Machine Learning Application to Predict Bicycle Ergometer Test Results: a Prospective Cohort Study

The aim of the study was to develop an optimal technique to predict the results of a bicycle ergometry test (BET) based on the parameters recorded during a six-minute walk test (6MWT) using machine learning methods.

Materials and Methods. The study involved 56 patients who had experienced acute myocardial infarction and were undergoing the second stage of cardiac rehabilitation. The patients underwent a complete examination, including history taking, physical examination, anthropometric assessment, as well as a symptom-limited BET and 6MWT. During the 6MWT, we recorded the following: the distance covered, the heart rate, the blood pressure, the oxygen saturation, Borg rating of perceived exertion, the number of steps taken, and the electrocardiographic data. The algorithms for random forest, gradient boosting, k-nearest neighbors, and multiple linear regression were used to construct the machine learning models. The performance of the models was evaluated based on a determination coefficient, a mean absolute error, a mean square error, and a root mean square error. SHAP analysis was applied to interpret the findings.

Results. The gradient boosting model provided the best prediction quality with a high determination coefficient (R² being around 0.99) and low error values for both target metrics: the distance walked in the 6MWT and the metabolic equivalent achieved during the BET. The significance analysis of features revealed the heart rate, age, and the body mass index to have the greatest impact on predicting the 6MWT distance, while for predicting the metabolic equivalent, the distance covered, the number of steps, and the body mass index were the most significant.

Conclusion. The developed gradient boosting-based machine learning model demonstrated its high efficiency in predicting the results of the 6MWT-based BET. The suggested method can serve as a valuable auxiliary tool to plan cardiac rehabilitation programs, particularly in cases when BET is difficult or impossible to perform. The use of SHAP analysis helped to understand the contribution of each feature to the prediction, increasing the confidence in the model results.

