An Extensive Review of Machine Learning and Deep Learning Techniques on Heart Disease Classification and Prediction
Publication Name
Archives of Computational Methods in Engineering
Abstract
Heart disease is a widespread global concern, underscoring the critical importance of early detection to minimize mortality. Although coronary angiography is the most precise diagnostic method, its discomfort and cost often deter patients, particularly in the disease's initial stages. Hence, there is a pressing need for a non-invasive and dependable diagnostic approach. In the contemporary era, machine learning has pervaded various aspects of human life, playing a significant role in revolutionizing the healthcare industry. Decision support systems based on machine learning, leveraging a patient's clinical parameters, offer a promising avenue for diagnosing heart disease. Early detection remains pivotal in mitigating the severity of heart disease. The healthcare sector generates vast amounts of patient and disease-related data daily. Unfortunately, practitioners frequently underutilize this valuable resource. To tap into the potential of this data for more precise heart disease diagnoses, a range of machine learning algorithms is available. Given the extensive research on automated heart disease detection systems, there is a need to synthesize this knowledge. This paper aims to provide a comprehensive overview of recent research on heart disease diagnosis by reviewing articles published by reputable sources between 2014 and 2022. It identifies challenges faced by researchers and proposes potential solutions. Additionally, the paper suggests directions for expanding upon existing research in this critical field.
Open Access Status
This publication is not available as open access