Publication Date: 2024/02/03
Abstract: The increasing breakthroughs in illness diagnosis classification and identification systems have led to a steady growth in the incorporation of machine learning in medical diagnostics. These systems provide crucial data aiding medical professionals in the early detection of fatal diseases, significantly enhancing patient survival rates. Globally, heart disease stands as the leading cause of death. The escalating rates of heart strokes among juveniles underscore the need for an early detection system to prevent potential incidents. Frequent and costly tests like electrocardiograms (ECG) are impractical for the general population. As a result, a simple and trustworthy method for estimating the risk of heart disease is suggested. This system makes use of machine learning techniques and algorithms including Support Vector Classifier (SVC), Random Forest, Naïve Bayes, and K-Nearest Neighbors (KNN). It provides a useful method of heart disease prediction by analyzing several factors that users provide through the frontend interface.
Keywords: No Keywords Available
DOI: https://doi.org/10.5281/zenodo.10527852
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT24JAN637.pdf
REFERENCES