name>
            <name>
              <surname>Armstrong</surname>
              <given-names>ADC</given-names>
            </name>
            <name>
              <surname>Mulinari</surname>
              <given-names>RA</given-names>
            </name>
            <name>
              <surname>Feitosa</surname>
              <given-names>ADM</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Brazilian Guidelines of Hypertension - 2025</article-title>
          <source>Arq Bras Cardiol</source>
          <year>2025</year>
          <volume>122</volume>
          <issue>9</issue>
          <elocation-id>e20250624</elocation-id>
          <pub-id pub-id-type="doi">10.36660/abc.20250624</pub-id>
        </element-citation>
        <mixed-citation>2 Brand&#227;o AA, Rodrigues CIS, Bortolotto LA, Armstrong ADC, Mulinari RA, Feitosa ADM, et al. Brazilian Guidelines of Hypertension - 2025. Arq Bras Cardiol. 2025;122(9):e20250624. doi: 10.36660/abc.20250624.</mixed-citation>
      </ref>
      <ref id="B3">
        <label>3</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Alhuneafat</surname>
              <given-names>L</given-names>
            </name>
            <name>
              <surname>Al Ta'ani</surname>
              <given-names>O</given-names>
            </name>
            <name>
              <surname>Arriola-Montenegro</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Al-Ajloun</surname>
              <given-names>YA</given-names>
            </name>
            <name>
              <surname>Naser</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Chaponan-Lavalle</surname>
              <given-names>A</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>The burden of Cardiovascular Disease in Latin America and the Caribbean, 1990-2019: An Analysis of the Global Burden of Disease Study</article-title>
          <source>Int J Cardiol</source>
          <year>2025</year>
          <volume>428</volume>
          <fpage>133143</fpage>
          <lpage>133143</lpage>
          <pub-id pub-id-type="doi">10.1016/j.ijcard.2025.133143</pub-id>
        </element-citation>
        <mixed-citation>3 Alhuneafat L, Al Ta'ani O, Arriola-Montenegro J, Al-Ajloun YA, Naser A, Chaponan-Lavalle A, et al. The burden of Cardiovascular Disease in Latin America and the Caribbean, 1990-2019: An Analysis of the Global Burden of Disease Study. Int J Cardiol. 2025;428:133143. doi: 10.1016/j.ijcard.2025.133143.</mixed-citation>
      </ref>
      <ref id="B4">
        <label>4</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Griffin</surname>
              <given-names>AC</given-names>
            </name>
            <name>
              <surname>Javier</surname>
              <given-names>SJ</given-names>
            </name>
            <name>
              <surname>Golding</surname>
              <given-names>M</given-names>
            </name>
            <name>
              <surname>Runnels</surname>
              <given-names>TW</given-names>
            </name>
            <name>
              <surname>Matthias</surname>
              <given-names>MS</given-names>
            </name>
            <name>
              <surname>Shimada</surname>
              <given-names>SL</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Designing Patient-Friendly Messages: Tutorial on Applying Human-Centered, Self-Determination Theory with AI Considerations</article-title>
          <source>J Med Internet Res</source>
          <year>2025</year>
          <volume>27</volume>
          <elocation-id>e78173</elocation-id>
          <pub-id pub-id-type="doi">10.2196/78173</pub-id>
        </element-citation>
        <mixed-citation>4 Griffin AC, Javier SJ, Golding M, Runnels TW, Matthias MS, Shimada SL, et al. Designing Patient-Friendly Messages: Tutorial on Applying Human-Centered, Self-Determination Theory with AI Considerations. J Med Internet Res. 2025;27:e78173. doi: 10.2196/78173.</mixed-citation>
      </ref>
      <ref id="B5">
        <label>5</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Wang</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Liu</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Yang</surname>
              <given-names>H</given-names>
            </name>
            <name>
              <surname>Guo</surname>
              <given-names>J</given-names>
            </name>
            <name>
              <surname>Wu</surname>
              <given-names>Y</given-names>
            </name>
            <name>
              <surname>Liu</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Ethical Considerations of Using ChatGPT in Health Care</article-title>
          <source>J Med Internet Res</source>
          <year>2023</year>
          <volume>25</volume>
