Predicting Heart Disease with Body Composition Using a Hybrid Machine Learning Approach

Heart diseases represent a significant global health concern, characterized by impaired heart function. Unfortunately, it’s predicted that fatalities resulting from heart-related illnesses may escalate dramatically, reaching an astounding 24.2 million by the year 2030. Accurate prognosis and identification of cardiac diseases play a pivotal role in facilitating timely prevention, detection, and therapy. However, existing medical equipment such as electrocardiograms and computerized tomography scans employed for detecting heart disorders often pose difficulties owing to prohibitive costs and operational constraints, making access challenging for many individuals. By harnessing these capabilities, machine learning models can potentially provide more accurate predictions of heart disease risk based on body composition data. The use of machine learning algorithms in healthcare has already shown encouraging results in various applications, including disease diagnosis, treatment planning, and patient outcome prediction. In light of these developments, the study aims to create a hybrid machine learning model that leverages the strengths of multiple algorithms to predict heart disease risk based on body composition data to reduce death rate. This paper proposed six Machine Learning algorithms using a body composition dataset, the algorithms are the Decision tree model (DTM), XGBOOST, LIGHTGBM, Support Vector Machine (SVM), KNN, and Hybrid model. The experimental result indicates that the HHP model outperformed others in the precision, recall, and F-score, with an accuracy of 90.2 %.