Studies in Medical Sciences

en Performance Evaluation of Supervised Learning Algorithms in Modeling and Predicting Cardiovascular Disorders عمومى General پژوهشي(توصیفی- تحلیلی) Research   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. Cardiovascular Disorders, Machine Learning, Supervised Learning, Supervised Classification 57 65 http://umj.umsu.ac.ir/browse.php?a_code=A-10-5925-1&slc_lang=en&sid=1 Samad Gholipour gholipour.s@umsu.ac.ir 3700319475328460038765 3700319475328460038765 Yes Department of Computer Science, School of Engineering, Afagh Higher Education Institute, Urmia, Iran. Parinaz Eskandarian P_eskandarian@yahoo.com 3700319475328460038766 3700319475328460038766 No Department of Computer Science, School of Engineering, Afagh Higher Education Institute, Urmia, Iran. Hadi Lotfnezhad Afshar hadi.afshar@gmail.com 3700319475328460038767 3700319475328460038767 No Department of Health Information Technology, School of Allied Medical Sciences, Urmia University of Medical Sciences, Urmia, Iran. Sara Mohammadi Kalashani mohammadi.sa@umsu.ac.ir 3700319475328460038768 3700319475328460038768 No Department of Health Information Technology, School of Allied Medical Sciences, Urmia University of Medical Sciences, Urmia, Iran.