Гибридная интеллектуальная система стратификации риска ишемической болезни сердца

Интеллектуальные системы и технологии, искусственный интеллект
Авторы:
Кудаева Ф.Х.Бицуев Т.М.
Аннотация:

В статье предложена гибридная интеллектуальная система для стратификации риска ишемической болезни сердца (ИБС), которая объединяет ансамблевое прогнозирование, обработку естественного языка и технологии объяснимого ИИ. Показано, что интеграция структурированных клинических признаков и неструктурированных текстовых данных повышает точность оценки риска ИБС по сравнению с традиционными шкалами SCORE2. На тестовых выборках достигнуты высокие значения метрик качества AUC-ROC и F1-score, при этом интерпретируемость прогнозов обеспечивается построением диаграмм типа «водопад» (waterfall plots), отражающих вклад ключевых факторов риска. Разработанный программный комплекс найдет применение в кардиологии для поддержки принятия врачебных решений.

Ключевые слова:
гибридная интеллектуальная системаансамблевое машинное обучениепрогнозирование сердечно-сосудистых исходовобработка естественного языкаискусственный интеллектSHAP-анализподдержка принятия врачебных решений
  • Список литературы

    1. Zhang P.-I., Hsu C.-C., Kao Y. et al. Real-time AI prediction for major adverse cardiac events in emergency department patients with chest pain. Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine, 2020, Vol. 28, Article no. 93. DOI: 10.1186/s13049-020-00786-x

    2. Olsson de Capretz P., Björkelund A., Björk J., Ohlsson M., Mokhtari A., Nyström A., Ekelund U. Machine learning for early prediction of acute myocardial infarction or death in acute chest pain patients using electrocardiogram and blood tests at presentation. BMC Medical Informatics and Decision Making, 2023, Vol. 23, Article no. 25. DOI: 10.1186/s12911-023-02119-1

    3. Liu N., Koh Z.X., Goh J., Lin Z., Haaland B., Ting B.P., Ong M.E.H. Prediction of adverse cardiac events in emergency department patients with chest pain using machine learning for variable selection. BMC Medical Informatics and Decision Making, 2014, Vol. 14, Article no. 75. DOI: 10.1186/1472-6947-14-75

    4. Tolpygina S.N., Martsevich S.Yu. Study of a trend in the frequency of using main drug classes indicated for the treatment of patients with chronic coronary heart disease in 2004 to 2014: data from the CHD prog-nosis registry. The Clinician, 2016, Vol. 10, No. 1, Pp. 29–35. DOI: 10.17650/1818-8338-2016-10-1-29-35

    5. Tolpygina S.N., Martsevich S.Yu. Cardiovascular risk stratification in stable coronary artery disease based on prognostic scores and models. Cardiovascular Therapy and Prevention, 2020, Vol. 19, No. 3, Pp. 240–247. DOI: 10.15829/1728-8800-2020-2528

    6. Tolpygina S.N., Martsevich S.Yu., Deev A.D. Enhanced risk stratification scale for predicting death and non-fatal cardiovascular events in patients of the PROGNOZ IBS registry. Cardiovascular Therapy and Prevention, 2021, Vol. 20, No. 7, Pp. 143–152. DOI: 10.15829/1728-8800-2021-3060

    7. Tolpygina S.N., Martsevich S.Yu., Gofman E.A., Deev A.D. Prognostic value of intstrumental diagnostics in chronic coronary heart disease. Data from “PROGNOS CHD”. Cardiovascular Therapy and Preven-tion, 2014, Vol. 13, No. 4, Pp. 29–35. DOI: 10.15829/1728-8800-2014-4-29-35

    8. Golukhova E.Z., Keren M.A., Zavalikhina T.V., Bulaeva N.I., Akatov D.S., Sigaev I.Yu., Yakhyaeva K.B., Kolesnikov D.A. Potential of machine learning methods in operational risk stratification in patients with coronary artery disease scheduled for coronary bypass surgery. Russian Journal of Cardiology, 2023, ol. 28, No. 2, Article no. 5211. DOI: 10.15829/1560-4071-2023-5211

    9. Motwani M., Dey D., Berman D.S., et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. European Heart Journal, 2017, Vol. 38, No. 7, Pp. 500–507. DOI: 10.1093/eurheartj/ehw188

