A COMPARATIVE ANALYSIS OF MACHINE LEARNING FOR THE EARLY DIAGNOSIS AND IDENTIFICATION OF CARDIOVASCULAR DISEASES

Abstract

With the advent of advanced digital technologies revolutionizing the healthcare sector through artificial intelligence and machine learning, there is a significant focus on accurate machine learning models to predict chronic heart diseases. The late detection and misdiagnosis of chronic diseases like cardiovascular disease can significantly increase the mortality rate. Therefore, a dependable, accurate, and workable system must identify these illnesses in time for appropriate treatment. Large-scale and sophisticated data processing has been automated using machine learning techniques and algorithms for various medical datasets. Several researchers have recently employed machine-learning techniques to assist the medical community and experts detect heart-related illnesses. The approach assists in predicting chronic diseases like heart failure and effective rehabilitation and timely management. This paper surveys various machine-learning models and compares their accuracy and other parameters in diagnosing heart-related disease. In this paper, we aim to compare various machine-learning models, and a predictive model is proposed for heart disease prediction based on the stacking of various classifiers. This model suggests fostering accurate decision-making. This proposed model will enhance prediction accuracy and eliminate anomalies, thus justifying the selection of the stacking classifier as the most accurate machine-learning model to predict heart failure about 98%.