Predective Analysis of Heart Disease Based on Machine Learning Approaches

Abstract

Heart disease, alternatively known as cardiovascular disease, indicates various conditions that impact the heart and is the primary basis of death worldwide over the span of the past few decades. It associates many risk factors in heart disease and it is needed to get accurate, reliable, and sensible approaches to make an early diagnosis to achieve prompt management of the disease. Predicting and diagnosing heart disease is the biggest challenge in the medical industry and relies on factors such as the physical examination, symptoms and signs of the patient. Machine learning algorithms play an essential and precise role in the prediction of heart disease. A hybrid machine learning approach is used to predict stroke via imbalanced and in complete medical data set. The existing system uses a hybrid approach model by combining the characteristics of Random Forest and Linear model approaches collectively termed as HRFLM (Hybrid Random Forest Linear Model). This model makes use of all the features without any restrictions while selecting them and uses artificial neural networks with back propagation concept. Heart disease dataset is collected from UCI machine learning repository with 13 clinical features as input. The Cleveland dataset contains an attribute with the name num to show the diagnosis of the heart disease in patient on different scales from 0 to 4. The proposed system uses other combination of hybrid approach by combing RBF SVM along with Logistic regression. RBF SVM uses kernel function to solve non-linear problems and Logistic regression provides great training efficiency for timely improving the diagnosis of the heart disease.