Heart Disease Prediction with SVM algorithm

Author Reg. ID: TIJER_151378

Published Paper Id: TIJER2403019

Published In: Volume 11 Issue 3, March-2024

Abstract: Cardiovascular disease, commonly known as heart disease, stands as a pervasive cause of mortality globally, presenting a substantial menace to public health. Data from the World Health Organization reveals that in 2017 alone, cardiovascular disease precipitated a staggering 17.9 million fatalities worldwide. Regrettably, the toll of cardiovascular disease continues to escalate annually, particularly in emerging nations. Reports indicate that nearly 80% of fatalities attributed to cardiac ailments transpire within middle and low-income countries, where the average age at which these fatalities occur is notably younger than in their high-income counterparts. Within the realm of medicine, discerning the presence of heart disease poses a formidable challenge. This intricate task hinges upon the meticulous analysis of extensive clinical and pathological datasets. Consequently, there has been a surge of interest among both researchers and clinical practitioners in devising more efficient and precise methodologies for predicting heart disease. The imperative of timely and accurate diagnosis in the early stages of cardiac ailments cannot be overstated, given the paramount importance of time in mitigating adverse outcomes. As the leading cause of mortality worldwide, the prognostication of heart disease assumes profound significance when undertaken preemptively. In recent years, machine learning has emerged as a dynamic and dependable ally in the medical domain, furnishing invaluable tools for disease prediction through rigorous training and testing protocols. The focal objective of this endeavor is to scrutinize various prediction models for heart disease, with a particular emphasis on discerning pivotal cardiac features utilizing the SVM algorithm.

Keywords: Machine Learning, Heart disease, Data Analysis, Chest Discomfort, Blood pressure, Sugar levels, Logistic Regression, Decision tree, K Nearest Neighbor, Accuracy, Precision, Recall, Heart disease prediction

Downloads: 00045

Page No: a115-a120

Country: Ranipettai, Tamilnadu, India

Research Area: Science All

Published Paper URL: https://tijer.org/TIJER/viewpaperforall?paper=TIJER2403019

Published Paper PDF: https://tijer.org/TIJER/papers/TIJER2403019

Click Here to Download This Article

Article Preview