<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">russjcardiol</journal-id><journal-title-group><journal-title xml:lang="ru">Российский кардиологический журнал</journal-title><trans-title-group xml:lang="en"><trans-title>Russian Journal of Cardiology</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1560-4071</issn><issn pub-type="epub">2618-7620</issn><publisher><publisher-name>«SILICEA-POLIGRAF» LLC</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.15829/10.15829/1560-4071-2026-6885</article-id><article-id custom-type="edn" pub-id-type="custom">PFQTXI</article-id><article-id custom-type="elpub" pub-id-type="custom">russjcardiol-6885</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МАШИННОЕ ОБУЧЕНИЕ В КЛИНИЧЕСКОЙ ПРАКТИКЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MACHINE LEARNING IN CLINICAL PRACTICE</subject></subj-group></article-categories><title-group><article-title>Ансамблевые машинные предикторы: новый подход к оценке риска госпитальной летальности у пациентов с острым коронарным синдромом</article-title><trans-title-group xml:lang="en"><trans-title>Ensemble machine learning predictors: a novel approach to assessing the risk of inhospital mortality in patients with acute coronary syndrome</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Торопов</surname><given-names>В. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Toropov</surname><given-names>V. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Василий Николаевич Торопов — магистрант, практикант научно-исследовательской лаборатории "Трансляционная биоинформатика и системная биология" медицинского института</p><p>Октябрьский проспект, д. 55, Сыктывкар, 167001</p></bio><bio xml:lang="en"><p>Oktyabrsky ave., 55, Syktyvkar, 167001</p></bio><email xlink:type="simple">vasily.toropov1@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-0019-0820</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Богомолов</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Bogomolov</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Андрей Николаевич Богомолов — к.м.н., с.н.с. лаборатории возрастной патологии сердечно-сосудистой системы, АННО ВО НИЦ Санкт-Петербургский институт биорегуляции и геронтологии; врач эндоваскулярный хирург, СПб ГБУЗ Александровская больница</p><p>пр. Солидарности, д. 4, Санкт-Петербург, 193312; пр. Динамо, д. 3, Санкт-Петербург, 197110</p></bio><bio xml:lang="en"><p>Solidarity ave., 4, St. Petersburg, 193312; Dynamo ave., 3, St. Petersburg, 197110</p></bio><email xlink:type="simple">endovsurg@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1595-7692</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Курочкина</surname><given-names>О. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Kurochkina</surname><given-names>O. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ольга Николаевна Курочкина — д.м.н., зав. кафедрой терапии медицинского института, ФГБОУ ВО Сыктывкарский государственный университет им. Питирима Сорокина; зав. научным отделом, ГУ РК Клинический кардиологический диспансер</p><p>Октябрьский проспект, д. 55, Сыктывкар, 167001; ул. Маркова, д. 1, Сыктывкар, 167981</p></bio><bio xml:lang="en"><p>Oktyabrsky ave., 55, Syktyvkar, 167001; Markova str., 1, Syktyvkar, 167981</p></bio><email xlink:type="simple">olga_kgma@mail.ru</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ветошкин</surname><given-names>Р. Е.</given-names></name><name name-style="western" xml:lang="en"><surname>Vetoshkin</surname><given-names>R. E.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Роман Евгеньевич Ветошкин — инженер научно-исследовательской лаборатории "Трансляционная биоинформатика и системная биология" медицинского института</p><p>Октябрьский проспект, д. 55, Сыктывкар, 167001</p></bio><bio xml:lang="en"><p>Oktyabrsky ave., 55, Syktyvkar, 167001</p></bio><email xlink:type="simple">myatataa@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1038-2271</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Соловьёв</surname><given-names>И. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Solovyov</surname><given-names>I. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Илья Андреевич Соловьёв — к.б.н., с.н.с. (заведующий) научноисследовательской лаборатории "Трансляционная биоинформатика и системная биология" медицинского института </p><p>Октябрьский проспект, д. 55, Сыктывкар, 167001</p></bio><bio xml:lang="en"><p>Oktyabrsky ave., 55, Syktyvkar, 167001</p></bio><email xlink:type="simple">i@ilyasolovev.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГБОУ ВО Сыктывкарский государственный университет им. Питирима Сорокина</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Pitirim Sorokin Syktyvkar State University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>СПб ГБУЗ Александровская больница; &#13;
