Early Prediction of Coronary Heart Disease Using Hybrid Machine Learning Models

Millions of people die each year from cardiovascular disease, which is the leading cause of death worldwide. Coronary Heart Disease is primarily brought on by poor lifestyle choices and heredity. If such diseases can be detected earlier, then proper lifestyle choices and treatment plans can save the lives of many people around the world. The goal of this study is to accurately detect patients by applying machine learning models like K-Nearest Neighbors, Support Vector Machine, Logistic Regression, Gaussian Naive Bayes, AdaBoost, and XGBoost. This research presents a hybrid machine learning model that promotes sensitivity over specificity. The suggested hybrid model, which combines bagged Logistic Regression with hyperparameter-optimized KNN, performs better than either algorithm alone, with 79% accuracy and 88% sensitivity. Additionally, this study will raise awareness among people in various age groups who are at higher risk for coronary heart disease, encouraging them to examine their heart health and take the necessary precautions to prevent premature death.