Heart Disease Evaluation with Deep Learning and Machine Learning

Abstract

All over the world is affected by the disease which is named as heart disease. The main reason behind the heart disease is our busy life, as the person is affected not only by office work but also by personal problems. This mortality rate is too high. We can predict this disease with the help of Machine Learning (ML) and Deep Learning (DL) prediction models. In this paper, to reach the accuracy we worked on three ML & DL models. For this paper we use ML models named as: SVM (Support Vector Machine), LR (Logistic Regression) & Naïve Bayes. DL models named as: CNN (Convolutional Neural Network), RNN (Recurrent Neural Network) & LSTM (Long Short Term Memory). The accuracy obtained in this study is made up of the 85% accuracy of Logistic Regression, the 89% accuracy of SVM, and the 85% accuracy of Naive Bayes. LSTM has an accuracy of 83%, RNN has an accuracy of 91%, and CNN has an accuracy of 83%. The study’s findings indicate that the RNN model is the most accurate, coming in at 90%, and from this we can say that it is the best at predicting heart disease.