Related Experiment Videos
Predictive Performance of Artificial Intelligence Models for Stroke Risk Stratification: A Systematic Review and
1Social Determinants of Health Research Center, Semnan University of Medical Sciences, Semnan, Iran.
Summary
Artificial intelligence (AI) models show promise for stroke risk stratification, with deep learning achieving high predictive performance. However, methodological inconsistencies limit widespread clinical use, necessitating standardized validation for AI in healthcare.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Public Health
Background:
- Stroke is a major global cause of death and disability, straining healthcare systems.
- Accurate stroke risk stratification is crucial for targeted prevention and resource optimization.
- Existing research on artificial intelligence (AI) for stroke risk assessment requires synthesis.
Purpose of the Study:
- To systematically evaluate the predictive performance of AI models for stroke risk stratification.
- To synthesize evidence through meta-analysis and explore implications for healthcare planning.
- To identify limitations and guide future research in AI-driven stroke prediction.
Main Methods:
- Systematic literature search across Web of Science, PubMed, and Scopus until January 2025.
- Adherence to PRISMA 2020 guidelines for systematic reviews.
- Meta-analysis of Area Under the Receiver Operating Characteristic Curve (AUC) values for AI algorithms.
Main Results:
- Deep learning (DL) models demonstrated strong discriminative performance with a pooled AUC of 0.955.
- Imaging-based DL models showed particular promise.
- Significant heterogeneity across studies impacted generalizability, despite sensitivity analysis.
Conclusions:
- AI, especially DL, shows high potential for stroke risk stratification.
- Methodological heterogeneity, limited external validation, and bias risk hinder current clinical implementation.
- Standardized reporting and validation frameworks (e.g., TRIPOD) are essential for future AI research in stroke prediction.