Abstract WP83: An Artificial Intelligence Based Approach To Clinical Trial Recruitment: The Impact Of Viz Recruit On Enrollment In The Embolise Trial

Background: EMBOLISE (NCT 04402632) is an ongoing randomized controlled trial investigating the safety and efficacy of middle meningeal artery embolization for the treatment of subacute or chronic subdural hematoma (SDH). We hypothesized that the implementation Viz RECRUIT SDH, an artificial-intelligence (AI)-based mobile recruitment platform, would aid enrollment by automatically pre-screening suspected candidates for SDH and coordinating communication and image sharing among the entire research team. Methods: Patient enrollment in EMBOLISE prior to and after implementation of Viz RECRUIT SDH at a primary (PSC) and comprehensive stroke center (CSC) was compared. Viz RECRUIT SDH automatically detects SDH in head non-contrast computed tomography (NCCT) images and reports the volume, maximum thickness, and midline shift. The EMBOLISE trial was activated on May 5, 2021, and Viz RECRUIT SDH was activated on October 6, 2021; therefore, the pre-Viz cohort consisted of all patients from EMBOLISE to Viz activation (131 days), and the post-Viz cohort consisted of all patients from Viz activation until August 18, 2022 (316 days). For the post-Viz cohort, additional data is presented on AI-based screening metrics. Results: Prior to implementation of the AI-based software, there were 5 patients enrolled (0.99 patients/month). After implementation of the software for trial screening, enrollment increased by 36% to 1.35 patients/month (14 total enrolled), and there were no screen failures. Over the entire post-Viz period, a total of 6804 NCCTs were prescreened by Viz with 208 total SDH detections (3% prevalence). A total of 50 detections were made at the PSC and 158 came from the CSC. 79% of all alerts for suspected SDH were viewed, and 48% of all viewed alerts occurred within 10 minutes. Conclusions: The implementation of an AI-based software for the automatic screening of SDH patients increased the enrollment rate in the EMBOLISE trial. Moreover, in a busy research institution with 13 active studies in 2022, the automatic alerts of all potential patients keep our attention on EMBOLISE with coordinated screening and communication in a single mobile application.