<!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="1.0" specific-use="sps-1.6" xml:lang="en">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">ijcs</journal-id>
      <journal-title-group>
        <journal-title>International Journal of Cardiovascular Sciences</journal-title>
        <abbrev-journal-title abbrev-type="publisher">Int. J. Cardiovasc. Sci.</abbrev-journal-title>
      </journal-title-group>
      <issn pub-type="epub">2359-5647</issn>
      <issn pub-type="ppub">2359-4802</issn>
      <publisher>
        <publisher-name>Sociedade Brasileira de Cardiologia</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id" specific-use="scielo-v3">4KsvPQ4ts8BXbPsmfKNX95J</article-id>
      <article-id pub-id-type="publisher-id" specific-use="scielo-v2">S2359-56472017000300187</article-id>
      <article-id pub-id-type="doi">10.5935/2359-4802.20170027</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Editorial</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Artificial Intelligence and Machine Learning in Cardiology - A Change of Paradigm</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <name>
            <surname>Mesquita</surname>
            <given-names>Claudio Tinoco</given-names>
          </name>
          <xref ref-type="aff" rid="aff1"/>
          <xref ref-type="corresp" rid="c1"/>
        </contrib>
        <aff id="aff1">
          <institution content-type="orgname">Universidade Federal Fluminense</institution>
          <institution content-type="orgdiv1">Hospital Universit&#225;rio Ant&#244;nio Pedro</institution>
          <institution content-type="orgdiv2">Departamento de Medicina Cl&#237;nica</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">Brazil</country>
          <institution content-type="original">Professor do Departamento de Medicina Cl&#237;nica do Hospital Universit&#225;rio Ant&#244;nio Pedro, Universidade Federal Fluminense (UFF), Niter&#243;i, RJ - Brazil</institution>
          <institution content-type="normalized">Universidade Federal Fluminense</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c1"><bold>Mailing Address: Cl&#225;udio Tinoco Mesquita</bold>, Hospital Universit&#225;rio Ant&#244;nio Pedro. Rua Marqu&#234;s do Paran&#225;, 303 - Centro. Postal Code: 24033-900 - Niter&#243;i, RJ - Brazil. E-mail: <email>claudiotinocomesquita@gmail.com</email>
				</corresp>
      </author-notes>
      <pub-date pub-type="epub-ppub">
        <season>May-Jun</season>
        <year>2017</year>
      </pub-date>
      <volume>30</volume>
      <issue>3</issue>
      <fpage>187</fpage>
      <lpage>188</lpage>
      <history>
        <date date-type="received">
          <day>13</day>
          <month>03</month>
          <year>2017</year>
        </date>
        <date date-type="rev-recd">
          <day>12</day>
          <month>04</month>
          <year>2017</year>
        </date>
        <date date-type="accepted">
          <day>12</day>
          <month>04</month>
          <year>2017</year>
        </date>
      </history>
      <permissions>
        <license license-type="open-access" xlink:href="http://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, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.</license-p>
        </license>
      </permissions>
      <kwd-group xml:lang="en">
        <title>Keywords</title>
        <kwd>Artificial Intelligence/trends</kwd>
        <kwd>Computer Systems/trends</kwd>
        <kwd>Machine Learning/trends</kwd>
        <kwd>Cardiovascular Diseases</kwd>
        <kwd>Echocardiography/trends</kwd>
        <kwd>NucleAR Medicine/trends</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <disp-quote>
      <p>
        <italic>A robot may not injure a human being or, through inaction,allow a human being to come to harm.</italic>
      </p>
      <p>
        <italic>First Law of Robotics - Isaac Asimov</italic>
      </p>
    </disp-quote>
    <p>We are experiencing a change paradigm in modern life. With the presence of computers and intelligent machines everywhere, the predictions of science-fiction books from years ago gradually become reality; these are the times of pervasive computing. Among the computational most frequently mentioned tools in clinical studies and seen with enthusiasm by the scientific community is the Artificial Intelligence and consequently the machines that learn, which is best quoted in its original English form, Machine Learning. In general Artificial Intelligence is defined as the constellation of items (algorithms, robotics, neural networks) that allow a software to have intelligence properties that are comparable to those of a human being, among them learning from databases with minimal human interference.<xref ref-type="bibr" rid="B1">1</xref>
