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

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.
Competing Interests: Declaration of competing interest This project reflects a collaboration by Sumitomo Pharma America, Inc, Quantic Innovation, WCG Inc., Louisiana State University, and the Psychiatric Research Institute at the University of Arkansas for Medical Sciences. Potential conflicts of interest between private and academic interests were formally reviewed and mitigated by an LSU review board. Potential conflicts of interest were addressed by transparent declaration of potentially competing interests, and by publishing these results such that the scientific community might be able to critically review, replicate and extend them. S.M, S.T.S, S.T., A.O., K.S.K, D.P. and S.H. are employees of Sumitomo Pharma America Inc. M.O. is a full-time employee and shareholder in WCG. In the past three years, A.S.C has received honoraria/support from Indivior and Boehringer Ingelheim. A.S.C., B.K., and M.O. have stock or related interests in Quantic Innovation which develops and validates digital health measurements. B.K receives licensing royalties from ProPhase for use of the Brief Negative Symptom Scale (BNSS) by for-profit groups; these fees are donated to the Brain and Behavior Research Foundation. In the last three years he has also received honoraria and travel support from ProPhase for training pharmaceutical company raters on the BNSS; consulting fees and/or travel support from Lundbeck, Acadia, ProPhase, Otsuka, and Minerva Neurosciences; fees from anonymized investors through Guideposts and Decision Resources Group; and an honorarium from Otsuka for preparation of educational materials.
(Copyright © 2024. Published by Elsevier B.V.)