Cardiovascular disease remains the leading cause of mortality worldwide, driving substantial research investment and necessitating robust evaluation of institutional research performance. This study employed the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to evaluate and rank the research performance of 30 leading universities based on their contributions to the top 100 highly cited cardiovascular medicine articles from 2010–2026, extracted from Scopus. Three evaluation criteria were selected: Unique Authors (minimized as a resource input measure), Total Citations (maximized as an impact indicator), and Number of Papers (maximized as a productivity measure), with equal weights (33.3% each) assigned to all criteria. TOPSIS analysis revealed substantial variation in institutional performance, with Harvard University emerging as the top-performing institution (TOPSIS score: 0.6050), demonstrating dominance across all criteria with 228 unique authors, 9,430 citations, and 83 papers, followed by Cleveland Clinic (0.4882), University of Toronto (0.4537), and Mayo Clinic (0.4158). US institutions dominated the ranking, accounting for 27 of 30 universities with an average TOPSIS score of 0.4112, while Canadian institutions achieved an average of 0.4078. The analysis identified an “efficiency gap” between high-citation, low-paper institutions (e.g., UCSF with 87.4 citations per paper and 1.3 authors per paper) and those demonstrating the inverse pattern. The findings highlight the dominance of US institutions, varying institutional strategies (high-volume vs. high-impact approaches), and the concentration of research activity among leading academic medical centers, with the TOPSIS methodology offering a robust framework for multidimensional research evaluation that can inform institutional benchmarking, strategic planning, and resource allocation in cardiovascular medicine.

Early identification of individuals at high risk of stroke is essential for improving prognosis, guiding preventive strategies, and reducing the burden of stroke-related disability. This study presents a comparative machine learning approach for stroke risk prediction using structured healthcare data containing demographic, lifestyle, and clinical variables. The proposed approach evaluates five supervised classification models, namely Random Forest, Support Vector Machine, XGBoost, LightGBM, and CatBoost, to identify the most suitable model for stroke risk classification. A systematic preprocessing pipeline was applied, including median imputation for missing BMI values, categorical feature encoding, stratified data splitting, feature scaling, and Synthetic Minority Over-sampling Technique (SMOTE) to address severe class imbalance in the training data. Model performance was assessed using accuracy, precision, recall, and F1-score Among the evaluated models, CastBoost achieved the most balanced overall performance, while SVM showed higher sensitivity in detecting stroke cases. These findings indicate that model selection should depend on the intended clinical purpose, particularly whether the goal is balanced prediction or improved detection of possible stroke cases. Overall, this study highlights the potential of machine learning to support early stroke risk assessment and preventive healthcare decision-making using routinely available structured health data.