A Machine Learning Approach for Predicting Disease in Heart Using Logistic Regression

Abstract

The heart plays an important role in humans. The diagnosis and prediction part of the heart disease prediction process improves accuracy, completeness and accuracy in diseases where small errors can lead to fatigue problems and individual death. Heart-related deaths are numerous, counted daily, and increasing exponentially. To solve the problem, there is no way to predict disease knowledge. What is known in the field of ML provides an excellent guide for predicting all kinds of events trained from natural events. In this article, we use the UCI repository dataset for teaching and experimentation to calculate the machine learning accuracy of a cardiac disease prediction algorithm. These algorithms are k-nearest neighbors, decision trees, linear regression, and support vector devices (SVM). Anaconda (Jupiter) Notebook is a great tool for implementing Python programming. It contains various kinds of libraries and header files that make your data more accurate and unique.