A Comparison of Supervised Machine Learning Algorithms on Heart Disease Risk Predictions - Clinical performance comparison

Aug 3, 2026

Upload by Anda

Cardiac disease detection and prediction remain challenging for clinicians, often requiring substantial time and resources and leading to costly hospital or clinic interventions. Early identification of risk can enable timely treatment and prevention before deterioration. This study applies supervised machine learning models using a dataset of diverse human health parameters to train and test predictive systems for cardiac illness. Multiple AI/ML algorithms are implemented and their performance compared to assess strengths and limitations. Results support using these models to flag at-risk individuals for proactive clinical intervention and preventive care.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Motivation

Study Setup

Naïve Bayes

K Neighbor Classifier

Logistic Regression

Decision Tree

ISSN: 2321-8363 Impact Factor: 6.308 (An Open Accessible, Fully Refereed and Peer Reviewed Journal) A Comparison of Supervised Machine Learning Algorithmson Heart Disease Risk Predictions Manoj Dharmawardhana1*, Ganesha Thondilage2 1University of Westminster, No 115, New Cavendish Street, London, UK 2Informatics Institute of Technology, No 57, Ramakrishna Road, Colombo 6, Sri Lanka [E-mail: w1790366@my.westminster.ac.uk](E-mail: w1790366@my.westminster.ac.uk) Received date: 02 June 2023, Manuscript No. ijcsma-23-101128; Editor assigned: 04-June-2023, Pre QC No ijcsma-23-101128 (PQ); Reviewed: 16 June 2023, QC No. ijcsma-23-101128 (Q); Revised: 22 June 2023, Manuscript No. ijcsma-23-101128 (R); Published date: 30 June 2023 DOI. 10.5281/zenodo.8371681 Abstract Cardiac disease detection and prediction have historically presented challenges for physicians, often requiring significant time and resources. Consequently, expensive therapies and operations are administered in hospitals and clinics to treat cardiac disorders. Therefore, early anticipation of cardiac disease holds immense potential in enabling individuals worldwide to seek timely treatment before the condition escalates. In recent years, heart disease has emerged as a prevalent global health issue, primarily attributed to excessive alcohol and tobacco use, as well as a lack of physical activity. This paper focuses on the utilization of machine learning methods to forecast cardiac illnesses. A comprehensive dataset encompassing diverse human health parameters is employed for training and testing purposes. Various AI and ML algorithms are implemented to predict cardiac disorders, and their performance is rigorously compared. The findings of this study contribute to the growing body of research on cardiac disease detection and prediction, highlighting the efficacy of machine learning approaches. By leveraging these algorithms, healthcare professionals can potentially identify individuals at risk of cardiac disease at an early stage, enabling ISSN: 2321-8363 Impact Factor: 6.308 (An Open Accessible, Fully Refereed and Peer Reviewed Journal) proactive intervention and preventive measures. Moreover, the comparative analysis of multiple machine learning algorithms offers valuable insights into their respective strengths and limitations, aiding in the selection of the most suitable approach for specific clinical scenarios. Keywords: Supervised Machine Learning; Heart Disease Prediction; Healthcare; Machine Learning Algorithms 1. Introduction The human heart, as the central organ responsible for pumping blood and ensuring the delivery of oxygen and nutrients to every cell in the body, is undeniably the lifeline of human existence. Its critical role in sustaining life underscores the profound significance of maintaining optimal cardiac health. However, the prevalence of heart diseases has escalated dramatically in recent years, emerging as a leading cause of mortality worldwide [1] . These diseases encompass a broad spectrum of conditions that disrupt the normal functioning of the heart, posing substantial threats to individual well-being and public health. Coronary Artery Disease (CAD) primarily arises from the obstruction of coronary arteries, impeding the normal flow of blood. These arteries play a crucial role in delivering oxygenated blood to various organs and tissues throughout the human body. Recent statistics indicate that CAD affects a staggering population of over 26 million individuals [2] . 1.1 Motivation The occurrence of heart diseases in the human body stems from a multitude of factors. These factors can be broadly categorized into two types of risk factors that contribute to the development of heart diseases. The first category encompasses uncontrollable factors such as family history, age, and gender, while the second category comprises modifiable risk factors that can be managed, such as smoking habits. Detecting heart diseases

FAQs

Why is early heart disease risk prediction important in the study?

The document explains that early anticipation enables timely treatment and preventive measures before the condition escalates, reducing reliance on costly interventions later.

What dataset is used to train and test the machine learning models?

A comprehensive dataset is used that includes diverse human health parameters for both training and testing predictive models.

Which supervised machine learning algorithms are compared?

The paper focuses on four supervised algorithms: Naïve Bayes, K Neighbor (K-Nearest Neighbor) Classifier, Logistic Regression, and Decision Tree.

Aug 3, 2026

Upload by Anda