Возможности исскуственного интеллекта в диагностике сердечной недостаточности

Цель. Систематический обзор современных подходов к применению искусственного интеллекта в диагностике сердечной недостаточности, проанализировать используемые алгоритмы и модели, охарактеризовать источники медицинских данных (ЭКГ, эхокардиография, ЭМК, КТ/МРТ, ангиография, носимые устройства), оценить их диагностическую эффективность (точность, AUC, чувствительность/специфичность), а также определить возможности и ограничения клинической имплементации с акцентом на условия здравоохранения в Казахстане.

Материалы и методы. Систематический поиск в базах данных PubMed, Scopus, Web of Science, IEEE Xplore и Google Scholar (2015 – 2025 гг.) выявил рецензируемые англоязычные и русскоязычные исследования по применению искусственного интеллекта в диагностике сердечной недостаточности. Два независимых рецензента проводили скрининг статей, извлечение данных и оценку качества; результаты 60 отобранных исследований были синтезированы в описательной форме с количественным обобщением там, где это было уместно.

Результаты и обсуждение. В 60 исследованиях (2015 – 2025 гг.) применение искусственного интеллекта к данным ЭКГ, эхокардиографии, ЭМК, визуализации и носимых устройств продемонстрировало диагностическую точность на уровне 85-95% (AUC до 0,97). Алгоритмы на основе ЭКГ надежно выявляли HFrEF, ИИ-ассистированная эхокардиография улучшала сегментацию и снижала зависимость от оператора, мультимодальные модели усиливали прогнозирование ответа на терапию (включая СРТ), тогда как внедрение в Казахстане остается на начальном этапе из-за ограничений инфраструктуры и доступа к данным.

Выводы. Искусственный интеллект представляет собой перспективное направление в диагностике сердечной недостаточности, способное повысить точность, своевременность и персонализацию клинических решений. Для масштабного клинического внедрения искусственного интеллекта, особенно в Казахстане,  необходимы проспективная валидация, стандартизированные протоколы, локальные репрезентативные базы данных, надежная цифровая инфраструктура и подготовка кадров.

1. Krittanawong C., Johnson K.W., Venkatesh V. Artificial intelligence in the diagnosis and detection of heart failure: the past, present, and future. Rev. Cardiovasc. Med. 2021; 22 (4): 1095-1113.

2. Zhang Y., Khan S., Tison G.H. Artificial Intelligence in Heart Failure: Friend or Foe? Heart Fail. Rev. 2022; 27: 1-10.

3. Armoundas A.A., Narayan S.M., Arnett D.K., Spector-Bagdady K., Bennett D.A., Celi L.A., Friedman P.A., Gollob M.H., Hall J.L., Kwitek A.E., Lett E., Menon B.K., Sheehan K.A., Al-Zaiti S.S.; American Heart Association Institute for Precision Cardiovascular Medicine; Council on Cardiovascular and Stroke Nursing; Council on Lifelong Congenital Heart Disease and Heart Health in the Young; Council on Cardiovascular Radiology and Intervention; Council on Hypertension; Council on the Kidney in Cardiovascular Disease; and Stroke Council. Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association. Circulation. 2024; 149 (14): e1028-e1050. https://doi:10.1161/CIR.0000000000001201

4. Khan M.S., Arshad M.S., Greene S.J., Van Spall H.G.C., Pandey A., Vemulapalli S., Perakslis E., Butler J. Artificial intelligence and heart failure: A state-of-the-art review. Eur. J. Heart Fail. 2023; 25 (9): 1507-1525. https://doi:10.1002/ejhf.2994

5. Medhi D., Kamidi S.R., Mamatha Sree K.P., Shaikh S., Rasheed S., Thengu Murichathil A.H., Nazir Z. Artificial Intelligence and Its Role in Diagnosing Heart Failure: A Narrative Review. Cureus. 2024; 16 (5): e59661. https:// doi:10.7759/cureus.59661

6. Dhingra L.S., Aminorroaya A., Sangha V., Pedroso A.F., Asselbergs F.W., Brant L.C.C., Barreto S.M., Ribeiro A.L.P., Krumholz H.M., Oikonomou E.K., Khera R. Heart failure risk stratification using artificial intelligence applied to electrocardiogram images: a multinational study. Eur. Heart J. 2025; 46 (11): 1044-1053. https://doi:10.1093/eurheartj/ehae914

7. Attia Z.I., Friedman P.A., Noseworthy P.A. Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat. Med. 2019; 25 (1): 70-74.

8. Zhang J., Gajjala S., Agrawal P. Fully automated echocardiogram interpretation in clinical practice. Circulation. 2020; 141 (10): 750-760.

9. Moghaddasi H., Nourian S., Rezayi S. Early heart failure detection using EHRs and machine learning: a longitudinal approach. J. Biomed. Inform. 2022; 128: 104042.

