Employing Deep Learning for Early Prediction of Heart Disease

Abstract

Numerous people get affected by heart diseases due to their daily inappropriate living habits. Prediction of heart disease at an earlier stage becomes crucial to prevent the disease or in the treatment of the disease. However, predicting the heart condition accurately as per symptoms is challenging, even for experienced doctors. The most demanding job is to anticipate the illness accurately. The medical or health sector is generating a large amount of data about heart disease every year. The easy availability of data in medical and healthcare fields and the accurate analyzing techniques for the medical data of earlier patients make it possible to predict various diseases. Machine learning algorithms may be used with medical information to forecast cardiac illness successfully. Developing the predictor of heart disease using machine learning algorithms is more beneficial than conventional approaches for accurate predictions of disease. This article proposes a deep learning model better than the other existing machine learning techniques. The dataset utilized for prediction is the heart dataset available at https://www.kaggle.com/. The proposed model has been compared with k-nearest neighbors (kNN), logistic regression (LR), support vector machine (SVM), Naïve Bayes (NB), decision tree (DT), random forest (RF), and artificial neural network (ANN). The comparative analysis of various machine learning techniques establishes the proposed model as the most precise heart disease predictor.