Hybrid Modelling of Cardiovascular Risk Analysis Using Machine Learning and Statistical Techniques}

Abstract

Since heart disease is still one of the main causes of death worldwide, especially among the youth after COVID-19, early identification and precise diagnosis are crucial to reduce the death rates. Conventional healthcare approaches often rely on manual evaluation, which can be laborious and prone to human error. To better predict and categorize cardiac disease based on patient health data, this study investigates the application of machine learning (ML) techniques and statistical techniques, such as the Chi-square test and t-test. A benchmark heart disease dataset from Kaggle was used to develop and test several machine learning models, including Logistic Regression, K-Nearest Neighbour’s (KNN), Decision Tree, Random Forest, Support Vector Machine (SVM), Gradient Boosting Machines, eXtreme Gradient Boosting (XGBoost), CatBoost, and Linear Discriminant Analysis (LDA). According to the study's findings, machine learning provides a reliable and effective framework for assisting clinical decision-making, facilitating early intervention, and potentially lowering heart disease-related mortality.