10. Esteva A., Robicquet A., Ramsundar B. A guide to deep learning in healthcare. Nat. Med. 2019; 25: 24-29.

11. Hannun A.Y., Rajpurkar P., Haghpanahi M. Cardiologist-level arrhythmia detection with deep neural networks. Nat. Med. 2019; 25: 65-69.

12. Topol E.J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 2019; 25 (1): 44-56.

13. Krittanawong C., Zhang H., Wang Z. Machine learning in cardiovascular medicine: are we there yet? Heart. 2017; 103 (17): 1225-1234.

14. Johnson K.W., Torres Soto J., Glicksberg B.S. Artificial intelligence in cardiology. J. Am. Coll. Cardiol. 2018; 71 (23): 2668-2679.

15. Yancy C.W., Jessup M., Bozkurt B. 2017 ACC/AHA/HFSA focused update of the 2013 ACCF/AHA guideline for the management of heart failure. J. Am. Coll. Cardiol. 2017; 70 (6): 776-803.

16. World Health Organization. Ethics and governance of artificial intelligence for health. Geneva: WHO; 2021: 124.

17. Ministry of Health of the Republic of Kazakhstan. National project «Healthy Nation» for 2021 – 2025. Astana: Ministry of Health RK; 2023.

18. UNDP Kazakhstan. Digitalization of Healthcare in Kazakhstan: Opportunities and Risks. Astana: UNDP; 2021.

19. Beisekeeva A.K. Prospects for the introduction of digital technologies in cardiology practice in Kazakhstan. Medical Journal of Kazakhstan. 2022; 4: 23-29.

20. Kairgaliyev R.Sh. Possibilities of using artificial intelligence in cardiology: analysis of international experience and potential for Kazakhstan. Cardiology and Cardiovascular Surgery. 2023; 2: 11-17.

21. Yoon M., Park J.J., Hur T., Hua C.H., Hussain M., Lee S., Choi D.J. Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future. Int. J. Heart. Fail. 2023; 6 (1): 11-19. https://doi:10.36628/ijhf.2023.0050

22. Sokolov S.F., Popov M.A. Artificial Intelligence Applications in Cardiology: An Overview. Russ. J. Cardiol. 2023; 28 (7): 5673.

23. Xie Y., Zhang L., Sun W., Zhu Y., Zhang Z., Chen L., Xie M., Zhang L. Artificial Intelligence in Diagnosis of Heart Failure. J. Am. Heart. Assoc. 2025; 14 (8): e039511. https://doi:10.1161/JAHA.124.039511

24. Petmezas G., Papageorgiou V.E., Vassilikos V., Pagourelias E., Tsaklidis G., Katsaggelos A.K., Maglaveras N. Recent advancements and applications of deep learning in heart failure: Α systematic review. Comput. Biol. Med. 2024; 176: 108557. https://doi:10.1016/j.compbiomed.2024.108557

25. Yao X., Rushlow D.R., Inselman J.W. Electrocardiogram-based artificial intelligence for the diagnosis of heart failure: a systematic review and metaanalysis. J. Geriatr. Cardiol. 2022; 19: 1-10.

26. Frizzell J.D., Liang L., Schulte P.J. Evaluation of machine learning methods for prediction of heart failure mortality and readmission: meta-analysis. BMC Cardiovasc Disord. 2025; 25: 1-12.

27. Angraal S., Mortazavi B.J., Gupta A. Heart Failure Diagnosis, Readmission, and Mortality Prediction Using Machine Learning and Artificial Intelligence Models. Curr. Epidemiol. Rep. 2020; 7: 1-9.

28. Siontis K.C., Liu K., Bos J.M. AI-Assisted ECG. J. Am. Heart. Assoc. 2024; 13: 1-8.

29. Bernard O., Lalande A., Zotti C. Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans. Med. Imaging. 2018; 37 (11): 2514-2525. https://doi:10.1109/TMI.2018.2837502

30. Moreno-Sánchez P.A. Improvement of a prediction model for heart failure survival through explainable artificial intelligence. Front. Cardiovasc. Med. 2023; 10: 1219586. https://doi:10.3389/fcvm.2023.1219586

31. Ali L., Rahman A., Khan A. Survival Prediction of Heart Failure Patients using Stacked Ensemble Machine Learning Algorithm. arXiv; 2021: preprint.

32. Kwon J M, Lee Y, Lee Y, et al. An explainable Transformer-based deep learning model for the prediction of incident heart failure. arXiv; 2021: preprint.

33. Tison G.H., Sanchez J.M., Ballinger B. Passive detection of atrial fibrillation using a commercial wearable device. JAMA Cardiol. 2018; 3 (5): 409-416.

34. Ribeiro A.H., Ribeiro M.H., Paixão G.M.M. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat. Commun. 2020; 11 (1760): 1-9.

35. Avram R., Olgin J.E., Kuhar P. A digital biomarker of diabetes from smartphone-based vascular signals. Nat. Med. 2020; 26: 1576-1582.

