A prevalent cardiovascular condition that can alter an individual's life, heart disease is very expensive for both individuals and healthcare systems. Effective prevention strategies and early diagnosis are necessary as it progresses to be a major global societal well-being concern. Improving patient outcomes and cutting costs associated with healthcare requires early detection and proactive management. Based on a variety of patient characteristics and medical data, machine-learning characteristics, classifiers, and algorithms have demonstrated promise in the past several years in the prediction of cardiac disease risk. This abstract describes the application of machine learning methods to the construction of a prediction system for cardiac disease. This abstract analyzes patient data, such as electronic health records (EHR), medical histories, vital signs, and diagnostic test results, using sophisticated algorithms. The principal aim of the system is to precisely detect individuals who are susceptible to heart failure through the application of particle swarm optimization, forward selection, and backward elimination techniques. This will facilitate early intervention and tailored care, with 0 signifying the non-existence of heart disease and 1 signifying its presence.
Article Details
Unique Paper ID: 166953
Publication Volume & Issue: Volume 11, Issue 3
Page(s): 37 - 40
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024