Prediction of Cardiovascular Disease using Machine Learning Approach

Cardiovascular disease (CVD) In order to improve patient outcomes and lower death rates, cardiovascular disease (CVD), which is still a major worldwide health problem, requires rapid detection. In contrast to previous studies that employed the standard Cleveland dataset, which only included 303 instances, this study examines the use of sophisticated machine learning (ML) models for early CVD prediction using a large-scale dataset of 1190 instances. By integrating K-Nearest Neighbors (KNN), Gradient Boosting (GB), and Decision Trees (DT) in a hybrid strategy, the suggested model achieves an amazing accuracy of 88.78%, with precision of 89%, recall of 93%, and F1 Score of 91%. This hybrid model fills in the gaps in earlier studies by combining several machine learning methods to improve clinical decision-making and dramatically increase prediction accuracy. Furthermore, a user-friendly recommendation system based on Tkinter is created to help healthcare professionals recognize the risks of CVD and offer preventative measures according to each patient's unique risk profile. This study highlights the value of hybrid models in promoting early CVD detection and providing useful insights for medical practitioners by concentrating on readily available clinical data. The results highlight how important ML-driven tools might be in enhancing patient care, encouraging early treatments, and eventually saving lives. The importance of hybrid machine learning models in clinical practice is highlighted by this study, which makes a substantial addition to the field of healthcare decision-making.