Heart Disease Detection Using Machine Learning and Deep Learning

Abstract

Heart is responsible for different functions like blood circulation and supplying oxygen. These days, heart disease has become one of the major causes of death of many people. It is caused by different reasons like having an unhealthy lifestyle and having high levels of blood pressure, cholesterol, and other conditions. When the patient is detected with the presence of heart disease, he could be monitored and treated to save their lives. An ensemble model is built to detect the presence of disease by using various machine learning and deep learning models. Initially, the unwanted features are removed from the data by using feature selection methods like correlation matrix and fisher score. The ML models are then trained with the data and are stacked with a meta model. The stacking model is ensembled with the deep learning models used. K-Fold cross validation technique is used to train the models. The built ensemble model gave higher accuracy of 87.2%