Abstract Body: Background:
The utilization of artificial intelligence (AI) platforms to provide rapid access to images, LVO detection, and team communication in acute stroke protocols is expanding globally. The VALIDATE study showed that Viz.ai was correlated with significant decrease in arrival to neurointerventionalist notification time of 40 minutes and a synergistic effect with hospital pre-notification. The study aims to assess if these findings are generalizable to other AI platforms specifically RAPIDAI.

Methods:
Acute stroke consultations seen in the emergency department in 103 facilities (35 RAPID AI and 68 no-AI) in 24 states from July 1, 2021 to December 31, 2021 were extracted from the TeleCare by TeleSpecialists^TM database. The encounters were reviewed for demographics, LVO, accepted for intervention, arrival to NIR notification time (ATN), and RAPIDAI software used. Patients were classified into two groups based on use of RAPIDAI or no AI software as well as hospital pre-notification of teleneurologist vs pre-notifications cases excluded. The median arrival to NIR notification times were compared.

Results:
A total of 14,159 patients were included: No AI group (7,433), and RAPIDAI (6,726). The median arrival to NIR notification time for No AI group was 88.5 minutes when compared to RAPIDAI groups 57.5 minutes was significantly longer, p <0.0001. For pre-notification cases, the No AI group was 80.5 minutes and the ATN time for RAPIDAI was 47 minutes, p <0.0001. When pre-notifications were excluded, the ATN times for No-AI were 94.5 minutes vs RAPIDAI were 69 minutes, p = 0.0001.

Conclusions:
The use of the RAPIDAI platform was associated with a significant, 31-minute reduction in the patient arrival to neurointerventionalist notification time. When looking at the subgroup of hospitals with RAPIDAI where a teleneurologist was also notified prior to the patient’s ED arrival, the ATN was even shorter at 33.5 minutes. Our data supports the conclusion that Best Practice for improving patient times to thrombectomy includes the combination of a pre-hospital notification to the teleneurologist and the use of an AI platform for LVO patients.