		</p>
    <p>Obermeyer and Emanuel recently wrote an editorial stating that Machine Learning has become widespread and imperative for solving complex problems in the various fields of science, and in the medical field its use will transform the practice.<xref ref-type="bibr" rid="B2">2</xref> The use of artificial intelligence is evolving increasingly in cardiology and there are already excellent examples in several areas. Using a sophisticated learning system to electrocardiographic interpretation, Li et al. achieved that electrocardiographic patterns were automatically recognized with an accuracy of 88% for the classification of abnormal rhythms<sup>(</sup><xref ref-type="bibr" rid="B3">3</xref><sup>)</sup>. One of the most important limitations of the system studied was the quality of the electrocardiographic signal for interpretation and learning, which highlights one of the essential characteristics of Machine Learning, that is the need for accurate and reproducible information for the formation of databases.<xref ref-type="bibr" rid="B2">2</xref><sup>,</sup><xref ref-type="bibr" rid="B3">3</xref> As databases are usually produced from patients selected for their basic condition, one of the most important points for development is the creation of broader and generalizable databases that do not induce biases in the interpretation of findings, point in which industry is heavily investing at the moment.<xref ref-type="bibr" rid="B2">2</xref>
		</p>
    <p>In echocardiography, many studies are evaluating the use of Machine Learning in image interpretation, such as the Narula et al.<xref ref-type="bibr" rid="B4">4</xref> who, through a database of patients with hypertrophic cardiomyopathy and individuals with physiological hypertrophy who were submitted to Speckle Tracking, were able to create a computer system based on Machine Learnig that reached to assist inexperienced echocardiographers in distinguishing between the two conditions with excellent accuracy. Tajik,<xref ref-type="bibr" rid="B5">5</xref> in an enthusiastic editorial, pointed out that Machine Learning should reduce or even eliminate the intra- and interobserver variability of echocardiographic exams and greatly reduce cognitive errors. At this point the use of artificial intelligence comes across medical ethics, because the doubts that can occur in cases of errors may be linked to the attribution of responsibilities: did the doctor fail or did the software fail? Experiences with the use of autopilots in aviation may serve as a basis for the ethical discussion that will occur, given that there is always at least one human being responsible for the flight even when using the modern devices of commercial aviation. Obermeyer and Emanuel<xref ref-type="bibr" rid="B2">2</xref> point out that there will be a massive reduction in the need for doctors in situations where computers can be fed directly by digital information such as radiology and pathology because the large amount of digital information available will allow the formation of reliable databases that will lead to a performance of the machines superior to the human.</p>
    <p>When artificial intelligence is employed in more complex clinical contexts, there is a still longer way to go. Austin et al.<xref ref-type="bibr" rid="B6">6</xref> used a Machine Learning and data mining system to evaluate and classify patients with heart failure and found that although the system was superior to conventional methods for predicting heart failure with preserved ejection fraction, there were no advantages over the traditional logistic regression. Liu et al.<xref ref-type="bibr" rid="B7">7</xref> developed a system based on Machine Learning for prediction of adverse coronary events in patients with chest pain in the emergency room and compared it with the TIMI score. Although the performance of the new system is reliable for predicting mortality and cardiac events in 30 days, the authors themselves acknowledge that clinical decisions are dependent on factors that still can not be fully incorporated into the machines, one of which is the physicians experience.<xref ref-type="bibr" rid="B7">7</xref>
		</p>
