Early Detection of Heart Disease Using Machine Learning Approach

Abstract

Heart attack is one of the leading causes of morbidity in the worldwide population. Cardiovascular disease is one of the major diseases involved in clinical data analysis or one of the most important part for forecasting. Early detection of cardiovascular diseases can help to reduce high-risk condition for heart patients to make individual decisions for their lifestyle adjustments, mitigating the challenges. Early detection of heart disease has been explored in this study using a machine-learning approach. Additionally, we used sampling strategies to deal with disparate datasets. The overall risk is estimated using a variety of machine-learning techniques. On Kaggle, the Heart Disease dataset is accessible and open for all. In present study testing set used this dataset. The ultimate objective is to determine whether the patient has a “10-year risk of developing coronary heart disease” (CHD). The dataset contained thirteen features that provided patient data, and the authors used machine learning algorithms to diagnose cardiac problems with 98.8% accuracy.