COGNOSPEAK: a feasibility pilot study of automated speech analysis to aid cognitive assessment post stroke

<h3>Background</h3> Stroke survivors (SSs) often experience cognitive decline following initial stroke, necessitating repeat cognitive assessments. Current methods of assessment, such as Montreal Cognitive Assessment (MoCA), are time-consuming and rely on health-care professionals. Addressing these challenges, we introduce Cognospeak. <h3>Methods</h3> CognoSpeak is used initially in the acute post-stroke within the hospital and subsequently at home. CognoSpeak assesses cognitive decline via a user interface using a virtual agent. SS answer questions and complete cognitive tests. CognoSpeak uses Artificial intelligence methods to extract and process speech, language, and interactional cues for cognitive decline. Barriers to automated cognitive assessment in SS are also explored. <h3>Results</h3> In a cohort of 55 SS, a best regression result (Normalized Root Mean Squared Error) of 0.092 was achieved for predicting MOCA score. Identifying cognitive impairment (MoCA score cutoff of &lt; 26) yields a Specificity of 0.73, Sensitivity of 0.75. Demonstrating the first evidence of the system’s robustness in SS. <h3>Conclusions</h3> CognoSpeak can be used successfully in the acute stroke setting to predict cognitive scores of SS, highlighting its use in streamlining and improving post-stroke cognitive assessment. Challenges of automated assessment on the stroke pathway include patient computer access, anxiety in using information technology resources and post-stroke apathy.