АННО ВО НИЦ Санкт-Петербургский институт биорегуляции и геронтологии</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Alexandrovskaya Hospital; &#13;
St. Petersburg Institute of Bioregulation and Gerontology</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ФГБОУ ВО Сыктывкарский государственный университет им. Питирима Сорокина; &#13;
ГУ РК Клинический кардиологический диспансер</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Pitirim Sorokin Syktyvkar State University; &#13;
Clinical Cardiology Dispensary</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>22</day><month>04</month><year>2026</year></pub-date><volume>31</volume><issue>2S</issue><issue-title>Искусственный интеллект в медицине</issue-title><fpage>6885</fpage><lpage>6885</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Торопов В.Н., Богомолов А.Н., Курочкина О.Н., Ветошкин Р.Е., Соловьёв И.А., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Торопов В.Н., Богомолов А.Н., Курочкина О.Н., Ветошкин Р.Е., Соловьёв И.А.</copyright-holder><copyright-holder xml:lang="en">Toropov V.N., Bogomolov A.N., Kurochkina O.N., Vetoshkin R.E., Solovyov I.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://russjcardiol.elpub.ru/jour/article/view/6885">https://russjcardiol.elpub.ru/jour/article/view/6885</self-uri><abstract><sec><title>Цель</title><p>Цель. Оценить эффективность современных ансамблевых моделей машинного обучения (МО) в прогнозировании госпитальной летальности у пациентов с острым коронарным синдромом (ОКС) в сравнении с традиционной клинической шкалой GRACE.</p></sec><sec><title>Материал и методы</title><p>Материал и методы. В ретроспективное исследование включены анонимизированные данные 14420 пациентов с ОКС, госпитализированных в кардиологический стационар. Для каждого клинического случая анализировалось 28 предикторов. На основе этих данных обучены алгоритмы МО: логистическая регрессия, деревья решений, случайный лес (Random Forest), градиентный бустинг (XGBoost, CatBoost). Для оценки качества моделей использовались площадь под ROC-кривой (AUC-ROC), полнота (Recall) и F1-мера. Результаты лучшей модели сопоставлялись с оценкой риска по шкале GRACE. Для интерпретации логики алгоритма применялся SHAP-анализ.</p></sec><sec><title>Результаты</title><p>Результаты. Госпитальная летальность составила 6,03% (804 пациента). Алгоритмы на основе градиентного бустинга продемонстрировали наилучшую предсказательную способность. Лидером стала модель CatBoost, показавшая значение AUC-ROC 0,961, статистически значимо превзойдя шкалу GRACE (AUCROC 0,919) на тестовой выборке. SHAP-анализ выявил, что наибольший вклад в прогноз модели вносят: наличие дислипидемии в анамнезе, фракция выброса левого желудочка, класс острой сердечной недостаточности по Killip, возраст и уровень систолического артериального давления. Модель успешно выявила скрытые нелинейные клинические паттерны, включая парадоксальный защитный эффект диагностированной ранее дислипидемии и критическую прогностическую значимость отсутствия анамнестических данных при поступлении.</p></sec><sec><title>Заключение</title><p>Заключение. Методы МО, в частности алгоритм CatBoost, обеспечивают более высокую точность прогнозирования госпитальной летальности при ОКС по сравнению с классическими шкалами. Способность алгоритмов учитывать сложные нелинейные взаимосвязи между клиническими показателями делает их перспективной основой для создания точных систем поддержки принятия врачебных решений.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Aim</title><p>Aim. To evaluate the effectiveness of modern ensemble machine learning (ML) models in predicting in-hospital mortality in patients with acute coronary syndrome (ACS) compared to the traditional GRACE clinical score.</p></sec><sec><title>Material and methods</title><p>Material and methods. This retrospective study included anonymized data from 14420 patients with ACS admitted to a cardiology hospital. For each case, 28 predictors were analyzed. Following machine learning algorithms were trained using this data: logistic regression, decision trees, random forest, and gradient boosting (XGBoost, CatBoost). The area under the receiver operating characteristic (AUC-ROC), recall, and F1 score were used to assess the model quality. The results of the best model were compared with the GRACE risk score. SHAP analysis was used to interpret the algorithm logic.