Heart Disease Prediction Using Machine Learning

EasyChair Preprint 10222

Abstract

Early identification is essential for successful treatment of heart disease, which is an increasing health problem. Although accurate diagnosis is required, it may be dangerous. The goal of this work is to create a system that employs multiple machine learning methods, such as logistic regression, to predict the likelihood of a heart attack based on a patient's medical history. To better forecast my own heart attacks is the aim.

Big data, machine learning, and data mining techniques are crucial for predicting cardiac disease. These models can be used by medical experts to pinpoint people who are at risk of acquiring heart disease. Predicting heart disease is a critical difficulty in medicine since it is a leading cause of mortality globally. This study discusses several data mining techniques for predicting heart disease..

Using logistic regression, our algorithm effectively determines whether a patient has heart disease. Our approach increases the accuracy of cardiac diagnosis when compared to previously employed classifiers like Naive Bayes. Physicians may deliver better patient care while spending less money by utilising our cardiovascular preventive technologies.

Doctors may provide better patient care while spending less money by utilising our cardiovascular preventive solutions.

Keyphrases: Cardiovascular disease, Data Mining, Heart Disease, machine learning, prediction

@booklet{EasyChair:10222,
  author    = {Deepanshu and Prabhjot Kaur and Urvi Jasrotia},
  title     = {Heart Disease Prediction Using Machine Learning},
  howpublished = {EasyChair Preprint 10222},
  year      = {EasyChair, 2023}}