Feasibility of automated longitudinal cognitive and mood assessment in the stroke pathway

ABSTRACT

Introduction: Over 50% of stroke survivors have cognitive impairment. National guidelines promote early cognitive testing however, current penand- 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. Method(s) Patients were approached if they pass the eligibility criteria of having recent acute stroke/TIA, and do not have pre-existing medical condition i.e dementia, severe aphasia or too medically unwell to complete the assessment. Participants completed the computerised doctor or "CognoSpeak" on the ward using a tablet or at home via a web-version (on home computer or tablet). The assessment included the GAD and PHQ9. All had standard cognitive assessment done with the Montreal Cognitive Assessment (MOCA). Result(s) Recruitment started on 8th December 2020 and is on-going. 951 people were screened and 104 were recruited. 49 have completed baseline Cognospeak, 8 have withdrawn and 3 have died. The mean NIHSS was 3.8 and mean MoCA of 23.9, 31 were female. Participants had a mean education level of 17 years. Conclusion(s) Preliminary data will be presented highlighting feasibility of an automated cognitive and mood assessment that can be completed at home and on the Hyper-acute Stroke Unit. Screening was adapted due to Covid pandemic and utilising remote consent and participation allowed the project to continue.