Design and Analysis of Improved Machine Learning Model for Heart Disease Prediction

Abstract

An early diagnosis of such a disease is a key responsibility for many health care professionals in order to safeguard their patients from contracting such an illness. Cardiovascular disease is one of the universal ailments that are prevalent in today's society. Due to the fact that even a minor error can result in serious health issues or even the individual's death, the diagnosis and treatment of heart-related diseases require an increased level of precision, perfection, and correctness. This is on account of there are a variety of death cases that are associated with the heart, and the number of people checking for these conditions is growing dramatically and gradually. In order to effectively handle the situation, there is an essential requirement for an expectation framework for practicing mindfulness towards disorders. With the application of Machine Learning techniques, it is possible to evaluate the data and determine the reasons that contribute to cardiac disorders such as coronary heart disease, arrhythmia, and dilated cardiomyopathy. Machine learning is playing an important role in the medical sector. This article provides a description of a preprocessing method and an analysis of the accuracy of the prediction of heart disease after the data including noise has been preprocessed. It has also been seen that the accuracy has improved after the preprocessing step has been taken.