Heart Disease Prediction Using Machine Learning

Abstract

A Web application built using the Flask framework, integrating user authentication, database management, and a predictive model for heart disease. Users can register, log in, and access a personalized dashboard displaying visualizations of age and gender distribution in a heart disease dataset. The application employs a logistic regression model trained on heart-related data to predict.Approximately 18 billion people die due to heart disease related problem over a year as per WHO.With increasing population, it gets further difficult to diagnose the disease. But in this growing technology world,Machine Learning techniques have accelerated the health sector by multiple researches. Thus, the objective of this paper is to build a ML model for heart disease prediction based on the related parameters. We have used adataset of UCI Heart disease prediction for this research, which consist of 13 different parameters related to Heart-disease. ML algorithms such as Random Forest, Support Vector Machine (SVM), Naïve Bayes and Decision tree have been used for developing the model. In this research we have also tried to find the correlations between the different attributes available in the dataset with the help of standard ML methods and then used them efficiently in predicting the chances of heart disease. Result shows that compared to other Machine learning techniques, Random Forest predicts with more accuracy in less time. This model can also be helpful to the medical practitioners at their clinic as decision support system.