Analyzing and Contrasting Machine Learning Algorithms for Predicting the Risk of Cardiovascular Disease

Cardiovascular conditions (CVDs) remain a major global health concern, challenging early threat assessment and forestallment. In this study, we employ three distinct machine learning algorithms - K Nearest Neighbors(KNN), Random Forest, and Decision Tree - to prognosticate the threat of cardiovascular conditions. The dataset used in this exploration consists of 14 essential features and has been sourced from Kaggle, a prominent platform for data wisdom competitions. Our primary idea is to estimate the prophetic performance of these algorithms and determine which algorithm gives us maximum accuracy. Among the algorithms examined, KNN classifier emerges as the top pantomime, achieving an accuracy of 84.48. This result showcases the efficacity of the KNN algorithm in handling the complexity of CVD threat vaticination. These findings give critical guidance for healthcare professionals and experimenters in enforcing effective prophetic models for early cardiovascular complaint threat identification and intervention.

I. Introduction

Cardiovascular conditions (CVDs) stand as a leading cause of morbidity and mortality worldwide, contributing to a substantial burden on healthcare systems and public health. Beforehand threat vaticination and forestallment are consummate in the battle against these life- hanging conditions. According to the data from World Health Organization, heart problem is the leading cause of mortality encyclopedically, performing in 17.9 million deaths annually [1]. But the data collected is veritably massive and, numerous times, this data can be veritably noisy. These datasets, which are too inviting for mortal minds to comprehend, can be fluently explored using colorful machine literacy ways[3]. The ways that are presently used to prognosticate and diagnose heart complaint are primarily grounded on the analysis of a case's medical history, symptoms, and physical examination reports by croakers[2]. At most times, it is delicate for medical experts to directly prognosticate a case's heart complaint, where they can prognosticate with over to 67 delicacy because, presently, the opinion of any complaint is done concerning the analogous symptoms observed from preliminarily diagnosed cases. Hence, the medical field requires an automated intelligent system for the accurate vaticination of heart complaint. To propagate this exploration, we start with enforcing machine literacy algorithms:- 1.

KNN Nearest Neighbor.

2.

Decision Tree.

3.

Random Forest