فهرست نشریات علمی دسترسی آزاد ایران

This study examines how Hesitant Fuzzy Sets (HFS) and Machine Learning (ML) might improve healthcare predictive analytics. HFS, which accommodates uncertainty and hesitation in decision-making, is used to improve healthcare projections. Predictive analytics methods struggle with data ambiguity and imprecision, resulting in poor decision-making. Traditional ML algorithms may not be able to collect hesitant information, resulting in less accurate patient outcomes and treatment recommendations. The Integrating Hesitant Fuzzy Sets with ML (IHFS-ML) framework overcomes these issues by integrating HFS flexibility with advanced ML approaches. This connection allows the representation of ambiguous patient data for better healthcare analytics. Data pre-processing in the IHFS-ML framework improves healthcare analytics prediction. These methods transform uncertain fuzzy data into an ML-friendly format. Disease prediction, patient risk assessment, and therapeutic effectiveness analysis are recommended. The approach aims to improve healthcare decision-making and deliver new insights by merging hesitant and ambiguous information. IHFS-ML uses HFS to characterize imprecise and confusing patient data. These HFS are combined with powerful ML classifiers like Random Forest (RF) and Logistic Regression. The IHFS-ML system outperforms current prediction accuracy and reliability methods, suggesting it might transform healthcare analytics. HFS improves ML model interpretability, improving patient outcomes and healthcare decisions. Compared to other methods, the IHFS-ML model improves prediction analysis reliability by 99.7%, scalability by 97.6%, data pre-processing efficiency by 97.1%, interpretability by 98.9%, and accuracy by 97.8%.