Comparative Analysis of Machine Learning Models for Heart Disease Prediction

The diagnosis and prognosis of cardiovascular disease play a vital role in ensuring accurate classification, which assists cardiologists in providing appropriate treatment to patients. The adoption of machine learning in the medical field has grown significantly due to its ability to detect patterns from data. Leveraging machine learning for cardiovascular disease classification can help reduce the risk of misdiagnosis. This study presents a model designed to accurately predict cardiovascular disease occurrences, ultimately minimizing fatalities. The proposed method utilizes k-modes clustering with Huang initialization to enhance classification accuracy. Machine learning algorithms such as Random Forest (RF), Decision Tree Classifier (DT), Multilayer Perceptron (MP), and XGBoost (XGB) are employed. Hyperparameter tuning using GridSearchCV was conducted to optimize model performance. The model was applied to a real-world Kaggle dataset comprising 70,000 instances, with an 80:20 train-test split.