          <elocation-id>e48009</elocation-id>
          <pub-id pub-id-type="doi">10.2196/48009</pub-id>
        </element-citation>
        <mixed-citation>5 Wang C, Liu S, Yang H, Guo J, Wu Y, Liu J. Ethical Considerations of Using ChatGPT in Health Care. J Med Internet Res. 2023;25:e48009. doi: 10.2196/48009.</mixed-citation>
      </ref>
      <ref id="B6">
        <label>6</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Mello</surname>
              <given-names>MM</given-names>
            </name>
            <name>
              <surname>Char</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Xu</surname>
              <given-names>SH</given-names>
            </name>
          </person-group>
          <article-title>Ethical Obligations to Inform Patients about Use of AI Tools</article-title>
          <source>JAMA</source>
          <year>2025</year>
          <volume>334</volume>
          <issue>9</issue>
          <fpage>767</fpage>
          <lpage>770</lpage>
          <pub-id pub-id-type="doi">10.1001/jama.2025.11417</pub-id>
        </element-citation>
        <mixed-citation>6 Mello MM, Char D, Xu SH. Ethical Obligations to Inform Patients about Use of AI Tools. JAMA. 2025;334(9):767-70. doi: 10.1001/jama.2025.11417.</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.20260254i</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Short Editorial</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Validating Artificial Intelligence before the Bedside: ChatGPT-4 vs Mini in Guideline-Based Hypertension Content</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-1466-9413</contrib-id>
          <name>
            <surname>Mesquita</surname>
            <given-names>Cl&#225;udio Tinoco</given-names>
          </name>
          <xref ref-type="aff" rid="aff5">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff6">
            <sup>2</sup>
          </xref>
          <xref ref-type="aff" rid="aff7">
            <sup>3</sup>
          </xref>
          <xref ref-type="aff" rid="aff8">
            <sup>4</sup>
          </xref>
          <xref ref-type="corresp" rid="c2"/>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Silva</surname>
            <given-names>Fernanda Azevedo</given-names>
          </name>
          <xref ref-type="aff" rid="aff5">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff6">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0004-1751-7089</contrib-id>
          <name>
            <surname>Couto</surname>
            <given-names>Ana Beatriz Costa do</given-names>
          </name>
          <xref ref-type="aff" rid="aff6">
            <sup>2</sup>
          </xref>
          <xref ref-type="aff" rid="aff7">
            <sup>3</sup>
          </xref>
        </contrib>
        <aff id="aff5">
          <label>1</label>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brazil</country>
          <institution content-type="original">Universidade Federal Fluminense, Niter&#243;i, RJ &#8211; Brazil</institution>
        </aff>
        <aff id="aff6">
          <label>2</label>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brazil</country>
          <institution content-type="original">Hospital Universit&#225;rio Ant&#244;nio Pedro, EBSERH, Health, Science &amp; Education Lab, Niter&#243;i, RJ &#8211; Brazil</institution>
        </aff>
        <aff id="aff7">
          <label>3</label>
          <addr-line>
            <named-content content-type="city">Niter&#243;i</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brazil</country>
          <institution content-type="original">Programa de P&#243;s-Gradua&#231;&#227;o em Ci&#234;ncias Cardiovasculares &#8211; Universidade Federal Fluminense, Niter&#243;i, RJ &#8211; Brazil</institution>
        </aff>
        <aff id="aff8">
          <label>4</label>
          <addr-line>
            <named-content content-type="city">Rio de Janeiro</named-content>
            <named-content content-type="state">RJ</named-content>
          </addr-line>
          <country country="BR">Brazil</country>
          <institution content-type="original">Hospital Pr&#243;-Card&#237;aco, Rio de Janeiro, RJ &#8211; Brazil</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c2"><label>Mailing Address:</label><bold>Claudio Tinoco Mesquita</bold> &#8226; Universidade Federal Fluminense, Hospital Universit&#225;rio Ant&#244;nio Pedro &#8211; Health, Science &amp; Education Lab &#8211; Av. Marqu&#234;s do Paran&#225;, 303. Postal Code <postal-code>24033-900</postal-code>. Niter&#243;i, RJ &#8211; Brazil E-mail: <email>claudiotinocomesquita@id.uff.br</email> </corresp>
      </author-notes>
      <kwd-group xml:lang="en">
        <title>Keywords</title>
        <kwd>Artificial Intelligence</kwd>
