Predicting the heart failure course using machine learning: an analysis of international methodological standards and their application in Russian research practice
https://doi.org/10.15829/1728-8800-2026-4736
EDN: BKSJDF
Abstract
The review aim was to develop a machine learning (ML) algorithm adapted to Russian conditions for creating reproducible prediction models of heart failure (HF) course, based on an analysis of international methodological quality standards and a review of existing practices. To this end, the international standards Prediction Model Risk Of Bias Assessment Tool (PROBAST) and Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis — Machine Learning (TRIPOD-ML) were systematized. An extensive search and methodological assessment of Russian studies from 2016-2025, where machine learning was used in patients with HF, were also conducted. The analysis revealed a critical shortage of Russian studies devoted to predicting the HF course. A review of existing studies revealed the following systemic deficiencies: no external validation, data leakage at the feature selection stage, incomplete reporting, and neglect of clinical utility assessment. The causes of these problems are systemic and related to data fragmentation, interdisciplinary gaps, and regulatory gaps. The gap between international standards and Russian practice is not due to technological lag, but to a lack of methodological culture. A step-by-step, practical algorithm is proposed as a solution, focusing on strict data separation, comprehensive validation, transparent reporting, and clinical utility assessment. Implementation of this algorithm will be an important step in the development of evidence-based predictive modeling for HF in Russia.
About the Authors
Yu. V. Burenkov
Burdenko Voronezh State Medical University
Russian Federation
Russian Federation
Yuri V. Burenkov — First-year resident in the specialty "Therapy"
Studencheskaya str., 10, Voronezh, 394036
V. I. Shevcova
Burdenko Voronezh State Medical University
Russian Federation
Russian Federation
Veronica I. Shevcova — Associate Professor, PhD, Associate Professor of the Department of Infectious Diseases and Clinical Immunology
Studencheskaya str., 10, Voronezh, 394036
A. D. Akhyadov
Khimki Clinical Hospital
Russian Federation
Russian Federation
Ahmed D. Akhyadov — Preventive Medical Doctor, State Budgetary Healthcare Institution of the Moscow Region
Kurkinskoe Highway, 11, Khimki, 141407
I. P. Alferova
Burdenko Voronezh State Medical University
Russian Federation
Russian Federation
Irina P. Alferova — 6th-year student, Faculty of Medicine
Studencheskaya str., 10, Voronezh, 394036
References
1. Larina VN, Kokorin VA, Larin VG, et al. Decompensated heart failure: a reconceptualization in the light of updated consensus statement of the European Society of Cardiology. Russian Journal of Cardiology. 2023;28(12):5581. (In Russ.) doi:10.15829/1560-4071-2023-5581.
2. Drapkina OM, Boytsov SA, Omelyanovskiy VV, et al. Socio-economic impact of heart failure in Russia. Russian Journal of Cardiology. 2021;26(6):4490. (In Russ.) doi:10.15829/1560-4071-2021-4490.
3. Larina VN, Skiba IK. Prospects for predicting and preventing the heart failure deterioration: an analytical review. Russian Journal of Cardiology. 2024;29(9):5854. (In Russ.) doi:10.15829/1560-4071-2024-5854.
4. Shin S, Austin PC, Ross HJ, et al. Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality. ESC Heart Fail. 2020;8(1):106-15. doi:10.1002/ehf2.13073.
5. Tohyama T, Ide T, Ikeda M, et al. Machine learning‐based model for predicting 1 year mortality of hospitalized patients with heart failure. ESC Heart Fail. 2021;8(5):4077-85. doi:10.1002/ehf2.13556.
6. Saqib M, Perswani P, Muneem A, et al. Machine learning in heart failure diagnosis, prediction, and prognosis: review. Ann Med Surg (Lond). 2024;86(6):3615-23. doi:10.1097/MS9.0000000000002138.
7. Abreu J, Seringa J, Magalhaes T. Machine learning methods, applications and economic analysis to predict heart failure hospitalisation risk: a scoping review. BMJ Open. 2025;15(6):e093495. doi:10.1136/bmjopen-2024-093495.
8. Mpanya D, Celik T, Klug E, et al. Predicting mortality and hospitalization in heart failure using machine learning: A systematic literature review. Int J Cardiol. Heart Vasc. 2021;34:100773. doi:10.1016/j.ijcha.2021.100773.
9. Wolff RF, Moons KGM, Riley RD, et al. PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies. Ann Intern Med. 2019;170(1):51-8. doi:10.7326/M18-1376.
10. Alnomasy N, Pangket P, Mostoles R, et al. Predictive Performance of Machine Learning Models for Heart Failure Readmission: A Systematic Review. Biomedicines. 2025;13(9):2111. doi:10.3390/biomedicines13092111.
11. Kovelkova MN, Iakovleva EG. Artificial intelligence in the prevention and diagnosis of cardiovascular diseases in Russia (literature review). Siberian Journal of Clinical and Experimental Medicine. 2025;40(1):28-41. (In Russ.) doi:10.29001/2073-8552-2025-40-1-28-41.
12. Yang HS, Rhoads DD, Sepulveda J, et al. Building the Model. Arch Pathol Lab Med. 2023;147(7):826-36. doi:10.5858/arpa.2021-0635-RA.
13. Ignatenko GA, Sedakov IE, Kolycheva OV, et al. Artificial intelligence in cardiovascular diseases: prospects for diagnostics and therapy. Neoplasm. 2023;15(4):10-6. (In Russ.)
14. Shakhgeldyan KI, Kuksin NS, Domzhalov IG, et al. Random forest of risk factors as a predictive tool for adverse events in clinical medicine. Computer Research and Modeling. 2025;17(5):987-1004. (In Russ.) doi:10.20537/2076-7633-2025-17-5-987-1004.
