Abstract
Heart diseases which are usually known as cardio vascular diseases are a wide range of conditions that affect the heart. These Cardiovascular diseases (CVDs) kill about 20.5 million people every year. It is also the primary cause for death worldwide over the past few decades. It is the need of the moment to obtain a precise and reliable approach to obtain an early diagnosis of the disease by automating the task and thus carrying out effective management. Many researchers used several data mining techniques to help medical professionals diagnose heart disease. However, using data mining can reduce the number of tests required. In order to reduce the number of deaths from heart disease, you must have a fast and effective detection technique. Early prediction can help people change their lifestyle. It also ensures proper medical treatment if needed. In order to reduce the number of deaths from heart disease, a rapid and effective detection technique is needed. The proposed work predicts the possibilities of heart diseases by implementing different data mining techniques such as logistic regression, nearby K nearest decision trees, support vector machine. Therefore, this article presents a comparative study analysing the performance of different machine learning algorithms. In this paper, a web based system which will predict the possibility or chance of person to get Heart Disease based on certain basic factors like cholesterol, diabetes, smoking etc. In this paper, a web based system is developed to predict thepossibility of getting a coronary heart disease. The test results verify that the Support Vector Machine achieved a maximum accuracy of 86.76% against other implemented ML algorithms
Keyword
Machine Learning, Health care, Cardio Vascular Diseases, Classification, Logistic regression, K-nearest neighbours, Decision trees, Support vector machine.
PDF Download (click here)
|