An Empirical Study of Machine Learning Methods for Analyzing Cardiovascular Disease

Abstract

The entire body depends on the heart to supply plasma to every part of it. Heart disease is diagnosed using conventional medical procedures (like angiography), which come with a greater price tag and serious health hazards. Previously, a range of information collection, information sources, and machine learning techniques were applied. Several study articles dedicated to a specific data standard have been published in multiple previous evaluations. As a result, scientists have created a variety of robotic detection systems using machine learning algorithms in addition to discovery methodologies. Simple, reliable, and efficient methods for detecting cardiovascular disease are provided by ML-based computer-aided diagnostics. In order to assess the prognosis of cardiovascular illness, this effort will analyze computerized diagnostics utilizing a variety of methodologies. With an F-1 score of 98.52, 99.25% precision, and 98.53% accuracy, the Random Forest model outperforms the other models.