Analysis of Heart attack Prediction Using Supervised Machine Learning Algorithms with an Electrotherapeutic Approaches

In recent days, heart attacks are considered to be the biggest concern in the health care industry. In most of the times, it is quite difficult for doctors to identify the disease. So, it results in more death of people. If the disease can be identified at an earlier stage, it will be easier to prevent the death rate. It is impossible for an individual to frequently undergo costly tests like ECG. Prediction of heart attack requires more precision, perfection and accuracy. A little mistake can cause unwanted problem or death of the person, there are numerous death cases related to heart which are increasing gradually day by day. As the medical diagnosing is a decision-making technique, an intelligent decision system can be implemented by using various machine learning techniques. Machine Learning (ML), a part of Artificial Intelligence technique (AI) which provides a support in predicting data. The use of machine learning technique is gradually increasing in the medical field. The main aim of this paper is to reduce the efforts and risk made by doctors in predicting heart attacks. One of the biggest challenges in healthcare is to record and analyse huge amount of information about patients. The main objective is to investigate different factors and its impacts in identifying heart attack. The factors such as chest pain, age, gender, fasting blood sugar level and cholesterol level. In this paper an analysis is done to check the performance of various heart disease prediction techniques, namely k-nearest neighbour (KNN), random forest,decision tree, linear regression and support vector machine (SVM).In this research, an accuracy of various machine learning algorithms for predicting heart attacks are obtained.