Predictive Performance of Artificial Intelligence Models for Stroke Risk Stratification: A Systematic Review and Meta-Analysis.
Background: Stroke remains a leading cause of mortality, long-term disability, and healthcare expenditure worldwide, placing substantial strain on healthcare systems, particularly in low- and middle-income countries. Effective risk stratification can facilitate targeted prevention strategies, optimi...
| Publicado en: | Inquiry (00469580) Vol. 63; pp. 1 - 15 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Sage Publications Inc.
7/28/2026
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=195711689&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 195711689 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00469580 INQ jtl: Inquiry (00469580) issn: 00469580 maglogo: Y pubinfo: dt: 7/28/2026 vid: 63 pid: 344 pub: Sage Publications Inc. artinfo: ui: 195711689 10.1177/00469580261466517 ppf: 1 ppct: 14 formats: tig: atl: Predictive Performance of Artificial Intelligence Models for Stroke Risk Stratification: A Systematic Review and Meta-Analysis. aug: au: Nopour, Raoof affil: Social Determinants of Health Research Center, Semnan University of Medical Sciences, Semnan, Iran su: Stroke prevention Risk assessment World Wide Web Prediction models Artificial intelligence Medical care Meta-analysis Descriptive statistics Systematic reviews MEDLINE Support vector machines Artificial neural networks Stroke Online information services Health care rationing Algorithms Disease risk factors sug: subj: Stroke prevention Risk assessment World Wide Web Prediction models Artificial intelligence Medical care Meta-analysis Descriptive statistics Systematic reviews MEDLINE Support vector machines Artificial neural networks Stroke Online information services Health care rationing Algorithms Disease risk factors keyword: artificial intelligence deep learning machine learning predictive models stroke ab: Background: Stroke remains a leading cause of mortality, long-term disability, and healthcare expenditure worldwide, placing substantial strain on healthcare systems, particularly in low- and middle-income countries. Effective risk stratification can facilitate targeted prevention strategies, optimize resource allocation, and reduce avoidable hospitalizations. This study synthesizes existing evidence on the predictive performance of artificial intelligence (AI)-based models for stroke risk assessment through meta-analysis and explores their potential implications for healthcare system planning. Methods: Studies were systematically retrieved from Web of Science (WoS), PubMed, and Scopus until 31 January 2025. The review followed the PRISMA 2020 guidelines. Area Under the Receiver Operating Characteristic Curve (AUC) values were extracted for each algorithm type and pooled using meta-analytic methods. Results: Deep learning (DL) algorithms demonstrated favorable pooled discriminative performance (AUC: 0.955; 95% CI: 0.906–1.00, I = 85.75%), especially for imaging-based models. Sensitivity analysis modestly reduced heterogeneity (I from 85.75% to 61.77%). Substantial heterogeneity remained across study populations, healthcare settings, predictor characteristics, and validation strategies, limiting the generalizability of findings. Conclusions: AI-based models, particularly DL approaches, demonstrate favorable predictive performance for stroke risk stratification. However, considerable methodological heterogeneity, limited external validation, and risk of bias reduce confidence in widespread clinical implementation. Future research should follow standardized reporting and validation frameworks, such as TRIPOD, to improve methodological rigor, transparency, and clinical applicability. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2026 holdings: @attributes: islocal: N |
|---|