Kahla, Mayssa BenKanzari, DalelAmor, Sana BenGhannouchi, Sonia AyachiMartinho, Ricardo2026-04-272026-04-272025-01-31Ben Kahla, M., Kanzari, D., Ben Amor, S., Ayachi Ghannouchi, S., & Martinho, R. (2025). Enhanced Fuzzy Score-Based Decision Support System for Early Stroke Prediction. ACM Transactions on Computing for Healthcare, 6(1), 7. https://doi.org/10.1145/3703461http://hdl.handle.net/10400.8/16196Article number - 7The research introduces an innovative approach for early stroke prediction using a fuzzy scoring-based Decision Support System. This approach encompasses three main modules: Mind map-based Data Modeling, Fuzzy scoring computing, and Machine Learning (ML)-Based Decision System. By incorporating fuzzy logic, the approach extracts valuable knowledge from imprecise and uncertain data. Combining the fuzzy stroke risk model with a ML-based decision support system aims to enhance stroke prediction accuracy and improve preventive measures and patient outcomes.According to the Global Health Observatory, stroke ranks second worldwide in causing dementia, right after Alzheimer’s disease. The mortality rate linked to dementia resulting from stroke is high because symptoms are often recognized late, and stroke can be misinterpreted as other brain disorders. Early detection and diagnosis of stroke is crucial. Therefore, increasing awareness of stroke symptoms and implementing preventive measures becomes imperative. Prompt intervention by healthcare professionals can improve outcomes and reduce long-term complications of stroke. The research introduces an innovative approach for early stroke prediction using a fuzzy scoring-based Decision Support System. This approach encompasses three main modules: Mind map-based Data Modeling, Fuzzy scoring computing, and Machine Learning (ML)-Based Decision System. By incorporating fuzzy logic, the approach extracts valuable knowledge from imprecise and uncertain data. Combining the fuzzy stroke risk model with a ML-based decision support system aims to enhance stroke prediction accuracy and improve preventive measures and patient outcomes. The approach’s effectiveness was validated using real clinical data and tested with various ML classifiers, including K-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The results showed a strong correlation between stroke cases and computed risk-scoring values. In comparison to predictions without fuzzy scoring and other related works, the stroke risk prediction using the proposed approach demonstrated higher accuracy, making it a promising method for early stroke detection and prevention.engStroke predictionFuzzy logicDecision support systemMachine learningHealthcare analyticsresearch article2026-04-23cv-prod-427388010.1145/37034612637-8051