Use of Machine Learning Techniques in the Prediction of Heart Disease
B. T. Krishna, Raghupatruni Durgadinesh, Killi Suryapratap, Gedela Vinaykumar
Abstract
Machine learning is a fiction that belongs to the computer science realm; in reality, it is an interdisciplinary subject with applications in every field. Machine learning techniques are being used in signal processing, picture and speech recognition, electronic design automation, and self-driving cars, to name a few. The goal of this paper is to determine the method that provides the highest level of accuracy about heart disease. The rationale for this research is that if we can anticipate heart disease as early as feasible, we can lower the risk and begin treatment as soon as possible. We can also shorten the time it takes to diagnose, and we can handle enormous amounts of medical data with ease using machine learning techniques. We chose Python to implement the project since it is simple to learn, understand, and implement. Python is free and open source, and it comes with a number of machine learning libraries. On the training dataset, we trained the model using several methods such as Logistic Regression, k Nearest Neighbors(kNN), Decision Trees, and Random Forest in order to predict heart disease, and we tested the model's accuracy using the testing data set. The performance of the Random Forest algorithm is found good compared to the remaining three algorithms. Random forest algorithm best fits the data with an accuracy of 88.16%.