050 Feasibility of an automated assessment to measure cognition and mood in the acute stroke setting

IntroductionOver 50% of stroke survivors have cognitive impairment. National guidelines promote early cognitive testing however, current pen-and-paper based tests are not always appropriate, typically take place in hospital and are time costly for busy clinicians.This project aimed to create an easy-to-use cognitive assessment tool specifically designed for the needs of stroke survivors. We used a computerised doctor utilising automatic speech recognition and machine learning.MethodsPatients are approached if they pass the eligibility criteria of having recent acute stroke/TIA, and do not have pre-existing condition i.e dementia, severe aphasia Participants could speak to the digital doctor on the ward or at home via a web-version.ResultsRecruitment started on 8th December 2020; We have screened 614 people assessed for suspected acute stroke/TIA at Sheffield Teaching Hospitals. Of those we have recruited 71 participants (13 with TIA) Mean NIHSS of 4.5 and mean MoCA of 24.6. We will present initial results of factors affecting participant recruitment. We will also compare the mood and anxiety screening scores used in this study to those collected via the SNAPP database.DiscussionScreening was adapted due to Covid pandemic and utilising remote consent and participa- tion allowed the project to continue.