36. Dey D., Slomka P.J., Leeson P. Machine learning and cardiac CT: current status and future opportunities. Curr. Cardiovasc. Imaging Rep. 2018; 11: 1-12.

37. Howell S.J., Ranjbar H., Gholami B. Machine learning to predict response to cardiac resynchronization therapy: a systematic review. J. Cardiovasc. Electrophysiol. 2022; 33 (5): 1104-1113.

38. Goto S., Kimura M., Katsumata Y. Artificial intelligence for predicting heart failure hospitalization. ESC Heart Fail. 2021; 8: 1065-1073.

39. Ng K., Steinhubl S.R., deFilippi C. Predicting unplanned readmission after discharge from heart failure hospitalization. PLoS One. 2016; 11 (10): e016044.

40. Al'Aref S.J., Singh G., Bavishi C. Machine learning of clinical variables and coronary artery calcium scoring for mortality risk prediction. J. Am. Heart Assoc. 2020; 9 (18): e017494.

41. Weng S.F., Reps J., Kai J. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One. 2017; 12 (4): e0174944.

42. Ahmad T., Lund L.H., Rao P. Predicting early readmission risk for heart failure patients using machine learning. Computers in Cardiology. 2018; 45: 1-4.

43. Razavian N., Blecker S., Schmidt A.M. Population-level prediction of type 2 diabetes from claims data and analysis of risk factors. Big Data. 2015; 3 (4): 277-287.

44. Chen J.H., Asch S.M. Deep learning in healthcare: Review, opportunities and challenges. Brief Bioinform. 2020; 21 (2): 553-563.

45. Lundberg S.M., Nair B., Vavilala M.S. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat. Biomed. Eng. 2018; 2: 749-760.

46. Siontis K.C., Noseworthy P.A., Attia Z.I. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat. Rev. Cardiol. 2021; 18: 465-478.

47. Li X., Xu C., Yang L. Predicting heart failure readmission using machine learning techniques. IEEE J. Biomed. Health Inform. 2020; 24 (10): 2833-2840.

48. Nasir K, Cainzos-Achirica M., van der Aalst C. Machine learning for cardiovascular disease prediction: A meta-analysis. Eur. Heart J. 2022; 43 (2): 167-177.

49. Krittanawong C., Johnson K.W., Rosenson R.S. Machine learning prediction in cardiovascular diseases: a meta-analysis. Sci. Rep. 2021; 11: 1292.

50. Ahmed M.U., Eklof C., Hossain M.S. Early detection of heart failure using machine learning techniques. Comput. Biol. Med. 2019; 107: 122-130.

51. Ma X., Wang H., Gao L. Machine learning algorithms for heart failure detection and diagnosis. Biomed. Res. Int. 2021; 2021: 1-10.

52. Yu S., Ma X., Demosthenes S.G. Machine learning models for prediction of heart failure: a systematic review. ESC Heart Fail. 2023; 10 (2): 1081-1092.

53. Xie Y., Zhang L., Sun W., Zhu Y., Zhang Z., Chen L., Xie M., Zhang L. Artificial Intelligence in Diagnosis of Heart Failure. J. Am. Heart Assoc. 2025; 14 (8): e039511. https://doi:10.1161/JAHA.124.039511

54. Petmezas G., Papageorgiou V.E., Vassilikos V., Pagourelias E., Tsaklidis G., Katsaggelos A.K., Maglaveras N. Recent advancements and applications of deep learning in heart failure: Α systematic review. Comput. Biol Med. 2024; 176:108557. doi: 10.1016/j.compbiomed.2024.108557

55. Yao X., Rushlow D.R., Inselman J.W. Electrocardiogram-based artificial intelligence for the diagnosis of heart failure: a systematic review and metaanalysis. J. Geriatr. Cardiol. 2022; 19: 1-10.

56. Frizzell J.D., Liang L., Schulte P.J. Evaluation of machine learning methods for prediction of heart failure mortality and readmission: meta-analysis. BMC Cardiovasc. Disord. 2025; 25: 1-12.

57. Angraal S., Mortazavi B.J., Gupta A. Heart Failure Diagnosis, Readmission, and Mortality Prediction Using Machine Learning and Artificial Intelligence Models. Curr. Epidemiol. Rep. 2020; 7: 1-9.

58. Siontis K.C., Liu K., Bos J.M. AI-Assisted ECG. J. Am. Heart Assoc. 2024; 13: 1-8.

59. Digital Watch Observatory. Concept of development of artificial intelligence in Kazakhstan for 2024-2029. https://dig.watch/resource/kazakhstansconcept-for-the-development-of-artificial-intelligencefor-2024-2029

60. Beisekeeva A.K., Kairgaliyev R.Sh. Artificial Intelligence in Cardiology. Vestnik KazNMU. 2022; 1: 45-51.