A comprehensive review of machine learning for heart disease prediction - challenges, trends, ethical considerations, and future directions

Aug 5, 2026

This review presents a structured, in-depth overview of machine learning approaches for heart disease prediction, focusing on technological progress, key challenges, and future directions. With cardiovascular diseases driving global mortality, the review emphasizes the need for early, accurate diagnostics and highlights how ML models can leverage large-scale healthcare data to improve predictive performance. Literature is organized into thematic categories including detection, model development, feature engineering, emerging healthcare technologies, and AI applications across conditions, alongside performance benchmarking, real-world clinical and wearable case studies, and discussion of ethical, dataset, and transparency limitations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages31

Reading Time1 h 18 min

AccessFree to download

Introduction

Background of the study

Thematic categories and literature organization

Heart Disease Detection and Diagnostics

Machine Learning Models and Algorithms for Healthcare

Feature Engineering and Optimization Techniques

Emerging Technologies in Healthcare

Applications of AI Across Diseases and Conditions

Model performance and benchmarking

Hybrid deep learning frameworks

Real-world deployment

Clinical and wearable settings

Future directions and ethics

Dataset limitations and model transparency

TYPE Review PUBLISHED 13 May 2025 DOI 10.3389/frai.2025.1583459 OPEN ACCESS EDITED BY Tim Hulsen, Rotterdam University of Applied Sciences, Netherlands REVIEWED BY Minjae Yoon, Seoul National University Bundang Hospital, Republic of Korea Annalisa Santucci, University of Siena, Italy *CORRESPONDENCE Jasmina Lozanović [jasmina.lozanovic@gmail.com](jasmina.lozanovic@gmail.com)[ ](jasmina.lozanovic@gmail.com)Rupinder Kaur [rupinderkaur1588@gmail.com](rupinderkaur1588@gmail.com)[ ](rupinderkaur1588@gmail.com)RECEIVED 28 February 2025 ACCEPTED 24 April 2025 PUBLISHED 13 May 2025 CITATION Kumar R, Garg S, Kaur R, Johar MGM, Singh S, Menon SV, Kumar P, Hadi AM, Hasson SA and Lozanović J (2025) A comprehensive review of machine learning for heart disease prediction: challenges, trends, ethical considerations, and future directions. Front. Artif. Intell. 8:1583459. doi: 10.3389/frai.2025.1583459 COPYRIGHT © 2025 Kumar, Garg, Kaur, Johar, Singh, Menon, Kumar, Hadi, Hasson and Lozanović . This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. A comprehensive review of machine learning for heart disease prediction: challenges, trends, ethical considerations, and future directions Raman Kumar1,2, Sarvesh Garg3, Rupinder Kaur4*, M. G. M. Johar5, Sehijpal Singh1,6, Soumya V. Menon7, Pulkit Kumar8,9, Ali Mohammed Hadi 10, Shams Abbass Hasson 11 and Jasmina Lozanović 12* 1 Department of Mechanical and Production Engineering, Guru Nanak Dev Engineering College, Ludhiana, India, 2Jadara Research Center, Jadara University, Irbid, Jordan, 3 Department of Computer Science and Engineering, Guru Nanak Dev Engineering College, Ludhiana, India, 4 Department of Information Technology, Guru Nanak Dev Engineering College, Ludhiana, India, 5 Management and Science University, Shah Alam, Malaysia, 6 Department of Mechanical Engineering, Graphic Era (Deemed to be University), Dehradun, India, 7 Department of Chemistry and Biochemistry, School of Sciences, JAIN (Deemed to be University), Bangalore, India, 8 Department of Electrical Engineering, Chandigarh University, Mohali, India, 9Chitkara University Institute of Engineering and Technology, Centre for Research Impact & Outcome, Chitkara University, Rajpura, India, 10 Department of Pharmacy, Mazaya University College, Dhiqar, Iraq, 11 Laboratories Techniques Department, College of Health and Medical Techniques, Al-Mustaqbal University, Babylon, Iraq, 12 Department of Engineering, FH Campus Wien-University of Applied Sciences, Vienna, Austria This review provides a thorough and organized overview of machine learning (ML) applications in predicting heart disease, covering technological advancements, challenges, and future prospects. As cardiovascular diseases (CVDs) are the leading cause of global mortality, there is an urgent demand for early and precise diagnostic tools. ML models hold considerable potential by utilizing large-scale healthcare data to enhance predictive diagnostics. To systematically investigate this field, the literature is organized into five thematic categories such as “Heart Disease Detection and Diagnostics,”“Machine Learning Models and Algorithms for Healthcare,”“Feature Engineering and Optimization Techniques,”“Emerging Technologies in Healthcare,”and “Applications of AI Across Diseases and Conditions.” The review incorporates performance benchmarking of various ML models, highlighting that hybrid deep learning (DL) frameworks, e. g., convolutional neural network-long short-term memory (CNN-LSTM) consistently outperform traditional models in term

FAQs

What problem does the review address in heart disease prediction?

The review addresses the need for early and precise diagnostic tools for heart disease, given that cardiovascular diseases remain a leading cause of global mortality.

How is the literature organized in the review?

The review organizes the literature into five thematic categories covering detection/diagnostics, healthcare ML models, feature engineering and optimization, emerging healthcare technologies, and broader AI applications across diseases and conditions.

Which approaches are highlighted as performing well and why?

The review highlights hybrid deep learning frameworks such as CNN-LSTM as consistently outperforming traditional models, with improved sensitivity, specificity, and AUC metrics.

Aug 5, 2026

Upload by River Wang