        <kwd>ChatGPT</kwd>
        <kwd>Hypertension</kwd>
        <kwd>Clinical Guidelines</kwd>
        <kwd>Validation</kwd>
      </kwd-group>
    </front-stub>
    <body>
      <p>The rapid integration of artificial intelligence (AI) into medical practice is a reality. From clinical decision support and study design to chatbot tools and the production of educational materials, large language models (LLMs) are increasingly used in daily practice. In this context, studies like the study of Ata&#237;des et al.,<sup><xref ref-type="bibr" rid="B1">1</xref></sup> evaluating the performance of LLM-based materials, are crucial.</p>
      <p>Hypertension is one of the leading causes of premature death; therefore, the World Health Organization (WHO) invests in prevention campaigns. It is a disease that affects multiple organs, causing a major impact on the entire body. The condition is defined by a systolic blood pressure (BP) of 140 mmHg or higher, or a diastolic BP of 90 mmHg, according to Brazilian Society of Cardiology guidelines.<sup><xref ref-type="bibr" rid="B2">2</xref></sup> The number of individuals diagnosed with hypertension increases each year, and studies indicate that the population's eating habits are characterized by high consumption of ultra-processed foods.<sup><xref ref-type="bibr" rid="B3">3</xref></sup></p>
      <p>The study comparing ChatGPT-mini and ChatGPT-4.0 in the generation of hypertension educational content addresses a very important aspect of AI in medicine: the quality and safety of patient-directed information. By systematically assessing accuracy, completeness, structural quality (EQIP), consistency, and alignment with clinical guidelines, the authors provided a comprehensive framework for evaluating AI-generated health content.<sup><xref ref-type="bibr" rid="B1">1</xref></sup></p>
      <p>At first glance, comparing two specific model versions may appear time-sensitive in a field characterized by rapid technological turnover. Indeed, as of February 2026, GPT-4-based models have been fully discontinued within the ChatGPT ecosystem, with newer generations now in use. However, this does not diminish the relevance of the study. On the contrary, it reinforces its central message.</p>
      <p>The authors must be congratulated because the true value of their work lies not in determining which model performs better, but in demonstrating that no AI-generated content should be assumed reliable without rigorous validation.<sup><xref ref-type="bibr" rid="B4">4</xref></sup> Even advanced models capable of producing fluent, coherent, and seemingly authoritative text may generate inaccuracies, omit critical information, or present recommendations that are misaligned with established guidelines.<sup><xref ref-type="bibr" rid="B5">5</xref></sup> Importantly, this study underscores a very important principle that must be followed with any specific LLM model or version: the responsibility for the content delivered to patients remains with healthcare professionals and institutions&#8212;not with the algorithm<sup><xref ref-type="bibr" rid="B4">4</xref>,<xref ref-type="bibr" rid="B6">6</xref></sup> (<xref ref-type="fig" rid="f2">Figure 1</xref>).</p>
      <fig id="f2">
        <label>Figure 1</label>
        <caption>
          <title>This figure summarizes the main domains to assess AI-generated content for patients: scientific accuracy and evidence base, expert review and responsibility, clarity and readability, absence of bias, patient safety, and data privacy. Together, these elements reinforce that AI outputs require systematic validation and human oversight before clinical use.</title>
        </caption>
        <graphic xlink:href="1678-4170-abc-123-02-e20260254-60254-gf01-en.tif"/></fig>
      <p>Finally, ethical use of AI is critical, especially when LLMs are used in patient management. Patients should be informed when content is AI-assisted, and institutions must establish clear processes for review, approval, and periodic updating of educational materials<sup>7</sup>.</p>
      <p>In conclusion, while technologies will continue to evolve, the fundamental requirement remains unchanged: before AI reaches the patient, it must be carefully tested, validated, and contextualized.</p>
    </body>
    <back>
      <fn-group>
        <fn fn-type="other" id="fn2">
          <p>Short Editorial related to the article: Assessment of ChatGPT-4.0 versus ChatGPT-Mini in Generating Guideline-Based Hypertension Content</p>
        </fn>
      </fn-group>
      <ack>
        <title>Acknowledgments</title>
        <p>Dr. Cl&#225;udio Tinoco receives the following funding: CNPq Productivity Grant and Rio de Janeiro State Scientist Grant from FAPERJ.</p>
      </ack>
    </back>
  </sub-article>
</article>
