Volume 36, Issue 4 (12-2025)
Studies in Medical Sciences 2025, 36(4): 57-65 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Gholipour S, Eskandarian P, Lotfnezhad Afshar H, Mohammadi Kalashani S. Performance Evaluation of Supervised Learning Algorithms in Modeling and Predicting Cardiovascular Disorders. Studies in Medical Sciences 2025; 36 (4) :57-65
URL: http://umj.umsu.ac.ir/article-1-6490-en.html
URL: http://umj.umsu.ac.ir/article-1-6490-en.html
Department of Computer Science, School of Engineering, Afagh Higher Education Institute, Urmia, Iran. , gholipour.s@umsu.ac.ir
Abstract: (219 Views)
Introduction: Cardiovascular disorders remain one of the leading causes of morbidity and mortality worldwide, highlighting the importance of accurate and reliable predictive models for early identification of high-risk individuals. Recent advances in supervised machine learning have provided new opportunities for modeling complex clinical data; however, comparative evidence regarding the performance of different algorithms under consistent evaluation settings remains limited. Accordingly, this study aimed to systematically compare widely used supervised learning classifiers using standardized preprocessing and clinically relevant metrics.
Materials and Methods: The objective of this study was to comparatively evaluate the performance of selected supervised learning algorithms in modeling and predicting cardiovascular disorders using a structured clinical dataset. In this descriptive modeling study, a publicly available cardiovascular dataset comprising 303 patient records and 13 routinely collected clinical features was analyzed. Data preprocessing included cleaning, categorical encoding, and normalization. Five widely used supervised learning algorithms Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Random Forest were implemented using RapidMiner Studio. Model performance was evaluated using accuracy, sensitivity, specificity, precision, and F1-score based on an 80/20 train–test split, with stratified 5-fold cross-validation applied within the training set to improve stability and reduce split-dependence.
Results: Among the evaluated models, the Random Forest algorithm demonstrated the highest overall performance, achieving an accuracy of 91.2%, sensitivity of 88.7%, specificity of 92.9%, precision of 89.4%, and F1-score of 89.0%. ANN (accuracy 88.7%) and SVM (accuracy 86.9%) showed moderate performance, whereas Decision Tree yielded the lowest accuracy (83.1%) and sensitivity (79.4%). This superior performance can be attributed to the ensemble structure of Random Forest, which reduces variance and overfitting while effectively capturing nonlinear relationships among clinical variables. Although the dataset size was relatively modest, it is widely used as a benchmark in cardiovascular prediction studies and is considered sufficient for comparative algorithm evaluation.
Conclusion: The findings indicate that ensemble-based supervised learning models, particularly Random Forest, may offer more robust predictive performance compared to single classifiers when applied to structured cardiovascular data. By emphasizing sensitivity and specificity alongside accuracy, this work provides a transparent comparative baseline for cardiovascular prediction on benchmark clinical features. While the results support the methodological value of such models for analytical and research-oriented purposes, further validation using larger and independent clinical datasets is required before real-world clinical implementation.
Materials and Methods: The objective of this study was to comparatively evaluate the performance of selected supervised learning algorithms in modeling and predicting cardiovascular disorders using a structured clinical dataset. In this descriptive modeling study, a publicly available cardiovascular dataset comprising 303 patient records and 13 routinely collected clinical features was analyzed. Data preprocessing included cleaning, categorical encoding, and normalization. Five widely used supervised learning algorithms Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Random Forest were implemented using RapidMiner Studio. Model performance was evaluated using accuracy, sensitivity, specificity, precision, and F1-score based on an 80/20 train–test split, with stratified 5-fold cross-validation applied within the training set to improve stability and reduce split-dependence.
Results: Among the evaluated models, the Random Forest algorithm demonstrated the highest overall performance, achieving an accuracy of 91.2%, sensitivity of 88.7%, specificity of 92.9%, precision of 89.4%, and F1-score of 89.0%. ANN (accuracy 88.7%) and SVM (accuracy 86.9%) showed moderate performance, whereas Decision Tree yielded the lowest accuracy (83.1%) and sensitivity (79.4%). This superior performance can be attributed to the ensemble structure of Random Forest, which reduces variance and overfitting while effectively capturing nonlinear relationships among clinical variables. Although the dataset size was relatively modest, it is widely used as a benchmark in cardiovascular prediction studies and is considered sufficient for comparative algorithm evaluation.
Conclusion: The findings indicate that ensemble-based supervised learning models, particularly Random Forest, may offer more robust predictive performance compared to single classifiers when applied to structured cardiovascular data. By emphasizing sensitivity and specificity alongside accuracy, this work provides a transparent comparative baseline for cardiovascular prediction on benchmark clinical features. While the results support the methodological value of such models for analytical and research-oriented purposes, further validation using larger and independent clinical datasets is required before real-world clinical implementation.