15. Ru B, Tan X, Liu Y, et al. Comparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study. JMIR Form Res. 2023;7:e41775. doi:10.2196/41775.
16. Błaziak M, Urban S, Wietrzyk W, et al. An Artificial Intelligence Approach to Guiding the Management of Heart Failure Patients Using Predictive Models: A Systematic Review. Biomedicines. 2022;10(9):2188. doi:10.3390/biomedicines10092188.
17. Jia Y, Cui N, Jia T, et al. Prognostic models for patients suffering a heart failure with a preserved ejection fraction: a systematic review. ESC Heart Fail. 2024;11(3):1341-51. doi:10.1002/ehf2.14696.
18. Mishkin IA, Kontsevaya AV, Gusev AV, et al. Prediction of cardiovascular events using proportional risk models and machine learning models: a systematic review. Current problems of health care and medical statistics. 2023(2):804-29. (In Russ.) doi:10.24412/2312-2935-2023-2-804-829.
19. Collins GS, Dhiman P, Andaur Navarro CL, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open. 2021;11(7):e048008. doi:10.1136/bmjopen-2020-048008.
20. Iba K, Shinozaki T, Maruo K, et al. Re-evaluation of the comparative effectiveness of bootstrap-based optimism correction methods in the development of multivariable clinical prediction models. BMC Med Res Methodol. 2021;21:9. doi:10.1186/s12874-020-01201-w.
21. Moons KGM, Altman DG, Reitsma JB, et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and Elaboration. Ann Intern Med. 2015;162(1):W1-73. doi:10.7326/M14-0698.
22. Austin PC, Putter H, Giardiello D, et al. Graphical calibration curves and the integrated calibration index (ICI) for competing risk models. Diagn Progn Res. 2022;6(1):2. doi:10.1186/s41512-021-00114-6.
23. Vickers AJ, Holland F. Decision curve analysis to evaluate the clinical benefit of prediction models. Spine J. 2021;21(10):1643-8. doi:10.1016/j.spinee.2021.02.024.
24. Dragomiretskaya NA, Tolmacheva AV, Vetluzhskaya MV, et al. Multifactor model to predict adverse outcomes in patients with chronic heart failure with preserved and moderately reduced left ventricular ejection fraction. Practical medicine. 2024;22(3):48-56. (In Russ.) doi:10.32000/2072-1757-2024-3-48-56.
25. Osipova OA, Kontsevaya AV, Demko VV, et al. Elements of artificial intelligence in a predictive personalized model of pharmacotherapy choice in patients with heart failure with mildly reduced ejection fraction of ischemic origin. Cardiovascular Therapy and Prevention. 2023;22(7):3619. (In Russ.) doi:10.15829/1728-8800-2023-3619.
26. Kovalenko EV, Markova LI, Belaya OL, et al. Prognostic significance of cardiac dysfunction markers in comorbid patients with chronic heart failure. Lechaschi Vrach. 2023;26(12):15-24. (In Russ.) doi:10.51793/OS.2023.26.12.002.
27. Polunina EA, Voronina LP, Popov EA, et al. Prognostic algorithms for the progression of chronic heart failure depending on the clinical phenotype. Cardiovascular Therapy and Prevention. 2019;18(3):41-7. (In Russ.) doi:10.15829/1728-8800-2019-3-41-47.
28. Mukhambetova GN, Voronina LP, Polunina OS, et al. The mathematical algorithm for predicting the progression of chronic heart failure in patients with ischemic cardiomyopathy. Modern problems of science and education. 2019;(6):108. (In Russ.)
29. Lebedeva NB, Egle AP, Argunova YuA, et al. Digital model for predicting the risk of developing acute decompensated heart failure. Rational Pharmacotherapy in Cardiology. 2024;20(3):309-15. (In Russ.) doi:10.20996/1819-6446-2024-3034.
30. Kovalenko EV, Markova LI, Belaya OL. Characteristics of heart failure and the predictors of adverse outcomes in patients with cardiovascular pathology, type 2 diabetes mellitus and chronic kidney disease. International Journal of Heart and Vascular Diseases. 2023;11(39):17-34. (In Russ.) EDN: AKPDQY.
31. Ilov NN, Palnikova OV, Stompel DR, et al. Lethal risk index — a novel tool for predicting one-year mortality in patients with heart failure with reduced ejection fraction. Russian Journal of Cardiology. 2025;30(6):6222. (In Russ.) doi:10.15829/1560-4071-2025-6222.
32. Posnenkova OM, Bogdanova TM, Fedonnikov AS. Practical and methodological aspects of managing a registry to assess the quality of health care for patients with heart failure. A systematic review. Russian Journal of Cardiology. 2025;30(9S):6345. (In Russ.) doi:10.15829/1560-4071-2025-6345.
What is already known about the subject?
- The international PROBAST and TRIPOD-ML standards set strict requirements for the creation of predictive models using machine learning.
- Predicting the heart failure course using machine learning is an important task in personalized medicine.
What might this study add?
- For the first time, a methodological analysis was conducted, revealing a shortage of targeted studies and systemic flaws (data leakage, no validation) in Russia.
- A practical algorithm has been developed for Russian researchers, enabling the creation of reproducible and clinically useful models in a domestic setting.
Review
For citations:
Burenkov Yu.V., Shevcova V.I., Akhyadov A.D., Alferova I.P. Predicting the heart failure course using machine learning: an analysis of international methodological standards and their application in Russian research practice. Cardiovascular Therapy and Prevention. 2026;25(5):4736. (In Russ.) https://doi.org/10.15829/1728-8800-2026-4736. EDN: BKSJDF
Views:
312
JATS XML
Email this article 