1. Gaidai O., Cao Y., Loginov S. Global cardiovascular diseases death rate prediction. Curr Probl Cardiol 2023; 48(5): 101622, https://doi.org/10.1016/j.cpcardiol.2023.101622.
2. World Health Organization. Cardiovascular diseases (CVDs). 31 July 2025. URL: https://www.who.int/en/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds).
3. Shokri K., Karimian A., Radfar A., Mohammadi A., Amerizadeh A., Karimi R., Sadeghi M. Effect of exercise-based cardiac rehabilitation in patients with acute coronary syndrome: a systematic review and meta-analysis. BMC Sports Sci Med Rehabil 2025; 17(1): 233, https://doi.org/10.1186/s13102-025-01270-8.
4. Meng Y., Zhuge W., Huang H., Zhang T., Ge X. The effects of early exercise on cardiac rehabilitation-related outcome in acute heart failure patients: a systematic review and meta-analysis. Int J Nurs Stud 2022; 130: 104237, https://doi.org/10.1016/j.ijnurstu.2022.104237.
5. Mahmood A., Ray R., Bin Salam S.S.T., Haque F., Akkaldevi J., Masmoum M.D., Hassan M.S., Essani B., Anjum T., Mirza M.S.S. The effectiveness of cardiac rehabilitation programs in improving cardiovascular outcomes: systematic review and meta-analysis. Cureus 2024; 16(10): e72450, https://doi.org/10.7759/cureus.72450.
6. Moghei M., Turk-Adawi K., Isaranuwatchai W., Sarrafzadegan N., Oh P., Chessex C., Grace S.L. Cardiac rehabilitation costs. Int J Cardiol 2017; 244: 322–328, https://doi.org/10.1016/j.ijcard.2017.06.030.
7. Thomas R.J., Beatty A.L., Beckie T.M., Brewer L.C., Brown T.M., Forman D.E., Franklin B.A., Keteyian S.J., Kitzman D.W., Regensteiner J.G., Sanderson B.K., Whooley M.A. Home-based cardiac rehabilitation: a scientific statement from the american association of cardiovascular and pulmonary rehabilitation, the American Heart Association, and the American College of Cardiology. Circulation 2019; 140(1): e69–e89, https://doi.org/10.1161/CIR.0000000000000663.
8. Kardioreabilitatsiya i vtorichnaya profilaktika. Pod red. Aronova D.M. [Cardiac rehabilitation and secondary prevention. Aronov D.M. (editor)]. Moscow: GEOTAR-Media; 2021, https://doi.org/10.33029/9704-6218-8-car-2021-1-464.
9. Coulshed A., Coulshed D., Pathan F. Systematic review of the use of the 6-minute walk test in measuring and improving prognosis in patients with ischemic heart disease. CJC Open 2023; 5(11): 816–825, https://doi.org/10.1016/j.cjco.2023.08.003.
10. Mikhailovskaya T.V., Nazarova O.A., Dovgalyuk Yu.V., Chistyakova Yu.V., Mishina I.E. Methodological issues of assessment of sixminute walk test in patients with coronary artery disease. Bulletin of Rehabilitation Medicine 2021; 20(3): 37–44, https://doi.org/10.38025/2078-1962-2021-20-3-37-44.
11. Mapelli M., Salvioni E., Paneroni M., Gugliandolo P., Bonomi A., Scalvini S., Raimondo R., Sciomer S., Mattavelli I., La Rovere M.T., Agostoni P. Brisk walking can be a maximal effort in heart failure patients: a comparison of cardiopulmonary exercise and 6 min walking test cardiorespiratory data. ESC Heart Fail 2022; 9(2): 812–821, https://doi.org/10.1002/ehf2.13781.
12. Cavero-Redondo I., Saz-Lara A., Bizzozero-Peroni B., Núñez-Martínez L., Díaz-Goñi V., Calero-Paniagua I., Matínez-García I., Pascual-Morena C. Accuracy of the 6-minute walk test for assessing functional capacity in patients with heart failure with preserved ejection fraction and other chronic cardiac pathologies: results of the ExIC-FEp trial and a meta-analysis. Sports Med Open 2024; 10(1): 74, https://doi.org/10.1186/s40798-024-00740-6.
13. Rasa A.R. Artificial intelligence and its revolutionary role in physical and mental rehabilitation: a review of recent advancements. Biomed Res Int 2024; 2024: 9554590, https://doi.org/10.1155/bmri/9554590.
14. Norgeot B., Glicksberg B.S., Butte A.J. A call for deep-learning healthcare. Nat Med 2019; 25(1): 14–15, https://doi.org/10.1038/s41591-018-0320-3.
15. Esteva A., Robicquet A., Ramsundar B., Kuleshov V., DePristo M., Chou K., Cui C., Corrado G., Thrun S., Dean J. A guide to deep learning in healthcare. Nat Med 2019; 25(1): 24–29, https://doi.org/10.1038/s41591-018-0316-z.
16. Chilamkurthy S., Ghosh R., Tanamala S., Biviji M., Campeau N.G., Venugopal V.K., Mahajan V., Rao P., Warier P. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 2018; 392(10162): 2388–2396, https://doi.org/10.1016/S0140-6736(18)31645-3.