Keywords: Cardiovascular Disorders, Machine Learning, Supervised Learning, Supervised Classification
References
1. World Health Organization. Cardiovascular diseases [Internet]. Geneva: World Health Organization; 2020 [cited 2026 Jul 22]. Available from: https://www.who.int/health-topics/cardiovascular-diseases. [URL]
2. Islam MA, Majumder MZH, Miah MS, Jannaty S. Precision healthcare: A deep dive into machine learning algorithms and feature selection strategies for accurate heart disease prediction. Comput Biol Med. 2024;176:108432. doi:10.1016/j.compbiomed.2024.108432. [DOI:10.1016/j.compbiomed.2024.108432] [PMID]
3. Ali MM, Paul BK, Ahmed K, Bui FM, Quinn JMW, Moni MA. Heart disease prediction using supervised machine learning algorithms: Performance analysis and comparison. Comput Biol Med. 2021;136:104672.doi:10.1016/j.compbiomed.2021.104672. [DOI:10.1016/j.compbiomed.2021.104672] [PMID] [PMCID]
4. Austin PC, Tu JV, Ho JE, Levy D, Lee DS. Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. J Clin Epidemiol. 2013;66(4):398-407. doi:10.1016/j.jclinepi.2012.11.008. [DOI:10.1016/j.jclinepi.2012.11.008] [PMID] [PMCID]
5. Noroozi Z, Orooji A, Erfannia L. Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction. Sci Rep. 2023;13(1):22588.
https://doi.org/10.1038/s41598-023-49962-w [DOI:10.1038/s41598-023-49962-w.] [PMID] [PMCID]
6. Srinivas, K., B.K. Rani, and A. Govrdhan, Applications of data mining techniques in healthcare and prediction of heart attacks. International Journal on Computer Science and Engineering (IJCSE), 2010. 2(2): 250-255. [GOOGLE SCHOLAR]
7. Dehkordi SK, Sajedi H. Prediction of disease based on prescription using data mining methods. Health Technol. 2019;9(1):37-44. doi:10.1007/s12553-018-0246-2. [DOI:10.1007/s12553-018-0246-2]
8. Al Bataineh A, Manacek S. MLP-PSO Hybrid Algorithm for Heart Disease Prediction. Journal of Personalized Medicine. 2022;12(8):1208. doi:10.3390/jpm12081208. [DOI:10.3390/jpm12081208] [PMID] [PMCID]
9. 1. Jan M, Awan AA, Khalid MS, Nisar S. Ensemble approach for developing a smart heart disease prediction system using classification algorithms. Research Reports in Clinical Cardiology. 2018 ;9:33-45. doi:10.2147/RRCC.S172035. [DOI:10.2147/RRCC.S172035]
10. Soni J, Ansari U, Soni S, Sharma D. Predictive data mining for medical diagnosis: An overview of heart disease prediction. International journal of computer applications. 2011;17(8):43-8. [DOI:10.5120/2237-2860]
11. Mansoor H, Elgendy IY, Segal R, Bavry AA, Bian J. Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction: A machine learning approach. Heart & Lung. 2017;46(6):405-11. doi:10.1016/j.hrtlng.2017.09.003. [DOI:10.1016/j.hrtlng.2017.09.003] [PMID]
12. Le HM, Tran TD, Van Tran L. Automatic heart disease prediction using feature selection and data mining technique. Journal of Computer Science and Cybernetics. 2018;34(1):33-48. [DOI:10.15625/1813-9663/34/1/12665]
13. Tarawneh M, Embarak O, editors. Hybrid Approach for Heart Disease Prediction Using Data Mining Techniques. Advances in Internet, Data and Web Technologies; 2019 2019//; Cham: Springer International Publishing. doi:10.1007/978-3-030-12839-5_41. [DOI:10.1007/978-3-030-12839-5_41]
14. Chitra R, Seenivasagam V. Heart disease prediction system using supervised learning classifier. Bonfring International Journal of Software Engineering and Soft Computing. 2013;3(1):1-7. [DOI:10.9756/BIJSESC.4336]
15. Latha CBC, Jeeva SC. Improving the accuracy of prediction of heart disease risk based on ensemble classification techniques. Informatics in Medicine Unlocked. 2019;16:100203. doi:10.1016/j.imu.2019.100203. [DOI:10.1016/j.imu.2019.100203]
16. Mohan S, Thirumalai C, Srivastava G. Effective heart disease prediction using hybrid machine learning techniques. IEEE access. 2019;7:81542-54. [DOI:10.1109/ACCESS.2019.2923707]
17. Ramalingam V, Dandapath A, Raja MK. Heart disease prediction using machine learning techniques: a survey. International Journal of Engineering & Technology. 2018;7(2.8):684-7. [DOI:10.14419/ijet.v7i2.8.10557]
18. Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI); 1995 Aug 20-25; Montreal, Quebec, Canada. San Francisco (CA): Morgan Kaufmann Publishers; 1995: 1137-1143 [URL]
19. El-Hasnony IM, Elzeki OM, Alshehri A, Salem H. Multi-Label Active Learning-Based Machine Learning Model for Heart Disease Prediction. Sensors [Internet]. 2022; 22(3):1184. doi: 10.3390/s22031184. [DOI:10.3390/s22031184] [PMID] [PMCID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