</p></sec><sec><title>Results</title><p>Results. Inhospital mortality was 6,03% (n=804). Gradient boosting algorithms demonstrated the highest predictive capability. The CatBoost model emerged as the top performer, achieving an AUC-ROC of 0,961, significantly outperforming the GRACE score (AUC-ROC 0,919) on the test set. SHAP analysis revealed that the greatest contributors to the model’s prediction were history of dyslipidemia, left ventricular ejection fraction, Killip class of acute heart failure, age, and systolic blood pressure levels. The model successfully identified hidden nonlinear clinical patterns, including the paradoxical protective effect of previously diagnosed dyslipidemia and the critical prognostic significance of missing medical history data upon admission.</p></sec><sec><title>Conclusion</title><p>Conclusion. ML methods, particularly the CatBoost algorithm, provide higher accuracy in predicting in-hospital mortality in ACS compared to conventional scores. The ability of these algorithms to account for complex nonlinear relationships between clinical indicators makes them a promising foundation for developing accurate clinical decision support systems.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>острый коронарный синдром</kwd><kwd>машинное обучение</kwd><kwd>прогнозирование</kwd><kwd>госпитальная летальность</kwd><kwd>шкала GRACE</kwd><kwd>стратификация риска</kwd><kwd>CatBoost</kwd><kwd>SHAP</kwd><kwd>искусственный интеллект</kwd></kwd-group><kwd-group xml:lang="en"><kwd>acute coronary syndrome</kwd><kwd>machine learning</kwd><kwd>prediction</kwd><kwd>inhospital mortality</kwd><kwd>GRACE score</kwd><kwd>risk stratification</kwd><kwd>CatBoost</kwd><kwd>SHAP</kwd><kwd>artificial intelligence</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Bhatt DL, Lopes RD, Harrington RA. Diagnosis and treatment of acute coronary syndromes: a review. JAMA. 2022;327(7):662-75. doi:10.1001/jama.2022.0358.</mixed-citation><mixed-citation xml:lang="en">Bhatt DL, Lopes RD, Harrington RA. Diagnosis and treatment of acute coronary syndromes: a review. JAMA. 2022;327(7):662-75. doi:10.1001/jama.2022.0358.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Fox KAA, Dabbous OH, Goldberg RJ, et al. Predictors of hospital mortality in the global registry of acute coronary events. Arch Intern Med. 2003;163(23):2345-53. doi:10.1001/archinte.163.19.2345.</mixed-citation><mixed-citation xml:lang="en">Fox KAA, Dabbous OH, Goldberg RJ, et al. Predictors of hospital mortality in the global registry of acute coronary events. Arch Intern Med. 2003;163(23):2345-53. doi:10.1001/archinte.163.19.2345.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Deo RC. Machine learning in medicine. Circulation. 2015;132(20):1920-30. doi:10.1161/CIRCULATIONAHA.115.001593.</mixed-citation><mixed-citation xml:lang="en">Deo RC. Machine learning in medicine. Circulation. 2015;132(20):1920-30. doi:10.1161/CIRCULATIONAHA.115.001593.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Arfat Y, Mittone G, Esposito R, et al. Machine learning for cardiology. Minerva Cardiol Angiol. 2022;70(1):75-91. doi:10.23736/S2724-5683.21.05709-4.</mixed-citation><mixed-citation xml:lang="en">Arfat Y, Mittone G, Esposito R, et al. Machine learning for cardiology. Minerva Cardiol Angiol. 2022;70(1):75-91. doi:10.23736/S2724-5683.21.05709-4.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">D’Ascenzo F, De Filippo O, Gallone G, et al. Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets. The Lancet. 2021;397(10270):199-207. doi:10.1016/S0140-6736(20)32519-8.</mixed-citation><mixed-citation xml:lang="en">D’Ascenzo F, De Filippo O, Gallone G, et al. Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets. The Lancet. 2021;397(10270):199-207. doi:10.1016/S0140-6736(20)32519-8.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang X, Wang X, Xu L, et al. The predictive value of machine learning for mortality risk in patients with acute coronary syndromes: a systematic review and meta-analysis. Eur J Med Res. 2023;28(1):451. doi:10.1186/s40001-023-01027-4.