Early Detection of Cardiovascular Disease Atrial Fibrillation

Cardiovascular disease remains a leading cause of mortality worldwide, and the early detection of its underlying conditions is crucial for effective prevention and management. This research paper presents a comprehensive approach to address the challenge of early prediction and detection of cardio-vascular diseases (CVDs) focusing on atrial fibrillation (AF). The proposed work integrates advanced machine learning techniques to study risk assessment and deep learning for ECG analysis. The Kaggle's Cardiovascular Disease Dataset and Cleveland's Heart Disease Dataset are used for the experimentation. The study also discusses practical application implementation, exploring the integration of developed models into healthcare systems for real-time risk assessment and disease detection. Results demonstrate that Random Forest Classifier gives superior performance with both datasets.