Improvising Performance of Machine Learning Algorithm using FAMD on Coronary Artery Disease

Coronary Artery Disease (CAD) is a significant global health issue that requires reliable and prompt prediction approaches. This research proposes an innovative approach to improvise CAD prediction by implementing different machine learning algorithms like Support Vector Machine (SVM), Logistic Regression, Random Forest and KNN [5]. To deal with the mixed types of data, FAMD is incorporated. It is used for dimensionality reduction purpose addressing the complexities of a mixed dataset comprising both categorical and numerical variables. We applied all these machine learning algorithms without reducing the dataset and evaluated the accuracy, precision, recall and f1-score of all the algorithms. After that, we reduced the dataset with the help of FAMD and than again applying all those included algorithms on the reduced dataset and calculated the accuracy, precision, recall and f1-score. All these included algorithms without the application of FAMD and with the application of FAMD undergo a comparative analysis to distinguish their performances in CAD prediction. With the help of the compaprative analysis, it is discovered that the results of the models are improved and better with the application of FAMD than without FAMD.