Heart Disease Prediction Using Supervised Algorithms in Machine Learning

Abstract

Abstract: There are various curable and incurable diseases which humans encounter in various stages of their life. Now-a-days due to poor nutrition and lifestyle modification, heart diseases are very prevalent. There are so many treatments available in medical field for heart diseases once predicted. However predicting heart disease is a challenging task. Therefore, predicting heart disease early helps people across the world to take the necessary actions before it reaches severe stage. From many years, machine learning approach has been used to deliver effective results in decision making and predictionaof heart diseaseausing different datasets available inathe medical industry. In this project we use Standard Scaler technique for feature selection. In this project an attempt has been made to predict or detect the presence of heart disease using five most commonly used supervised machine learning algorithms that are, Decision Tree (DT), RandomaForest (RF), Support Vector Machine (SVM), Logisticaregression (LR) and the K-nearestaneighbor (KNN) algorithms. Lastly the performance of these five supervised machine learning algorithms is summarized.