    <p>In nuclear cardiology Arsanjani et al.<xref ref-type="bibr" rid="B8">8</xref> evaluated the use of the Machine Learning tool to predict myocardial revascularization from myocardial perfusion scintigraphy data, finding an accuracy comparable or even superior to that of experienced examiners in the interpretation of the scintigraphic examination. Garcia et al.,<xref ref-type="bibr" rid="B9">9</xref> in an excellent review on the subject, point out that clinical decision support and artificial intelligence systems serve as warnings for the cognitive bias of clinicians and reduce intra and interobserver variability, allowing to interpret the exams faster and with greater accuracy, as observed in studies in which the diagnostic interpretation of the examination by the computer is similar to that of the experts.<xref ref-type="bibr" rid="B10">10</xref> We generally agree with this view and consider that the support to make the clinical decision and the improvement of diagnostic and prognostic performances should be encouraged and supported by physicians of the various specialties. The frequent concern about the eventual replacement of the physician by the machines is not substantiated by the facts. The medical profession is of a complexity and subjectivity that makes the task impossible in its entirety by the machines, at least at the present stage of knowledge. The proper use of computing allows for not only the improved of medical performance but also the quest for solidarity among patients with successful experiences in creating social networks for patients.<xref ref-type="bibr" rid="B11">11</xref>
		</p>
    <p>Only the study of the profound impact for the development and use of these tools can bring the answers to the questions that are now in the minds of doctors and their patients. The <italic>International Journal of Cardiovascular Sciences</italic> encourages its readers and contributors to send scientific papers on the subject for publication.</p>
  </body>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="B1">
        <label>1</label>
        <mixed-citation>1 Forsting M. Hot Topics: Will Machine Learning Change Medicine? J Nucl Med. 2017;58(3):357-8.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Forsting</surname>
              <given-names>M</given-names>
            </name>
          </person-group>
          <article-title>Hot Topics: Will Machine Learning Change Medicine?</article-title>
          <source>J Nucl Med</source>
          <year>2017</year>
          <volume>58</volume>
          <issue>3</issue>
          <fpage>357</fpage>
          <lpage>358</lpage>
        </element-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <mixed-citation>2 Obermeyer Z . Emanuel EJ. Predicting the future: big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216-9.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Obermeyer</surname>
              <given-names>Z</given-names>
            </name>
          </person-group>
          <article-title>Emanuel EJ: Predicting the future: big data, machine learning, and clinical medicine</article-title>
          <source>N Engl J Med</source>
          <year>2016</year>
          <volume>375</volume>
          <issue>13</issue>
          <fpage>1216</fpage>
          <lpage>1219</lpage>
        </element-citation>
      </ref>
      <ref id="B3">
        <label>3</label>
        <mixed-citation>3 Li Q, Rajagopalan C, Clifford GD. A machine learning approach to multi-level ECG signal quality classification. Comput Methods Programs Biomed . 2014;117(3):435-47.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Li</surname>
              <given-names>Q</given-names>
            </name>
            <name>
              <surname>Rajagopalan</surname>
              <given-names>C</given-names>
            </name>
            <name>
              <surname>Clifford</surname>
              <given-names>GD</given-names>
            </name>
          </person-group>
          <article-title>A machine learning approach to multi-level ECG signal quality classification</article-title>
          <source>Comput Methods Programs Biomed</source>
          <year>2014</year>
          <volume>117</volume>
          <issue>3</issue>
          <fpage>435</fpage>
          <lpage>447</lpage>
        </element-citation>
      </ref>
      <ref id="B4">
        <label>4</label>
        <mixed-citation>4 Narula S, Shameer K, Salem Omar AM, Dudley JT, Sengupta PP. Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography. J Am Coll Cardiol. 2016;68(21):2287-95.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Narula</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Shameer</surname>
              <given-names>K</given-names>
            </name>
            <name>
              <surname>Salem Omar</surname>
              <given-names>AM</given-names>
            </name>
            <name>
              <surname>Dudley</surname>
              <given-names>JT</given-names>
            </name>
            <name>
