Conference proceeding
Heart Disease Prediction using Machine Learning Techniques
2021 International Conference on Data Analytics for Business and Industry (ICDABI), pp 118-123
25 Oct 2021
Abstract
One of the main contributors to death cases globally is heart diseases. Heart illnesses have an impact on many people in the middle or elderly age which, in most instances, lead to serious health adverse effects such as strokes and heart attacks. Therefore, it is necessary to diagnose and predict heart diseases to prevent any serious health issues before they occur. In this paper, a provisional study and examination, using different state of the art Machine Learning Techniques namely Artificial Neural Networks, Decision Trees and Naïve Bayes, Random Forest, Logistic Regression, Support Vector Machines and XG Boost, were implemented at various evaluation stages to predict heart diseases. Results show that Random Forest technique has outperformed the other techniques and achieved a prediction accuracy of 95%.
Metrics
2 Record Views
15 citations in Scopus
Details
- Title
- Heart Disease Prediction using Machine Learning Techniques
- Creators
- Reldean Williams - University of JohannesburgThokozani Shongwe - University of JohannesburgAli N. Hasan - Higher Colleges of TechnologyVikash Rameshar - University of Johannesburg
- Publication Details
- 2021 International Conference on Data Analytics for Business and Industry (ICDABI), pp 118-123
- Publisher
- IEEE
- Number of pages
- 6
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Engineering Leadership and Society/Engineering Technology
- Scopus ID
- 2-s2.0-85124651655
- Other Identifier
- 991022004624204721