    10. Kakadiaris I.A., Vrigkas M., Yen A.A., Kuznetsova T., Budoff M., Naghavi M. Machine Learning Outperforms ACC/AHA CVD Risk Calculator in MESA. Journal of the American Heart Association, 2018, Vol. 7, No. 22, Article no. e009476. DOI: 10.1161/JAHA.118.009476

    11. Commandeur F., Slomka P.J., Goeller M., et al. Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: a prospective study. Cardiovascular Research, 2020, Vol. 116, No. 14, P. 2216–2225. DOI: 10.1093/cvr/cvz321

    12. Piepoli M.F., Hoes A.W., Agewall S., et al. 2016 European Guidelines on cardiovascular disease prevention in clinical practice: The Sixth Joint Task Force of the European Society of Cardiology and Other Societies on Cardiovascular Disease Prevention in Clinical Practice (constituted by representatives of 10 societies and by invited experts). Developed with the special contribution of the European Association for Cardiovascular Prevention & Rehabilitation (EACPR). European Heart Journal, 2016, Vol. 37, No. 29, P. 2315–2381. DOI: 10.1093/eurheartj/ehw106

    13. Conroy R.M., Pyörälä K., Fitzgerald A.P., et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. European Heart Journal, 2003, Vol. 24, No. 11, P. 987–1003. DOI: 10.1016/s0195-668x(03)00114-3

    14. SCORE2 working group and ESC Cardiovascular risk collaboration. SCORE2 risk prediction algorithms: new models to estimate 10-year risk of cardiovascular disease in Europe. European Heart Journal, 2021, Vol. 42, No. 25, Pp. 2439–2454. DOI: 10.1093/eurheartj/ehab309

    15. Visseren F.L.J., Mach F., Smulders Y.M., et al. 2021 ESC Guidelines on cardiovascular disease prevention in clinical practice. European Heart Journal, 2021, Vol. 42, No. 34, Pp. 3227–3337. DOI: 10.1093/eurheartj/ehab484

    16. VanHouten J.P., Starmer J.M., Lorenzi N.M., Maron D.J., Lasko T.A. Machine learning for risk pre-diction of acute coronary syndrome. AMIA Annual Symposium Proceedings Archive, 2014, 2014, Pp. 1940–1949.

    17. Topol E.J. High performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 2019, Vol. 25, P. 44–56. DOI: 10.1038/s41591-018-0300-7

    18. Krittanawong C., Zhang H., Wang Z., Aydar M., Kitai T. Artificial intelligence in precision cardiovascular medicine. Journal of the American College of Cardiology (JACC), 2017, Vol. 69, No. 21, Pp. 2657–2664. DOI: 10.1016/j.jacc.2017.03.571

    19. Johnson K.W., Torres Soto J., Glicksberg B.S., Shameer K., Miotto R., Ali M., Ashley E., Dudley J.T. Artificial intelligence in cardiology. Journal of the American College of Cardiology (JACC), 2018, Vol. 71, No. 23, Pp. 2668–2679. DOI: 10.1016/j.jacc.2018.03.521

    20. Lundberg S.M., Lee S.-I. A unified approach to interpreting model predictions. arXiv:1705.07874, 2017. DOI: 10.48550/arXiv.1705.07874

    21. Al’Aref S.J., Anchouche K., Singh G., et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. European Heart Journal, 2019, Vol. 40, No. 24, Pp. 1975–1986. DOI: 10.1093/eurheartj/ehy404

    22. Dey D., Slomka P.J., Leeson P., Comaniciu D., Shrestha S., Sengupta P.P., Marwick T.H. Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. Journal of the American College of Cardiology (JACC), 2019, Vol. 73, No. 11, Pp. 1317–1335. DOI: 10.1016/j.jacc.2018.12.054

    23. Janosi A., Steinbrunn W., Pfisterer M., Detrano R. Heart Disease. UCI Machine Learning Repository, 1989. DOI: 10.24432/C52P4X

    24. Lundberg S.M., Erion G., Chen H., DeGrave A., Prutkin J.M., Nair B., Katz R., Himmelfarb J., Bansal N., Lee S.-I. From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2020, Vol. 2, Pp. 56–67. DOI: 10.1038/s42256-019-0138-9

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Предыдущая статья