              <surname>Sengupta</surname>
              <given-names>PP</given-names>
            </name>
          </person-group>
          <article-title>Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography</article-title>
          <source>J Am Coll Cardiol</source>
          <year>2016</year>
          <volume>68</volume>
          <issue>21</issue>
          <fpage>2287</fpage>
          <lpage>2295</lpage>
        </element-citation>
      </ref>
      <ref id="B5">
        <label>5</label>
        <mixed-citation>5 Tajik AJ. Machine Learning for Echocardiographic Imaging: Embarking on Another Incredible Journey. J Am Coll Cardiol.2016;68(21):2296-8.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Tajik</surname>
              <given-names>AJ</given-names>
            </name>
          </person-group>
          <article-title>Machine Learning for Echocardiographic Imaging: Embarking on Another Incredible Journey</article-title>
          <source>J Am Coll Cardiol</source>
          <year>2016</year>
          <volume>68</volume>
          <issue>21</issue>
          <fpage>2296</fpage>
          <lpage>2298</lpage>
        </element-citation>
      </ref>
      <ref id="B6">
        <label>6</label>
        <mixed-citation>6 Austin PC, Tu J V, Ho JE, Levy D, Lee DS. Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. J Clin Epidemiol. 2013;66(4):398-407.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Austin</surname>
              <given-names>PC</given-names>
            </name>
            <name>
              <surname>Tu</surname>
              <given-names>J V</given-names>
            </name>
            <name>
              <surname>Ho</surname>
              <given-names>JE</given-names>
            </name>
            <name>
              <surname>Levy</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Lee</surname>
              <given-names>DS</given-names>
            </name>
          </person-group>
          <article-title>Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes</article-title>
          <source>J Clin Epidemiol</source>
          <year>2013</year>
          <volume>66</volume>
          <issue>4</issue>
          <fpage>398</fpage>
          <lpage>407</lpage>
        </element-citation>
      </ref>
      <ref id="B7">
        <label>7</label>
        <mixed-citation>7 Liu N, Lee MAB, Ho AFW, Haaland B, Fook-Chong S, Koh ZX, et al. Risk stratification for prediction of adverse coronary events in emergency department chest pain patients with a machine learning score compared with the TIMI score. Int J Cardiol . 2014;177(3):1095-7.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Liu</surname>
              <given-names>N</given-names>
            </name>
            <name>
              <surname>Lee</surname>
              <given-names>MAB</given-names>
            </name>
            <name>
              <surname>Ho</surname>
              <given-names>AFW</given-names>
            </name>
            <name>
              <surname>Haaland</surname>
              <given-names>B</given-names>
            </name>
            <name>
              <surname>Fook-Chong</surname>
              <given-names>S</given-names>
            </name>
            <name>
              <surname>Koh</surname>
              <given-names>ZX</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Risk stratification for prediction of adverse coronary events in emergency department chest pain patients with a machine learning score compared with the TIMI score</article-title>
          <source>Int J Cardiol</source>
          <year>2014</year>
          <volume>177</volume>
          <issue>3</issue>
          <fpage>1095</fpage>
          <lpage>1097</lpage>
        </element-citation>
      </ref>
      <ref id="B8">
        <label>8</label>
        <mixed-citation>8 Arsanjani R, Dey D, Khachatryan T, Shalev A, Hayes SW, Fish M, et al. Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population. J Nucl Cardiol. 2014;22(5):877-84.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Arsanjani</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Dey</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Khachatryan</surname>
              <given-names>T</given-names>
            </name>
            <name>
              <surname>Shalev</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Hayes</surname>
              <given-names>SW</given-names>
            </name>
            <name>
              <surname>Fish</surname>
              <given-names>M</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population</article-title>
