Leveraging fuzzy embedded wavelet neural network with multi-criteria decision-making approach for coronary artery disease prediction using biomedical data

Coronary artery disease (CAD) is the main cause of death. It is a complex heart disease that is linked with many risk factors and a variety of symptoms. In the past few years, CAD has experienced a remarkable growth. Prompt risk prediction of CAD would be capable of decreasing the death rate by permitting timely and targeted treatments. Angiography is the most precise CAD diagnosis technique; however, it has several side effects and is expensive. Multi-criteria decision-making approaches can well perceive CAD by analysing main clinical indicators like ChestPain type, ST_Slope, and HeartDisease presence. By assessing and evaluating these factors, the model improves diagnostic accuracy and aids informed clinical decisions for quick CAD detection. Mainly machine learning (ML) and deep learning (DL) use plentiful models and algorithms, which are commonly employed and very useful in exactly detecting the CAD within a short time. Current studies have employed numerous features in gathering data from patients while using dissimilar ML and DL models to attain results with high accuracy and lesser side effects and costs. This study presents a Leveraging Fuzzy Wavelet Neural Network with Decision Making Approach for Coronary Artery Disease Prediction (LFWNNDMA-CADP) technique. The presented LFWNNDMA-CADP technique focuses on the multi-criteria decision-making model for predicting CAD using biomedical data. In the LFWNNDMA-CADP method, the data pre-processing stage utilizes Z-score normalization to convert an input data into a uniform format. Furthermore, the improved ant colony optimization (IACO) method is used for electing an optimum sub-set of features. Furthermore, the classification of CAD is accomplished by utilizing the fuzzy wavelet neural network (FWNN) technique. Finally, the hyperparameter tuning of the FWNN model is accomplished by employing the hybrid crayfish optimization algorithm with the self-adaptive differential evolution (COASaDE) technique. The simulation outcomes of the LFWNNDMA-CADP approach are investigated under a benchmark database. The experimental validation of the LFWNNDMA-CADP approach portrayed a superior accuracy value of 99.49% over existing techniques.