<![CDATA[Introduction: Delayed interpretation of emergency chest X-rays (CXRs) represents a critical bottleneck in emergency department (ED) workflow, potentially compromising outcomes in time-sensitive conditions. Artificial intelligence (AI) algorithms have demonstrated capacity for automated detection and prioritization of radiographic findings, offering a potential solution to interpretation delays. Methods: A systematic search adhered to the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) 2020 guidelines for studies evaluating AI-assisted CXR interpretation in emergency settings reporting time-related outcomes. Risk of bias was assessed using QUADAS-2 and RoB 2.0 tools. Seventeen primary studies encompassing 16 distinct AI algorithms and over 1.2 million CXR images were included. Results: AI implementation was consistently associated with significant reductions in mean report turnaround time (RTAT; range: 2.7–29.7 minutes reduction) and radiologist reading time (average reduction 13–27%). Active worklist prioritization reduced RTAT for critical findings from 80.1 to 35.6 minutes (p<0.0001) and reduced average reporting delay from 11.2 to 2.7 days. AI-assisted interpretation improved diagnostic sensitivity for pneumothorax (AUC 0.97), pleural effusion (AUC 0.94–0.97), and consolidation (AUC 0.83–0.88). Non-radiology emergency clinicians derived greatest benefit, with pneumothorax AUC improving from 0.846 to 0.974 with AI assistance. Generative AI models produced reports of equivalent clinical accuracy to radiologists while improving documentation efficiency by 15.5%. Discussion: AI integration significantly reduces RTAT and optimizes worklist prioritization, particularly for critical findings. Active worklist re-ordering algorithms produced greater RTAT reductions (43.7%) than passive notification systems (7.6%). Algorithmic bias against underserved populations and false-negative safety risks mandate mandatory equity auditing and time-cap mechanisms prior to clinical deployment. Conclusion: AI implementation for emergency CXR interpretation is clinically effective in reducing waiting time and RTAT, improving diagnostic sensitivity, and enhancing workflow efficiency. Active worklist prioritization systems yield greatest benefit. Future prospective multicenter randomized controlled trials are necessary to establish standardized implementation protocols and evaluate long-term clinical outcomes.]]>
