Leveraging fuzzy embedded wavelet neural network with multi-criteria decision-making approach for coronary artery...

Area of Science:

• Cardiovascular Medicine
• Artificial Intelligence in Healthcare
• Biomedical Data Analysis

Background:

• Coronary artery disease (CAD) is a leading cause of mortality globally, necessitating accurate and timely risk prediction for effective intervention.
• Traditional diagnostic methods like angiography are invasive, costly, and carry risks, highlighting the need for advanced, non-invasive predictive models.
• Machine learning and deep learning offer promising avenues for analyzing complex clinical indicators to improve CAD diagnosis.

Purpose of the Study:

• To develop and validate a novel technique, Leveraging Fuzzy Wavelet Neural Network with Decision Making Approach for Coronary Artery Disease Prediction (LFWNNDMA-CADP), for accurate CAD risk prediction.
• To enhance diagnostic accuracy and reduce healthcare costs associated with CAD detection through an intelligent decision-making model.
• To explore the efficacy of integrating multi-criteria decision-making with advanced neural network architectures for biomedical data analysis.

Main Methods:

• The LFWNNDMA-CADP technique employs Z-score normalization for data pre-processing and Improved Ant Colony Optimization (IACO) for optimal feature selection.
• Classification of CAD is performed using a Fuzzy Wavelet Neural Network (FWNN) model.
• Hyperparameter tuning of the FWNN model is achieved through a hybrid Crayfish Optimization Algorithm with Self-Adaptive Differential Evolution (COASaDE).

Main Results:

• The LFWNNDMA-CADP approach demonstrated a high diagnostic accuracy of 99.49% on a benchmark database.
• The proposed method effectively utilizes key clinical indicators for precise CAD prediction, outperforming existing techniques.
• Feature selection and hyperparameter optimization significantly contributed to the model's superior predictive performance.

Conclusions:

• The LFWNNDMA-CADP technique presents a highly accurate and efficient method for coronary artery disease prediction.
• This approach offers a cost-effective and less invasive alternative to traditional diagnostic methods, facilitating timely clinical decisions.
• The study underscores the potential of advanced AI techniques, like fuzzy wavelet neural networks and hybrid optimization algorithms, in improving cardiovascular disease management.