An Analysis of Machine Learning Models for Early Cardiac Risk Stratification

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 13 | Issue : 02 | Page :
By

Naresh Kumar,

Surendra Kumar Yadav,

Dushyant Singh,

  1. Student, Department of CSE, JECRC University Jaipur, Rajasthan
  2. Professor, Department of CSE JECRC University Jaipur, Rajasthan, India
  3. Professor, Department of CSE JECRC University Jaipur, Rajasthan, India

Abstract

The paper shows an in-depth study of machine learning and artificial intelligence solutions to early cardiac risk stratification which has a crucial necessity because cardiovascular disease (CVD) prediction remains a significant issue that needs to be improved beyond the conventional risk score. Since CVD is the most serious disease killer in the world, claiming 17.9 million deaths every year, there is a strong need to get the most sophisticated predictive analytics, which will detect at-risk patients in time and more precisely. This paper reviews 15 peer-reviewed articles published by 2022-2025 with the intention to examine the current state of AI/ML methods in several aspects’ algorithmic performance, clinical interpretability, data-set characteristics, and implement ability to real-life applications. The analyzed methodologies include ensemble learning (XGBoost, LightGBM, Random Forest), deep learning models (CNNs, LSTMs, Transformers), federated learning terms of privacy, reinforcement learning systems, as a way to optimize treatment, and explainable AI. The quality of methods, the measures of performance, the size and the diversity of its data sets, the practices of external validation, and its clinical relevance were thoroughly evaluated to conduct the studies. The evaluation shows that accurately predicting an item ranged between 83% and 98.6% with a higher performance of the gradient boosting techniques and deep convolutional neural networks. SHAP based explainability has become the standard of clinical interpretability with 20% of reviewed studies adopting it. Nevertheless, serious weaknesses include poor design (small size of datasets; median n=287-6,300), lack of external validation (only 20 percent out of studies), and the inability to generalize the results to other populations; and little prospective validation with randomized controlled trials. Although AI/ML methods show high retrospective performance, there is a lot to improve in actual clinical applications, cross-center testing, algorithmic equity across groups, and electronic integration into clinical procedures. This discussion shows that prospective validation studies, creation of standardized benchmarks, privacy-preserving collaborative learning models, and clinician-in-the-loop design protocols should be implemented as the focus of future research to effectively transfer the success in the laboratory to the measurable patient outcome improvements.

Keywords: cardiovascular disease prediction, machine learning, deep learning, explainable AI, federated learning, clinical decision support

[This article belongs to Research & Reviews: A Journal of Bioinformatics ]

How to cite this article: Naresh Kumar, Surendra Kumar Yadav, Dushyant Singh. An Analysis of Machine Learning Models for Early Cardiac Risk Stratification. Research & Reviews: A Journal of Bioinformatics. 2026; 13(02):-.
How to cite this URL: Naresh Kumar, Surendra Kumar Yadav, Dushyant Singh. An Analysis of Machine Learning Models for Early Cardiac Risk Stratification. Research & Reviews: A Journal of Bioinformatics. 2026; 13(02):-. Available from: https://journals.stmjournals.com/rrjobi/article=2026/view=253520

References

  1. A. Bouqentar et al., “Early Heart Disease Prediction using Feature Engineering and Machine Learning Algorithms,” Heliyon, vol. 10, no. 19, pp. e38731–e38731, Oct. 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e38731.
  2. Areti Papadopoulou, D. Harding, G. Slabaugh, Eirini Marouli, and Panos Deloukas, “Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank,” Heliyon, vol. 10, no. 7, pp. e28034–e28034, Apr. 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e28034.
  3. H. Kim et al., “PPFL: A personalized progressive federated learning method for leveraging different healthcare institution-specific features,” iScience, vol. 27, no. 10, p. 110943, Sep. 2024, doi: https://doi.org/10.1016/j.isci.2024.110943.
  4. Zhang et al., “Construction and Validation of a Predictive Model for Coronary Artery Disease Using Extreme Gradient Boosting,” Journal of Inflammation Research, vol. Volume 17, pp. 4163–4174, Jul. 2024, doi: https://doi.org/10.2147/jir.s464489.
  5. Ibomoiye Domor Mienye and Nobert Jere, “Optimized Ensemble Learning Approach with Explainable AI for Improved Heart Disease Prediction,” Information, vol. 15, no. 7, pp. 394–394, Jul. 2024, doi: https://doi.org/10.3390/info15070394.
  6. Fatema, S. Montaha, Md. A. H. Rony, S. Azam, Md. Z. Hasan, and M. Jonkman, “A Robust Framework Combining Image Processing and Deep Learning Hybrid Model to Classify Cardiovascular Diseases Using a Limited Number of Paper-Based Complex ECG Images,” Biomedicines, vol. 10, no. 11, p. 2835, Nov. 2022, doi: https://doi.org/10.3390/biomedicines10112835.
  7. Phani Praveen et al., “Enhanced feature selection and ensemble learning for cardiovascular disease prediction: hybrid GOL2-2 T and adaptive boosted decision fusion with babysitting refinement,” Frontiers in Medicine, vol. 11, Jul. 2024, doi: https://doi.org/10.3389/fmed.2024.1407376.
  8. Puyol-Antón et al., “A multimodal deep learning model for cardiac resynchronisation therapy response prediction,” Medical Image Analysis, vol. 79, p. 102465, Jul. 2022, doi: https://doi.org/10.1016/j.media.2022.102465.
  9. Ni et al., “Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers,” pp. 584–589, Jun. 2024, doi: https://doi.org/10.1109/eei63073.2024.10695966.
  10. Hasan, M. A. Sahid, M. P. Uddin, M. A. Marjan, S. Kadry, and J. Kim, “Performance discrepancy mitigation in heart disease prediction for multisensory inter-datasets,” PeerJ Computer Science, vol. 10, p. e1917, Mar. 2024, doi: https://doi.org/10.7717/peerj-cs.1917.
  11. Sultan Alasmari, R. AlGhamdi, G. G. Tejani, S. K. Sharma, and Seyed Jalaleddin Mousavirad, “Federated learning-based multimodal approach for early detection and personalized care in cardiac disease,” Frontiers in Physiology, vol. 16, Apr. 2025, doi: https://doi.org/10.3389/fphys.2025.1563185.
  12. Guo, J. Li, H. Liu, and J. He, “Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven study,” BMC Medical Informatics and Decision Making, vol. 22, no. 1, Feb. 2022, doi: https://doi.org/10.1186/s12911-022-01774-0.
  13. Moosavi et al., “Prospective Human Validation of Artificial Intelligence Interventions in Cardiology: A Scoping Review,” JACC: Advances, vol. 3, no. 9, p. 101202, Aug. 2024, doi: https://doi.org/10.1016/j.jacadv.2024.101202.
  14. Y. Desai, “Machine Learning to Predict Future Disease-Specific Outcomes,” JACC: Asia, vol. 4, no. 5, pp. 387–388, May 2024, doi: https://doi.org/10.1016/j.jacasi.2023.12.004.
  15. Sheeba. Rani, D. Gopal, S. Vignesh, and P. S. Ramesh, “Advanced IoT-enabled embedded wearable system for continuous cardiovascular health monitoring using edge intelligence,” Biomedical Signal Processing and Control, vol. 111, p. 108362, Jul. 2025, doi: https://doi.org/10.1016/j.bspc.2025.108362.
Regular Issue Subscription Original Research
Volume 13
Issue 02
Received 19/03/2026
Accepted 02/06/2026
Published 27/08/2026
Publication Time 161 Days

Login

My IP

PlumX Metrics

Support