Artificial Intelligence Application Expediates Surgical Team Evaluation as Part of Hemorrhagic Stroke Workflow Metrics

ObjectiveThe ENRICH Trial was the first to demonstrate superiority of surgical intervention over medical management when performed within 24 hours of symptom onset for supratentorial lobar hemorrhages. We aimed to determine whether the implementation of an intracranial hemorrhage detection algorithm that provides immediate active notification to provider cell phones would expediate the screening of hemorrhagic stroke patients for the trial at our institution. MethodsA retrospective review of our prospectively collected ENRICH Trial patient screening log was performed at our Comprehensive Stroke Center. The log encompassed patients screened for the ENRICH Trial who presented between January 2018 and March 2022. Trial screening data was compared pre- and post-implementation of the VizAI (Viz.ai, San Francisco, California, USA) smartphone application. Results188 adult patients were identified during the study period. Time between CT Head and notification of the neurosurgical team for trial screening was reduced by 50 minutes after the implementation of VizAI (p<0.002). The number increases to 57 minutes when hemorrhages not identified by the ICH algorithm were excluded. ConclusionsActive notification of the neurosurgical team by an artificial intelligence application significantly reduces the time from hemorrhage identification to trial screening. Further studies are needed to evaluate whether this results in a clinical benefit.