An Innovative Machine Learning based Heart Disease Assessment System by Sequential Feature Selection Approach

According to the World Health Organization, 12 million people die each year as a result of heart disease. Because heart attacks and stroke are the primary causes of morbidity and mortality in the global population, recent research has focused on the prediction of cardiovascular disease. Many studies have been undertaken in an attempt to identify the most relevant risk factors for heart disease and to accurately assess the overall risk. Early detection of cardiac disease is critical in making lifestyle adjustments decisions in high-risk patients, reducing consequences.This research study presents a Machine Learning-based Innovative Heart Disease Assessment System (ML-IHDAS) that employs the Forward Sequential Feature Selection (FSFS) approach. In this investigation, the FSFS technique assesses subsets of features and selects the subset that gets the maximum performance on a certain criterion after making that determination. The proposed ML-IHDAS builds the classification models using Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosted decision trees (XGBoost) with selected features. Several performance indicators, including accuracy, precision, recall, and F1-measure, are utilized by the authors in order to assess the effectiveness of these models. The experimental results indicate that the XGBoost classifier outperforms the other three classifiers with highest accuracy. This method has the potential to assist medical professionals in accurately and successfully identifying heart disease.