Applying speech technologies to assess verbal memory in patients with serious mental illness

Verbal memory deficits are significant neurocognitive impairments in schizophrenia and serious mental illnesses. Traditional assessment methods are resource-intensive and limited. This study developed a digital ambulatory verbal memory test with automated scoring and repeated self-administration via smart devices. 104 adults (25 patients, 79 healthy controls) participated. High-quality speech recordings were obtained (92% of prompts). Scores from natural language processing (NLP) on transcriptions were comparable to human ratings (R=0.83). A fully automated approach using automatic speech recognition (ASR) yielded comparable accuracy (R=0.82) and high correlation with human-transcribed scores (R=0.99). This demonstrates the feasibility of using speech technologies for frequent verbal memory assessment in psychiatry.

Terje B. Holmlund, Chelsea Chandler, Peter W. Foltz, Alex S. Cohen, Jian Cheng, Jared C. Bernstein, Elizabeth P. Rosenfeld, Brita Elvevåg