• Soumendra Kumar Mishra
• Manoranjan Dash
• Saumendra Pattnaik
• Suprava Ranjan Laha
• Salankara Sarkar

Cardiovascular disease remains a leading cause of global mortality, responsible for around 12 million deaths annually. Early detection is essential for high-risk individuals to make necessary lifestyle changes, reducing the likelihood of severe complications. This study introduces a machine learning based system for predicting heart disease using several classification algorithms: Random Forest, Decision Tree, Support Vector Machine (SVM), AdaBoost, XGBoost, and Logistic Regression. A dataset containing 76 attributes, with 14 critical features such as age, cholesterol levels, blood pressure, and fasting blood sugar, was used to predict outcomes. The models were evaluated using accuracy, precision, recall, and F1 score. XGBoost achieved the highest accuracy at 82%, followed by SVM with 81% and Logistic Regression with 80%. These results demonstrate the potential of ML techniques to predict cardiovascular disease with high reliability, enabling healthcare professionals to make informed decisions and improve patient outcomes. This research contributes to public health by providing a tool to predict cardiovascular disease more accurately, allowing for earlier interventions. The system helps medical practitioners prioritize high-risk patients and promotes preventive care measures. By enhancing prediction accuracy, this ML approach could lower healthcare costs and improve the quality of life, reducing global cardiovascular mortality rates.

Machine learning, Heart disease prediction, XGBoost, Support Vector Machine (SVM), cardiovascular disease

"Comparative analysis of AI Models for Cardiovascular Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 9, page no.d200-d205, September-2024, Available :http://www.jetir.org/papers/JETIR2409324.pdf

"Comparative analysis of AI Models for Cardiovascular Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 9, page no. ppd200-d205, September-2024, Available at : http://www.jetir.org/papers/JETIR2409324.pdf