Cardiovascular Disease Prediction Using Machine Learning Metrics

Background: This project aims to develop a Machine-Learning model for heart disease prediction based on clinical and demographic data. Traditional diagnostic methods may not always detect subtle risk factors, hence Machine Learning offers a promising approach to enhance predictive accuracy. Materials and Methods: The methodology involves comprehensive pre-processing of the Kaggle Heart Disease dataset, applying algorithms such as Decision Tree, K-Nearest Neighbors, Naive Bayes algorithm, XGBoost, and Random Forest for predictive modelling. Results: The XGBoost algorithm outperformed other models with an accuracy of 93% on the test set. Key predictors of heart disease identified through feature importance analysis included age, sex, BMI, genetic, and lifestyle factors. An interactive dashboard was developed to enable users to predict the likelihood of heart disease based on input parameters. Conclusion: This project demonstrates the feasibility and effectiveness of Machine Learning techniques in predicting heart disease, enabling timely interventions and personalized treatment strategies. Future research directions include integrating additional data sources and refining models to improve prediction accuracy and robustness in diverse patient populations.