May 13, 2025Frontiers in Artificial IntelligenceOpen Access

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

View Full Paper

Ask AI

Bookmark

Why the study?

Cardiovascular diseases are the leading cause of global mortality, creating an urgent demand for early and precise diagnostic tools.

Do machine learning models improve the prediction and diagnosis of heart disease compared to traditional classifiers?

Structured PICO

Do machine learning models improve the prediction and diagnosis of heart disease compared to traditional classifiers?

Population

Patients at risk of or diagnosed with cardiovascular diseases (including coronary heart disease, heart failure, arrhythmias, and valvular heart disease) evaluated using machine learning prediction models

Intervention

Machine learning (ML) and artificial intelligence (AI) models, including hybrid deep learning frameworks (e.g., CNN-LSTM) and federated learning

Comparator

Traditional classifiers and existing diagnostic methods

Outcome

Model performance metrics including sensitivity, specificity, and area under the curve (AUC)

Machine learning, particularly hybrid deep learning and emerging technologies like federated learning, shows significant potential to enhance early and precise heart disease prediction, though ethical and dataset challenges remain.

Limitations

Ethical issues
Dataset limitations including imbalance and noise
Model transparency and explainability
Biases and patient privacy

Implication

ML heart-disease predictors should not yet change practice; leaves open prospective trials addressing bias, ethics, and clinical integration.

Abstract

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 terms of sensitivity, specificity, and area under the curve (AUC). Several real-world case studies are presented to demonstrate the successful deployment of ML models in clinical and wearable settings. This review showcases the progression of ML approaches from traditional classifiers to hybrid DL structures and federated learning (FL) frameworks. It also discusses ethical issues, dataset limitations, and model transparency. The conclusions provide important insights for the development of artificial intelligence (AI) powered, clinically applicable heart disease prediction systems.