知镜 Cognispect · 医学文献与研究工作台

Impact of Artificial Intelligence-Based Triage on Stroke Workflow Metrics: A Systematic Review and Meta-Analysis.

Barrera Gutierrez JC, Vivian E, Shah J, Meyrat R.
Cardiovascular and interventional radiology · 2026-07-07 · PMID 42414634

文献摘要

Background Artificial intelligence is an increasingly valuable tool in ischemic stroke management. This systematic review and meta-analysis evaluated the effect of artificial intelligence implementation on stroke workflow metrics. Methods PubMed, EMBASE, OpenEvidence, and the Cochrane Central Register of Controlled Trials were searched for studies (2015-2025) evaluating automated large vessel occlusion detection. Pooled mean differences with 95% CIs were calculated for door-to-groin puncture, door-to-first pass, door-to-revascularization, door-to-needle, and door-in-door-out times. Results Twelve studies met the inclusion criteria: one clinical trial and eleven observational studies. Artificial intelligence was associated with reductions in multiple workflow intervals, including door-to-groin puncture (-17.12 minutes), door-to-first pass (-26.55 minutes), door-to-revascularizationon (-14.55 minutes), door-to-needle (-4.44 minutes), and door-in-door-out time (-36.8 minutes). Conclusion Overall, AI-based platforms appear to contribute meaningfully to stroke workflow optimization, although randomized controlled trials are still needed to confirm their effectiveness. Level of evidence Level 2c, Systematic review of randomized clinical trials, and observational studies.

在知镜精读原文来源DOI 原文

知镜提供医学文献检索、阅读笔记、人体图谱、统计绘图与研究复现工具。