MLP-PSO Hybrid Algorithm for Heart Disease Prediction.

Area of Science:

• Cardiology
• Medical Informatics
• Machine Learning

Background:

• Machine learning (ML) is increasingly vital in healthcare for enhancing diagnostic accuracy and timeliness.
• Predicting and preventing cardiovascular disease (CVD) is a critical area in clinical data analysis due to rising treatment costs.
• Manual assessment of heart disease risk is challenging due to numerous contributing factors.

Purpose of the Study:

• To develop and compare ML algorithms for predicting heart disease using the Cleveland Heart Disease dataset.
• To introduce and evaluate an alternative multilayer perceptron (MLP) training technique using particle swarm optimization (PSO) for heart disease detection.

Main Methods:

• The study employed a proposed MLP-PSO hybrid algorithm alongside ten other ML algorithms.
• Performance evaluation was conducted using various classification metrics.

Main Results:

• The proposed MLP-PSO hybrid algorithm demonstrated superior performance compared to all other tested algorithms.
• The MLP-PSO model achieved an accuracy of 84.61% in predicting heart disease.

Conclusions:

• The developed MLP-PSO classifier facilitates earlier, more accurate, and effective diagnosis of heart disease.
• This ML-based approach empowers healthcare providers with better tools for cardiovascular disease management.