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.
Background:
Coronary artery disease (CAD) is a major global cause of death, necessitating early, accurate prediction for better management. Traditional diagnostics are often invasive, costly, and less accessible. Machine learning (ML) offers a non-invasive alternative, but high-dimensional data and redundancy can hinder performance. This study integrates Bald Eagle Search Optimization (BESO) for feature selection to improve CAD classification using multiple ML models.
Methods:
Two publicly available datasets, Framingham (4200 instances, 15 features) and Z-Alizadeh Sani (304 instances, 55 features), were used. The former predicts 10-year CAD risk, while the latter classifies current CAD status. Data preprocessing included missing value imputation, normalization, categorical encoding, and class balancing using SMOTE. We employed a 70-30 holdout validation strategy with empirical hyperparameter optimization, providing more reliable final model development than cross-validation. BESO was applied to optimize feature selection, significantly outperforming traditional methods like RFE and LASSO. Six ML models-KNN, logistic regression, SVM with linear, polynomial, and RBF kernels, and random forest-were trained and evaluated.
Results:
Random Forest achieved the highest performance across both datasets. In the Framingham dataset, RF recorded 90 % accuracy, significantly outperforming traditional clinical risk scores (71-73 % accuracy). Linear models performed better on the Z-Alizadeh Sani dataset (90 % accuracy) than Framingham (66 %), indicating dataset characteristics strongly influence model efficacy.
Conclusion:
BESO significantly enhances feature selection, with RF emerging as the optimal classifier (92 % accuracy) and substantially outperforming established clinical risk scores. This study highlights the potential of AI-driven CAD diagnosis, supporting early detection and improved patient outcomes. Future work should focus on prospective validation and clinical implementation.