EUVIMEDEUVIMED entdecken
Crossref

Diagnosing Patient Stroke Status Using Modern AI After Dataset Balancing: A Comprehensive Comparative Study

Asmaa A. Mahdi

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →