Author : Nidhi Singh and Bhanu Pratap Singh

Cardiovascular disease remains the leading cause of death across the globe. Predicting heart disease (HDP) is a complex task that demands specialized knowledge and experience. Additionally, it faces numerous challenges related to clinical data analysis. Despite extensive research in this area, prediction accuracy—a key performance metric—still falls short of expectations. Accurate HDP can be life-saving, while incorrect predictions may lead to fatal consequences. To address these concerns, this review explores various Heart Disease Prediction techniques based on Deep Learning (DL), Machine Learning (ML), and optimization methods. Recently, numerous researchers have applied DL and ML algorithms to support healthcare professionals in diagnosing heart disease. The paper also examines different optimization algorithms and their performance. Ultimately, this review suggests that optimization-based HDP methods can play a crucial role in helping doctors predict heart disease early and recommend appropriate treatments.

Keywords: Machine Learning, Supervised learning, Support vector machine, Random Forest, Neural Network