PREDICTING HEART ISSUES WITH MACHINE LEARNING: A FORWARD-LOOKING APPROACH

Abstract

Globally, the healthcare industry looks after billions of people and produces massive volumes of data. As the machine learning-based algorithms analyze the complex medical data, they are producing better insights. This paper classifies a cardiovascular dataset using a variety of state-of-the-art Supervised Machine Learning techniques that are specifically used for sickness prediction. The results showed that the Decision Tree classification model performed better in predicting cardiovascular ailments than the Naive Bayes, Logistic Regression, Random Forest, SVM, and KNN based approaches. At 73% accuracy, the Decision Tree produced the best results. This technique could help doctors detect cardiac issues early and administer the appropriate treatment.