王月琴, Luxin Guo
Diffusion-weighted imaging (DWI) is central to acute ischemic stroke (AIS) management; however, its performance varies across different clinical applications. This systematic review and meta-analysis comprehensively evaluated the diagnostic accuracy, time window estimation capability, and prognostic value of DWI in AIS. This registered systematic review searched three major databases for DWI studies in adult AIS patients published from 2010 to 2025. Risk of bias was assessed using QUADAS-2. The meta-analysis was performed in three distinct phases: (1) diagnostic accuracy, (2) time window estimation, and (3) prognostic value using a bivariate random-effects model. Extensive subgroup analyses were conducted to investigate sources of heterogeneity, including AI assistance, MRI field strength, study design, onset-to-DWI time, sequence type, lesion location, and stroke severity. Of 34 eligible studies, 22 independent studies with 30 datasets were included in the meta-analysis across three phases. DWI demonstrated excellent diagnostic accuracy with a pooled sensitivity of 0.912 (95% CI: 0.888–0.932) and specificity of 0.959 (95% CI: 0.940–0.970). For time window estimation, DWI showed moderate performance with a pooled sensitivity of 0.786 (95% CI: 0.688–0.860) and specificity of 0.727 (95% CI: 0.668–0.780), with substantial heterogeneity and markedly lower accuracy in posterior circulation strokes. DWI-derived biomarkers demonstrated good prognostic value for predicting functional outcomes with a pooled sensitivity of 0.702 (95% CI: 0.540–0.825) and specificity of 0.904 (95% CI: 0.821–0.951). DWI offers excellent diagnostic accuracy for AIS (sensitivity: 0.912, specificity: 0.959) but only modest performance for time estimation (sensitivity: 0.786, specificity: 0.727). DWI-derived biomarkers show good prognostic value (sensitivity: 0.702, specificity: 0.904), while AI and ultra-fast MRI protocols demonstrate promise for improving clinical utility. Registered systematic review and meta-analysis following PRISMA guidelines 2026 CRD420261376477.