17. Ehteshami Bejnordi B., Veta M., Johannes van Diest P., van Ginneken B., Karssemeijer N., Litjens G., van der Laak JAWM; the CAMELYON16 Consortium; Hermsen M., Manson Q.F., Balkenhol M., Geessink O., Stathonikos N., van Dijk M.C., Bult P., Beca F., Beck A.H., Wang D., Khosla A., Gargeya R., Irshad H., Zhong A., Dou Q., Li Q., Chen H., Lin H.J., Heng P.A., Haß C., Bruni E., Wong Q., Halici U., Öner M.Ü., Cetin-Atalay R., Berseth M., Khvatkov V., Vylegzhanin A., Kraus O., Shaban M., Rajpoot N., Awan R., Sirinukunwattana K., Qaiser T., Tsang Y.W., Tellez D., Annuscheit J., Hufnagl P., Valkonen M., Kartasalo K., Latonen L., Ruusuvuori P., Liimatainen K., Albarqouni S., Mungal B., George A., Demirci S., Navab N., Watanabe S., Seno S., Takenaka Y., Matsuda H., Ahmady Phoulady H., Kovalev V., Kalinovsky A., Liauchuk V., Bueno G., Fernandez-Carrobles M.M., Serrano I., Deniz O., Racoceanu D., Venâncio R. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017; 318(22): 2199–2210, https://doi.org/10.1001/jama.2017.14585.
18. Zhu M., Chen W., Hirdes J.P., Stolee P. The k-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol. J Clin Epidemiol 2007; 60(10): 1015–1021, https://doi.org/10.1016/j.jclinepi.2007.06.001.
19. Zhu M., Cheng L., Armstrong J.J., Poss J.W., Hirdes J.P., Stolee P. Using machine learning to plan rehabilitation for home care clients: beyond "black-box" predictions. In: Dua S., Acharya U., Dua P. (editors). Machine learning in healthcare informatics. Intelligent systems reference library, vol 56. Springer, Berlin, Heidelberg; 2014, https://doi.org/10.1007/978-3-642-40017-9_9.
20. Lin W.Y., Chen C.H., Tseng Y.J., Tsai Y.T., Chang C.Y., Wang H.Y., Chen C.K. Predicting post-stroke activities of daily living through a machine learning-based approach on initiating rehabilitation. Int J Med Inform 2018; 111: 159–164, https://doi.org/10.1016/j.ijmedinf.2018.01.002.
21. Sharma A., Lysenko A., Jia S., Boroevich K.A., Tsunoda T. Advances in AI and machine learning for predictive medicine. J Hum Genet 2024; 69(10): 487–497, https://doi.org/10.1038/s10038-024-01231-y.
22. De Cannière H., Corradi F., Smeets CJP, Schoutteten M., Varon C., Van Hoof C., Van Huffel S., Groenendaal W., Vandervoort P. Wearable monitoring and interpretable machine learning can objectively track progression in patients during cardiac rehabilitation. Sensors (Basel) 2020; 20(12): 3601, https://doi.org/10.3390/s20123601.
23. Desai F., Chowdhury D., Kaur R., Peeters M., Arya R.C., Wander G.S., Gill S.S., Buyya R. HealthCloud: a system for monitoring health status of heart patients using machine learning and cloud computing. Internet of Things 2022; 17: 10048, https://doi.org/10.1016/j.iot.2021.100485.
24. Alshurafa N., Sideris C., Pourhomayoun M., Kalantarian H., Sarrafzadeh M., Eastwood J.A. Remote health monitoring outcome success prediction using baseline and first month intervention data. IEEE J Biomed Health Inform 2017; 21(2): 507–514, https://doi.org/10.1109/JBHI.2016.2518673.
25. den Uijl I., van den Berg-Emons R.J.G., Sunamura M., Lenzen M.J., Stam H.J., Boersma E., Tenbült-van Limpt N.C.C.W., Kemps H.M.C., Geleijnse M.L., Ter Hoeve N. Effects of a dedicated cardiac rehabilitation program for patients with obesity on body weight, physical activity, sedentary behavior, and physical fitness: the OPTICARE XL randomized controlled trial. Phys Ther 2023; 103(9): pzad055, https://doi.org/10.1093/ptj/pzad055.
26. O'Connor F.K., Chen D., Sharma P., Adsett J., Hwang R., Roberts L., Bach A., Louis M., Morris N. Physiological responses to sit-to-stand and six-minute walk tests in heart failure: a randomised trial. Heart Lung Circ 2025; 34(8): 789–797, https://doi.org/10.1016/j.hlc.2025.03.002.
27. Büsching G., Schmid J.P. 6-minute walk test: exploring factors influencing perceived intensity in older patients undergoing cardiac rehabilitation-a qualitative study. Healthcare (Basel) 2025; 13(7): 735, https://doi.org/10.3390/healthcare13070735.

Berezina E.V., Blinova K.A., Dmitrieva O.A., Mishina I.E. Machine Learning Application to Predict Bicycle Ergometer Test Results: a Prospective Cohort Study. Sovremennye tehnologii v medicine 2026; 18(2): 63, https://doi.org/10.17691/stm2026.18.2.06