• Juan José Cirio, Pablo Diluca, Celina Ciardi, Esteban Scrivano, Javier Lundquist, Iván R Lylyk, Nicolas Pérez, Pedro N Lylyk, Carlos Bleise, and Pedro Lylyk.
• Unidad de ACV, La Sagrada Familia, Instituto Médico ENERI, Buenos Aires, Argentina. E-mail: jjcirio@gmail.com.
• Medicina (B Aires). 2023 Jan 1; 83 (5): 705718705-718.

IntroductionThe start of the COVID-19 pandemic forced the implementation of changes in the emergency services care system. Concomitantly, at our institution, we implemented the artificial intelligence (AI) software, RAPID.AI, for image analysis in ischemic stroke (IS). Our objective was to evaluate the impact of the use of AI together with the changes in the triage during the COVID-19 pandemic in patients with stroke due to large vessel occlusion (LVO).MethodsWe included patients with IS due to LVO treated with intravenous reperfusion therapy plus endovascular or direct endovascular therapy.ResultsTwo groups were created. Group 1: patients from January 2019 to June 2020; Group 2: patients from July 2020 to December 2021, studied with RAPID.AI. Clinical data and temporal metrics were analyzed. They were compared according to arrival time from 08:00 to 20:00 (daytime) vs 20:01 to 7:59 (night).ResultsWe included 286 patients, 153 in group 1 and 133 in group 2. In group 2, door-image metric and image duration were lower, with shorter door-image onset and door-recanalization times; patients who arrived at night had higher NIHSS and longer time from onset-to-door with lower proportion of functional independence at 90 days (mRS = 2).ConclusionsThe use of AI for image analysis along with a shorter door to end of image time allowed to reduce the interval to groin puncture. In the analysis by hours during the pandemic, patients admitted in daytime hours had significantly lower door to image, image time acquisition, and door to recanalization metrics.

17 keywords...

hide…