Heart Disease Prediction Through Ensemble Learning Model

Cardiovascular disease is one of the most life threatening disease all over world and under distributed age groups. Mortality rates of heart disease around the world is high comparing to any other diseases. Thus heart disease prediction gains importance study and improvement in prediction is needed to save human lives. Once the disease is early predicted, with proper medications, the human lives can be saved. The delay in detection leaves to complexity and the rates of mortality increases. Medical diagnosis industry is gaining pace with latest technologies such as machine learning, deep learning. Medical treatment industry is already developed with highly effective treatments. Machine learning (ML) one of the best diagnosis for effective decision making. The proposed system aims to study cardiovascular disease prediction on UCI repository, Cleveland dataset with a novel ensemble learning strategy. The algorithm used are Decision Tree classifier and Random forest classifier for learning. The proposed ensemble model exploit use of both model to create novel learning method. The experimental study proved that the proposed model is highly optimized model of existing machine learning classification algorithms.