          <source>J Nucl Cardiol</source>
          <year>2014</year>
          <volume>22</volume>
          <issue>5</issue>
          <fpage>877</fpage>
          <lpage>884</lpage>
        </element-citation>
      </ref>
      <ref id="B9">
        <label>9</label>
        <mixed-citation>9 Garcia E V, Klein JL, Taylor AT. Clinical decision support systems in myocardial perfusion imaging. J Nucl Cardiol. 2014;21(3):427-39.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Garcia</surname>
              <given-names>E V</given-names>
            </name>
            <name>
              <surname>Klein</surname>
              <given-names>JL</given-names>
            </name>
            <name>
              <surname>Taylor</surname>
              <given-names>AT</given-names>
            </name>
          </person-group>
          <article-title>Clinical decision support systems in myocardial perfusion imaging</article-title>
          <source>J Nucl Cardiol</source>
          <year>2014</year>
          <volume>21</volume>
          <issue>3</issue>
          <fpage>427</fpage>
          <lpage>439</lpage>
        </element-citation>
      </ref>
      <ref id="B10">
        <label>10</label>
        <mixed-citation>10 Arsanjani R, Xu Y, Dey D, Vahistha V, Shalev A, Nakanishi R, et al. Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population. J Nucl Cardiol. 2013;20(4):553-62.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Arsanjani</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Xu</surname>
              <given-names>Y</given-names>
            </name>
            <name>
              <surname>Dey</surname>
              <given-names>D</given-names>
            </name>
            <name>
              <surname>Vahistha</surname>
              <given-names>V</given-names>
            </name>
            <name>
              <surname>Shalev</surname>
              <given-names>A</given-names>
            </name>
            <name>
              <surname>Nakanishi</surname>
              <given-names>R</given-names>
            </name>
            <etal/>
          </person-group>
          <article-title>Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population</article-title>
          <source>J Nucl Cardiol</source>
          <year>2013</year>
          <volume>20</volume>
          <issue>4</issue>
          <fpage>553</fpage>
          <lpage>562</lpage>
        </element-citation>
      </ref>
      <ref id="B11">
        <label>11</label>
        <mixed-citation>11 Medina EL, Mesquita CT, Loques Filho O. Healthcare social networks for patients with cardiovascular diseases and recommendation systems. Int J Cardiovasc Sci. 2016;29(1):80-5.</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Medina</surname>
              <given-names>EL</given-names>
            </name>
            <name>
              <surname>Mesquita</surname>
              <given-names>CT</given-names>
            </name>
            <name>
              <surname>Loques</surname>
              <given-names>O</given-names>
              <suffix>Filho</suffix>
            </name>
          </person-group>
          <article-title>Healthcare social networks for patients with cardiovascular diseases and recommendation systems</article-title>
          <source>Int J Cardiovasc Sci</source>
          <year>2016</year>
          <volume>29</volume>
          <issue>1</issue>
          <fpage>80</fpage>
          <lpage>85</lpage>
        </element-citation>
      </ref>
    </ref-list>
  </back>
  <sub-article article-type="translation" id="s1" xml:lang="pt">
    <front-stub>
      <title-group>
        <article-title>Intelig&#234;ncia Artificial e <italic>Machine Learning</italic> em Cardiologia - Uma Mudan&#231;a de Paradigma</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <name>
            <surname>Mesquita</surname>
            <given-names>Claudio Tinoco</given-names>
          </name>
          <xref ref-type="corresp" rid="c2"/>
          <xref ref-type="aff" rid="aff2">1</xref>
        </contrib>
        <aff id="aff2">
          <label>1</label>
          <institution content-type="original">Professor do Departamento de Medicina Cl&#237;nica do Hospital Universit&#225;rio Ant&#244;nio Pedro, Universidade Federal Fluminense (UFF), Niter&#243;i, RJ - Brasil</institution>
        </aff>
      </contrib-group>
      <author-notes>
        <corresp id="c2"><bold>Correspond&#234;ncia: Cl&#225;udio Tinoco Mesquita</bold>, Hospital Universit&#225;rio Ant&#244;nio Pedro. Rua Marqu&#234;s do Paran&#225;, 303 - Centro. CEP 24033-900 - Niter&#243;i, RJ - Brasil. E-mail: <email>claudiotinocomesquita@gmail.com</email>
