Diagnosing Patient Stroke Status Using Modern AI After Dataset Balancing: A Comprehensive Comparative Study
Journal of Scientific Reports · 2025
DOI: 10.58970/jsr.1105 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Scientific Reports, 2025. Verfasst von Asmaa A. Mahdi.
Themen: Schlaganfall
Abstract (Originalsprache)
Accurate prediction of stroke patient status is vital for early intervention and clinical decision-making. This study systematically evaluates the latest artificial intelligence (AI) methods for stroke diagnosis on a balanced real-world dataset. Using Synthetic Minority Oversampling Technique (SMOTE) for class balancing, we compare traditional and modern AI models, including XGBoost, Random Forest, Deep Neural Networks, TabTransformer, and TabPFN (a transformer-based model for tabular data). Stacked ensemble models were also tested. Results demonstrate that transformer-based and ensemble approaches outperform classic methods, with stacked models and TabPFN achieving AUC scores up to 0.96 and accuracy exceeding 97%. Model interpretability was assessed using SHAP. The findings confirm that combining SMOTE with state-of-the-art AI yields robust and generalizable tools for stroke prediction, supporting safe and transparent clinical implementation.
Zitieren
APA
Mahdi, A. A. (2025). Diagnosing Patient Stroke Status Using Modern AI After Dataset Balancing: A Comprehensive Comparative Study. Journal of Scientific Reports. https://doi.org/10.58970/jsr.1105
Vancouver
Mahdi AA. Diagnosing Patient Stroke Status Using Modern AI After Dataset Balancing: A Comprehensive Comparative Study. Journal of Scientific Reports. 2025. doi:10.58970/jsr.1105
BibTeX
@article{Mahdi2025,
author = {Mahdi, Asmaa A.},
title = {Diagnosing Patient Stroke Status Using Modern AI After Dataset Balancing: A Comprehensive Comparative Study},
journal = {Journal of Scientific Reports},
year = {2025},
doi = {10.58970/jsr.1105}
}
EUVIMED