</mixed-citation><mixed-citation xml:lang="en">Zhang X, Wang X, Xu L, et al. The predictive value of machine learning for mortality risk in patients with acute coronary syndromes: a systematic review and meta-analysis. Eur J Med Res. 2023;28(1):451. doi:10.1186/s40001-023-01027-4.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Emakhu J, Monplaisir L, Aguwa C, et al. Acute coronary syndrome prediction in emergency care: A machine learning approach. Comput Methods Programs Biomed. 2022;225:107080. doi:10.1016/j.cmpb.2022.107080.</mixed-citation><mixed-citation xml:lang="en">Emakhu J, Monplaisir L, Aguwa C, et al. Acute coronary syndrome prediction in emergency care: A machine learning approach. Comput Methods Programs Biomed. 2022;225:107080. doi:10.1016/j.cmpb.2022.107080.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Chopannejad S, Sadoughi F, Bagherzadeh R, Shekarchi S. Predicting Major Adverse Cardiovascular Events in Acute Coronary Syndrome: A Scoping Review of Machine Learning Approaches. Appl Clin Inform. 2022;13(3):720-40. doi:10.1055/a-1863-1589.</mixed-citation><mixed-citation xml:lang="en">Chopannejad S, Sadoughi F, Bagherzadeh R, Shekarchi S. Predicting Major Adverse Cardiovascular Events in Acute Coronary Syndrome: A Scoping Review of Machine Learning Approaches. Appl Clin Inform. 2022;13(3):720-40. doi:10.1055/a-1863-1589.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Khera R, Haimovich J, Hurley NC, et al. Use of machine learning models to predict death after acute myocardial infarction. JAMA Cardiol. 2021;6(6):633-41. doi:10.1001/jamacardio.2021.0122.</mixed-citation><mixed-citation xml:lang="en">Khera R, Haimovich J, Hurley NC, et al. Use of machine learning models to predict death after acute myocardial infarction. JAMA Cardiol. 2021;6(6):633-41. doi:10.1001/jamacardio.2021.0122.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Prokhorenkova L, Gusev G, Vorobev A, et al. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst. 2018;31:6638-48.</mixed-citation><mixed-citation xml:lang="en">Prokhorenkova L, Gusev G, Vorobev A, et al. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst. 2018;31:6638-48.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765-74. doi:10.48550/arXiv.1705.07874.</mixed-citation><mixed-citation xml:lang="en">Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765-74. doi:10.48550/arXiv.1705.07874.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Cho SM, Austin PC, Ross HJ, et al. Machine learning compared with conventional statistical models for predicting myocardial infarction readmission and mortality: a systematic review. Can J Cardiol. 2021;37(8):1207-14. doi:10.1016/j.cjca.2021.02.020.</mixed-citation><mixed-citation xml:lang="en">Cho SM, Austin PC, Ross HJ, et al. Machine learning compared with conventional statistical models for predicting myocardial infarction readmission and mortality: a systematic review. Can J Cardiol. 2021;37(8):1207-14. doi:10.1016/j.cjca.2021.02.020.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Jian R, Zhang J, Zeng Y, et al. In-hospital mortality risk prediction models for patients with acute coronary syndrome: a systematic review and meta-analysis. Frontiers in Cardiovascular Medicine. 2025;3(12):1659184. doi:10.3389/fcvm.2025.1659184.</mixed-citation><mixed-citation xml:lang="en">Jian R, Zhang J, Zeng Y, et al. In-hospital mortality risk prediction models for patients with acute coronary syndrome: a systematic review and meta-analysis. Frontiers in Cardiovascular Medicine. 2025;3(12):1659184. doi:10.3389/fcvm.2025.1659184.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Wu TT, Lin XQ, Mu Y, et al. Machine learning for early prediction of in-hospital cardiac arrest in patients with acute coronary syndromes. Clin Cardiol. 2021;44(3):349-56. doi:10.1002/clc.23541.</mixed-citation><mixed-citation xml:lang="en">Wu TT, Lin XQ, Mu Y, et al. Machine learning for early prediction of in-hospital cardiac arrest in patients with acute coronary syndromes. Clin Cardiol. 2021;44(3):349-56. doi:10.1002/clc.23541.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Соловьёв И. А., Курочкина О. Н. Приложения искусственного интеллекта в кардиологии: обзор. Российский кардиологический журнал. 2024;29(11S):5673. doi:10.15829/1560-40712024-5673.</mixed-citation><mixed-citation xml:lang="en">Soloviev IA, Kurochkina ON. Artificial intelligence applications in cardiology: a review. Russian Journal of Cardiology. 2024;29(11S):5673. (In Russ.) doi:10.15829/1560-40712024-5673.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
