Related Experiment Videos

Comparative analysis of machine learning models for coronary artery disease prediction with optimized feature

David B Olawade1, Afeez A Soladoye2, Bolaji A Omodunbi2

  • 1Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London, United Kingdom; Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom; Department of Public Health, York St John University, London, United Kingdom; School of Health and Care Management, Arden University, Arden House, Middlemarch Park, Coventry CV3 4FJ, United Kingdom.

Insights

Bald Eagle Search Optimization (BESO) improves machine learning for coronary artery disease (CAD) prediction. Random Forest with BESO achieved 92% accuracy, outperforming traditional risk scores for early CAD diagnosis.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Data Science

Background:

  • Coronary artery disease (CAD) is a leading global cause of mortality.
  • Traditional diagnostic methods for CAD are often invasive and costly.
  • Machine learning (ML) offers a non-invasive approach, but high-dimensional data poses challenges.

Purpose of the Study:

  • To enhance coronary artery disease (CAD) classification accuracy using machine learning.
  • To optimize feature selection in ML models for CAD prediction through metaheuristic optimization.
  • To compare the performance of various ML models integrated with optimized feature selection against traditional methods.

Main Methods:

  • Utilized two public datasets (Framingham and Z-Alizadeh Sani) for CAD prediction.
  • Applied data preprocessing techniques including imputation, normalization, encoding, and SMOTE for class balancing.
  • Integrated Bald Eagle Search Optimization (BESO) for superior feature selection, outperforming RFE and LASSO, and trained six ML models.

Main Results:

  • Random Forest (RF) demonstrated the highest performance, achieving 92% accuracy with BESO-optimized features.
  • RF significantly outperformed traditional clinical risk scores (71-73% accuracy) on the Framingham dataset.
  • Linear models showed dataset-dependent efficacy, achieving 90% accuracy on Z-Alizadeh Sani but 66% on Framingham.

Conclusions:

  • BESO-enhanced feature selection optimizes ML models for improved CAD classification.
  • Random Forest with BESO is a highly effective classifier for early CAD detection, surpassing existing clinical risk scores.
  • AI-driven diagnostic tools show significant potential for early CAD detection and improved patient outcomes, warranting further clinical validation.
Abstract

Related Concept Videos