Multicenter comparison using two AI stroke CT perfusion software packages for determining thrombectomy eligibility.

BACKGROUND: Stroke AI platforms assess infarcted core and potentially salvageable tissue (penumbra) to identify patients suitable for mechanical thrombectomy. Few studies have compared outputs of these platforms, and none have been multicenter or considered NIHSS or scanner/protocol differences. Our objective was to compare volume estimates and thrombectomy eligibility from two widely used CT perfusion (CTP) packages, Viz.ai and RAPID.AI, in a large multicenter cohort. METHODS: We analyzed CTP data of acute stroke patients with large vessel occlusion (LVO) from four institutions. Core and penumbra volumes were estimated by each software and DEFUSE-3 thrombectomy eligibility assessed. Results between software packages were compared and categorized by NIHSS score, scanner manufacturer/model, and institution. RESULTS: Primary analysis of 362 cases found statistically significant differences in both software's volume estimations, with subgroup analysis showing these differences were driven by results from a single scanner model, the Canon Aquilion One. Viz.ai provided larger estimates with mean differences of 8cc and 18cc for core and penumbra, respectively (p<0.001). NIHSS subgroup analysis also showed systematically larger Viz.ai volumes (p<0.001). Despite volume differences, a significant difference in thrombectomy eligibility was not found. Additional subgroup analysis showed significant differences in penumbra volume for the Phillips Ingenuity scanner, and thrombectomy eligibility for the Canon Aquilion One scanner at one center (7 % increased eligibility with Viz.ai, p=0.03). CONCLUSIONS: Despite systematic differences in core and penumbra volume estimates between Viz.ai and RAPID.AI, DEFUSE-3 eligibility was not statistically different in primary or NIHSS subgroup analysis. A DEFUSE-3 eligibility difference, however, was seen on one scanner at one institution, suggesting scanner model and local CTP protocols can influence performance and cause discrepancies in thrombectomy eligibility. We thus recommend centers discuss optimal scanning protocols with software vendors and scanner manufacturers to maximize CTP accuracy.

(VISIION-S): Viz.ai Implementation of Stroke augmented Intelligence and communications platform to improve Indicators and Outcomes for a comprehensive stroke center and Network - Sustainability.

OBJECTIVES: As Comprehensive Stroke Centers (CSCs) strive to improve neuro-intervention (NIR) times, process improvements are put in place to streamline workflows. Our prior publication (VISIION) demonstrated improvements in key performance indicators (KPIs). The purpose VISIION-S was to analyze whether those results were sustainable. MATERIALS AND METHODS: Consecutive Direct Arriving LVO (DALVO) and telemedicine transfer LVO (BEMI) stroke NIR cases were assessed, including subgroups of DALVO-OnHours, DALVO-OffHours, BEMI-OnHours, and BEMI-OffHours. We analyzed times for the original 6 months pre (6/10/20-1/15/21) and compared them to a 17 month post-implementation period (1/16/21- 6/25/22) to evaluate for sustainability. Mann-Whitney U was utilized. RESULTS: 150 NIR cases were analyzed pre (n = 47) v. post (n = 103) implementation (DALVO-OnHours 7 v. 20, DALVO-OffHours 10 v. 25, BEMI-OnHours 13 v. 20, BEMI-OffHours 17 v. 38). For Door-to-groin (DTG), improvement was noted for DALVO-OffHours 39%(157 min,96 min;p < 0.001), DALVO-ALL 25%(127 min,95 min;p = 0.006), BEMI-OffHours 46%(45 min,25 min;p = 0.023), and BEMI-ALL 40%(42 min,25 min;p = 0.005). Activation-to-groin (ATG), door-to-device (DTD), and door-to-recanalization (DTR) also showed statistical improvements. For DALVO-OffHours, there were reductions in door to CT (DTC) 80%(26 min,5 min;p < 0.001), ATG 32%(90 min,61 min;p = 0.036), DTG 39%(157 min,96 min;p < 0.001), DTD 31%(178 min,123 min;p = 0.002), and DTR 32%(197 min,135 min;p = 0.003). CONCLUSIONS: We noted sustainability over a 17 month period with sustained reduction in KPIs for even more NIR time interval comparisons. In the greatest opportunity subgroup (DALVO-OffHours), we noted a reduction in all 5 time interval metrics. Our sustainability finding is important to show that process improvements continued even after the immediate period, adding credibility to the results. Models such as this could be useful for other centers striving to optimize workflow and improve times.