Evaluating speech latencies during structured psychiatric interviews as an automated objective measure of psychomotor slowing

• Published in: Psychiatry research Vol. 340; p. 116104
• Main Authors: Cohen, Alex S., Rodriguez, Zachary, Opler, Mark, Kirkpatrick, Brian, Milanovic, Snezana, Piacentino, Daria, Szabo, Steven T., Tomioka, Sasagu, Ogirala, Ajay, Koblan, Kenneth S., Siegel, Joshua S., Hopkins, Seth
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.10.2024
• Subjects: Adult; Biomarker; Bipolar Disorder - diagnosis; Bipolar Disorder - physiopathology; Cross-Sectional Studies; Depression; Digital phenotyping; Double-Blind Method; Female; Humans; Interview; Interview, Psychological; Language; Latency; Male; Middle Aged; Psychiatric Status Rating Scales - standards; Psychomotor; Psychomotor Performance - physiology; Reaction Time - physiology; Speech; Speech - physiology; Young Adult; Digital phenotyping; Biomarker; Language; Depression; Speech; Psychomotor; Latency; Interview
• ISSN: 0165-1781; 1872-7123; 1872-7123
• DOI: 10.1016/j.psychres.2024.116104

•We derived an objective measure of psychomotor slowing using speech latencies during a psychiatric interview.•This measure showed good temporal stability, convergent validity, sensitivity/responsivity to clinical change, and generalization across seven socio-linguistically diverse countries (k = 1352 interviews).•This measure was highly accurate for differentiating people with versus without concurrent depression and for predicting whether depression remitted over time.•Other speech features offered little incremental contribution beyond speech latency.•Neurophysiological speech parameters with face validity can be derived from psychiatric interviews without the added patient burden of additional testing. We sought to derive an objective measure of psychomotor slowing from speech analytics during a psychiatric interview to avoid potential burden of dedicated neurophysiological testing. Speech latency, which reflects response time between speakers, shows promise from the literature. Speech data was obtained from 274 subjects with a diagnosis of bipolar I depression enrolled in a randomized, doubleblind, 6-week phase 2 clinical trial. Audio recordings of structured Montgomery–Åsberg Depression Rating Scale (MADRS) interviews at 6 time points were examined (k = 1,352). We evaluated speech latencies, and other aspects of speech, for temporal stability, convergent validity, sensitivity/responsivity to clinical change, and generalization across seven socio-linguistically diverse countries. Speech latency was minimally associated with demographic features, and explained nearly a third of the variance in depression (categorically defined). Speech latency significantly decreased as depression symptoms improved over time, explaining nearly 20 % of variance in depression remission. Classification for differentiating people with versus without concurrent depression was high (AUCs > 0.85) both cross-sectionally and longitudinally. Results replicated across countries. Other speech features offered modest incremental contribution. Neurophysiological speech parameters with face validity can be derived from psychiatric interviews without the added patient burden of additional testing.