Authors' Affiliations

* Ngozi Umeanowai, Department of Computing, College of Business and Technology, East Tennessee State University, Johnson City, TN. * Ojugo Joel Okhae, Department of Computing, College of Business and Technology, East Tennessee State University, Johnson City, TN.

Location

D.P. Culp Center Ballroom

Start Date

4-5-2024 9:00 AM

End Date

4-5-2024 11:30 AM

Poster Number

130

Name of Project's Faculty Sponsor

Ghaith Husari

Faculty Sponsor's Department

Computing

Classification of First Author

Graduate Student-Master’s

Competition Type

Competitive

Type

Poster Presentation

Presentation Category

Science, Technology and Engineering

Abstract or Artist's Statement

Cardiovascular disease (CVD) stands as a formidable global health threat, claiming the lives of over 17 million individuals annually, according to the World Health Federation. According to data provided by the World Health Organization (WHO), cardiac disease shows a significantly higher annual fatality rate when compared to any other disease. This research aims to develop and assess predictive models for heart disease using three distinguished Machine Learning algorithms: Decision Tree, Gaussian Naive Bayes, and RandomForestClassifier to understand what characteristics makes one most likely to from suffer Heart Disease. The dataset comprises a comprehensive set of features pertaining to the health and lifestyle of patients, with 19 columns and 308854 rows. Three different models were deployed, and the random forest classifier performed the best with accuracy of 92%. We conclude that machine learning models have great potential in aiding the diagnosis of patients with heart disease. Major determinants of the likelihood of heart disease include features such as BMI, weight, and green vegetables consumption. This machine learning model when implemented will help practitioners easily diagnose patients at risk of heart disease and help them spot underlying characteristics that put patients at risk of heart disease.

Download

Share

COinS
 
Apr 5th, 9:00 AM Apr 5th, 11:30 AM

Prediction of Heart Disease Using Machine Learning Models

D.P. Culp Center Ballroom

Cardiovascular disease (CVD) stands as a formidable global health threat, claiming the lives of over 17 million individuals annually, according to the World Health Federation. According to data provided by the World Health Organization (WHO), cardiac disease shows a significantly higher annual fatality rate when compared to any other disease. This research aims to develop and assess predictive models for heart disease using three distinguished Machine Learning algorithms: Decision Tree, Gaussian Naive Bayes, and RandomForestClassifier to understand what characteristics makes one most likely to from suffer Heart Disease. The dataset comprises a comprehensive set of features pertaining to the health and lifestyle of patients, with 19 columns and 308854 rows. Three different models were deployed, and the random forest classifier performed the best with accuracy of 92%. We conclude that machine learning models have great potential in aiding the diagnosis of patients with heart disease. Major determinants of the likelihood of heart disease include features such as BMI, weight, and green vegetables consumption. This machine learning model when implemented will help practitioners easily diagnose patients at risk of heart disease and help them spot underlying characteristics that put patients at risk of heart disease.