				</corresp>
      </author-notes>
      <kwd-group xml:lang="pt">
        <title>Palavras-chave:</title>
        <kwd>Intelig&#234;ncia Artificial/tend&#234;ncias</kwd>
        <kwd>Aprendizado de M&#225;quinas/tend&#234;ncias</kwd>
        <kwd>Doen&#231;as cardiovasculares</kwd>
        <kwd>Ecocardiografia/tend&#234;ncias</kwd>
        <kwd>Medicina Nuclear/tend&#234;ncias</kwd>
      </kwd-group>
    </front-stub>
    <body>
      <disp-quote>
        <p>
          <italic>A robot may not injure a human being or, through inaction,allow a human being to come to harm.</italic>
        </p>
        <p>
          <italic>First Law of Robotics - Isaac Asimov</italic>
        </p>
      </disp-quote>
      <p>Vivenciamos uma mudan&#231;a de paradigma na vida moderna. Com a presen&#231;a de computadores e m&#225;quinas inteligentes em todos os lugares, as predi&#231;&#245;es dos livros de fic&#231;&#227;o cient&#237;fica de anos atr&#225;s passam gradativamente a se tornar realidade; s&#227;o os tempos da computa&#231;&#227;o &#250;b&#237;qua. Entre as ferramentas computacionais mais frequentemente mencionadas em estudos cl&#237;nicos e vistas com entusiasmo por parte da comunidade cient&#237;fica se destacam a Intelig&#234;ncia Artificial e o consequente aprendizado das m&#225;quinas, que &#233; melhor citado na sua forma original em ingl&#234;s, o Machine Learning. De modo geral a Intelig&#234;ncia Artificial &#233; definida como a constela&#231;&#227;o de itens (algoritmos, rob&#243;tica, redes neuronais) que permitem que um software tenha propriedades de intelig&#234;ncia que se comparam &#224;s de um ser humano, entre elas o aprendizado com m&#237;nima interfer&#234;ncia humana a partir de bancos de dados.<xref ref-type="bibr" rid="B1">1</xref>
			</p>
      <p>Recentemente Obermeyer e Emanuel escreveram um editorial afirmando que o Machine Learning tornou-se disseminado e indispens&#225;vel para a resolu&#231;&#227;o de problemas complexos nos diversos campos da ci&#234;ncia, sendo que na &#225;rea m&#233;dica sua utiliza&#231;&#227;o ir&#225; transformar a pr&#225;tica.<xref ref-type="bibr" rid="B2">2</xref> A utiliza&#231;&#227;o de intelig&#234;ncia artificial est&#225; evoluindo de modo crescente na cardiologia e j&#225; h&#225; excelentes exemplos em diversas &#225;reas. Utilizando um sistema sofisticado de aprendizado para interpreta&#231;&#227;o eletrocardiogr&#225;fica Li e colaboradores<xref ref-type="bibr" rid="B3">3</xref> conseguiram que padr&#245;es eletrocardiogr&#225;ficos fossem reconhecidos automaticamente com acur&#225;cia de 88% para classifica&#231;&#227;o dos ritmos anormais. Uma das limita&#231;&#245;es mais importantes do sistema estudado foi a qualidade do sinal eletrocardiogr&#225;fico para interpreta&#231;&#227;o e aprendizado, o que ressalta uma das caracter&#237;sticas essenciais do Machine Learning, que &#233; a necessidade de informa&#231;&#245;es acuradas e reprodut&#237;veis para forma&#231;&#227;o de bancos de dados.<xref ref-type="bibr" rid="B2">2</xref><sup>,</sup><xref ref-type="bibr" rid="B3">3</xref> Como os bancos de dados s&#227;o, geralmente produzidos a partir de pacientes selecionados por sua condi&#231;&#227;o de base, um dos mais importantes pontos para o desenvolvimento &#233; a cria&#231;&#227;o de bases de dados mais amplas e generaliz&#225;veis, que n&#227;o induzam vieses na interpreta&#231;&#227;o dos achados, ponto em que a ind&#250;stria est&#225; investindo intensamente no momento.<xref ref-type="bibr" rid="B2">2</xref>
			</p>
      <p> Na ecocardiografia muitos estudos est&#227;o avaliando o uso do Machine Learning na interpreta&#231;&#227;o de imagens, como o de Narula et al.<xref ref-type="bibr" rid="B4">4</xref> que atrav&#233;s de um banco de dados de pacientes com miocardiopatia hipertr&#243;fica e de indiv&#237;duos com hipertrofia fisiol&#243;gica que foram submetidos a Speckle Tracking, conseguiram criar um sistema computacional baseado em Machine Learnig que foi capaz de assistir ecocardiografistas pouco experientes na distin&#231;&#227;o entre as duas condi&#231;&#245;es com excelente acur&#225;cia. Tajik,<xref ref-type="bibr" rid="B5">5</xref> em um entusiasmado editorial, assinalou que o Machine Learning dever&#225; reduzir ou mesmo eliminar a variabilidade intra e interobservador dos exames ecocardiogr&#225;ficos e reduzir acentuadamente os erros cognitivos. Neste ponto o uso da intelig&#234;ncia artificial depara-se com a &#233;tica m&#233;dica, pois as d&#250;vidas que podem ocorrer em casos de erros poder&#227;o estar ligadas &#224; atribui&#231;&#227;o de responsabilidades: errou o m&#233;dico