Authors : R. Renugadevi; Nivethitha. A

Volume/Issue : Volume 9 - 2024, Issue 3 - March

Google Scholar : https://tinyurl.com/4y684fbc

Scribd : https://tinyurl.com/28duc857

DOI : https://doi.org/10.38124/ijisrt/IJISRT24MAR444

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This day and age individuals are increasingly giving precedence to their material needs as opposed to self-care, leading to physical and mental strain. Cardiovascular diseases (CVDs) present a significant menace worldwide, causing about 17.9 million deaths annually which is roughly 32% of global mortality. Heart failure, which impacts over 550,000 individuals on a yearly basis, emerges as an urgent global health concern. The formulation of effective prediction techniques for heart failure proves to be imperative in lessening its repercussions. Linear and machine learning models are put into service to forecast heart failure utilizing a myriad of inputs, comprising clinical data. With the burgeoning population, the early detection and intervention for heart disease grow more complex. Heart disease prevalence has escalated to concerning levels, culminating in untimely deaths due to arterial plaque accumulation. The premature pinpointing of heart disease holds the potential to rescue many lives by upholding arterial wellness. Our research integrates supervised machine learning algorithms to predict heart disease presence, underscoring methods to enhance classifier efficacy. Null values within the dataset are managed through mean value imputation, whereas irrelevant attributes are expunged utilizing information- gain feature selection. By wielding breakthroughs in machine learning (ML), the key aim of this study is to design prognostic models for cardiovascular disease utilizing 12 clinical attributes. By capitalizing on a dataset offered by Davide Chicco and Giuseppe Jurman, encompassing 12 clinical features and 299 data points, the efficacy of three ML algorithms: Support Vector Machine (SVM), Random Forest, and Logistic Regression is evaluated. Our examination discloses that Logistic Regression showcases the most outstanding accuracy and likelihood in foretelling cardio vascular disease presence. This predictive model exhibits potential in aiding healthcare experts in curtailing heart disease- linked fatalities.

Keywords : Random Forest, Support Vector Machine, Logistic Regression, Machine Learning Model, Heart Failure Prediction, Disease Prediction, Accuracy.