ou errou o software? As experi&#234;ncias com o uso de pilotos autom&#225;ticos na avia&#231;&#227;o poder&#227;o servir de base para a discuss&#227;o &#233;tica que ocorrer&#225;, tendo em vista que sempre h&#225; pelo menos um ser humano respons&#225;vel pelo voo mesmo com uso dos modernos dispositivos da avia&#231;&#227;o comercial. Neste ponto, Obermeyer e Emanuel<xref ref-type="bibr" rid="B2">2</xref> chamam a aten&#231;&#227;o para o fato de que haver&#225; uma redu&#231;&#227;o maci&#231;a da necessidade de m&#233;dicos em situa&#231;&#245;es em que os computadores poder&#227;o ser alimentados diretamente por informa&#231;&#245;es digitais como na radiologia e na patologia, pois a grande quantidade de informa&#231;&#245;es digitais dispon&#237;veis permitir&#225; a forma&#231;&#227;o de bancos de dados confi&#225;veis que levar&#227;o a uma performance das m&#225;quinas superior &#224; humana.</p>
      <p>Quando a intelig&#234;ncia artificial &#233; empregada em contextos cl&#237;nicos mais complexos ainda h&#225; um caminho mais longo a ser percorrido. Austin et al.<xref ref-type="bibr" rid="B6">6</xref> utilizaram um sistema de Machine-Learning e de minera&#231;&#227;o de dados para avaliar e classificar pacientes com insufici&#234;ncia card&#237;aca e encontraram que apesar do sistema ser superior aos m&#233;todos convencionais para predi&#231;&#227;o de insufici&#234;ncia card&#237;aca com fra&#231;&#227;o de eje&#231;&#227;o preservada, n&#227;o houve vantagens em rela&#231;&#227;o &#224; tradicional regress&#227;o log&#237;stica. Liu et al.<xref ref-type="bibr" rid="B7">7</xref> desenvolveram um sistema de predi&#231;&#227;o de eventos adversos coronarianos em pacientes com dor tor&#225;cica na sala de emerg&#234;ncia baseado em Machine Learning e o compararam com o TIMI escore. Embora a performance do novo sistema seja confi&#225;vel para predi&#231;&#227;o de mortalidade e de eventos card&#237;acos em 30 dias, os pr&#243;prios autores reconhecem que as decis&#245;es cl&#237;nicas s&#227;o dependentes de fatores que ainda n&#227;o podem ser completamente incorporados &#224;s m&#225;quinas, sendo um deles a experi&#234;ncia dos m&#233;dicos.<xref ref-type="bibr" rid="B7">7</xref>
			</p>
      <p>Em cardiologia nuclear Arsanjani et al.<xref ref-type="bibr" rid="B8">8</xref> avaliaram o uso da ferramenta de Machine Learning para predi&#231;&#227;o de revasculariza&#231;&#227;o mioc&#225;rdica a partir de dados da cintilografia de perfus&#227;o mioc&#225;rdica, encontrando uma acur&#225;cica compar&#225;vel ou mesmo superior &#224; de examinadores experientes na interpreta&#231;&#227;o do exame cintilogr&#225;fico. Garcia et al.,<xref ref-type="bibr" rid="B9">9</xref> em excelente revis&#227;o sobre o tema apontam que os sistemas de suporte &#224; decis&#227;o cl&#237;nica e de intelig&#234;ncia artificial servem como alertas para os vieses cognitivos dos cl&#237;nicos e reduzem a variabilidade intra e interobservador, permitindo interpretar os exames mais rapidamente e com maior acur&#225;cia, como observado em estudos em que a interpreta&#231;&#227;o diagn&#243;stica do exame pelo computador &#233; similar &#224; dos experts.<xref ref-type="bibr" rid="B10">10</xref> De um modo geral concordamos com esta vis&#227;o e consideramos que o amparo &#224; tomada de decis&#227;o cl&#237;nica e melhoria da performance diagn&#243;stica e progn&#243;stica devem ser encorajados e suportados pelos m&#233;dicos das diversas especialidades. A preocupa&#231;&#227;o frequente com a eventual substitui&#231;&#227;o definitiva do m&#233;dico pelas m&#225;quinas n&#227;o &#233; consubstanciada pelos fatos. A profiss&#227;o m&#233;dica &#233; de uma complexidade e subjetividade que tornam a tarefa imposs&#237;vel de ser realizada na sua totalidade pelas m&#225;quinas, pelo menos no est&#225;gio atual do conhecimento. A utiliza&#231;&#227;o adequada da computa&#231;&#227;o permite n&#227;o s&#243; a melhoria da performance m&#233;dica mas tamb&#233;m a busca da solidariedade entre pacientes, com experi&#234;ncias bem sucedidas na cria&#231;&#227;o de redes sociais para pacientes.<xref ref-type="bibr" rid="B11">11</xref>
			</p>
      <p>Apenas o estudo do impacto aprofundado para desenvolvimento e utiliza&#231;&#227;o destas ferramentas poder&#225; trazer as respostas para as perguntas que hoje est&#227;o nas mentes dos m&#233;dicos e dos seus pacientes. <italic>O International Journal of Cardiovascular Sciences</italic> estimula seus leitores e contribuintes a enviar comunica&#231;&#245;es cient&#237;ficas sobre o tema para publica&#231;&#227;o</p>
    </body>
  </sub-article>
</article>
