Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings
- PMID: 40630759
- PMCID: PMC12235459
- DOI: 10.3389/fpsyt.2025.1571647
Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings
Abstract
Introduction: Speech is considered a clinically meaningful indicator of schizophrenia symptom severity and the quantification of speech measures has the potential to improve the measurement of symptoms. Speech collection for digital phenotyping is often dependent on platforms built using closed-source code and associated with patient and clinician burden. Here, we evaluate recordings of clinical interviews conducted as part of standard clinical trial procedures as reliable sources of patient speech for symptom assessment using digital phenotyping. We hypothesize that speech will be associated with schizophrenia symptom severity as measured by PANSS scores using PANSS interview recordings as a data source, in line with existing research showing these associations using dedicated speech collection platforms and proprietary processing pipelines.
Methods: Positive and Negative Syndrome Scale (PANSS) interview recordings, collected during a Phase 2 schizophrenia clinical trial, are used to calculate speech characteristics using open source code. A total of 825 PANSS recordings from 212 participants were used in this study. Mixed effects models accounting for demographic variables and time were conducted to assess the relationship between speech characteristics and PANSS scores.
Results: Our findings show strong relationships between the calculated speech characteristics and schizophrenia symptom severity. Positive symptoms were associated with greater amount of speech, faster speech, and shorter, less varied pauses. By contrast, negative symptoms were associated with decreased amount of speech, slower speech, and longer, more varied pauses.
Discussion: A large sample of PANSS recordings was successfully processed using open source methods for phenotyping and strong relationships between speech characteristics and symptoms from these recordings were observed. These observations, consistent with existing understandings of speech-based manifestations of schizophrenia, highlight the potential use of patient speech collected passively during clinical interactions for digital phenotyping and symptom assessment. Implications for clinical practice, drug development, and progress towards precision psychiatry are discussed.
Keywords: digital health measures; digital phenotyping; natural language processing; psychosis; schizophrenia spectrum disorders; speech characteristics.
Copyright © 2025 Worthington, Efstathiadis, Yadav, Galatzer-Levy, Kott, Pintilii, Patel, Sauder, Kaul, Brannan and Abbas.
Conflict of interest statement
AA, MW, GE, VY, and IG-L are affiliated with Brooklyn Health, a private company that developed the open source software that was used in this study and indirectly benefits from its continued adoption. IG-L is also an employee of and holds shares in Google. AK and EP are employees of Signant Health, a private company that develops the eCOA platform used to collect clinical interview recordings and directly benefits from the continued use of such recordings for the purposes explored here. TP, CS, IK, and SB are employees of Karuna Therapeutics, a Bristol Myers Squibb company, a publicly traded pharmaceutical company that sponsored the clinical trial reported on here. The authors declare that this study received funding from Karuna Therapeutics, Signant Health, and Brooklyn Health. Karuna Therapeutics played a role in study design, data collection, and decision to publish; Signant Health played a role in data processed, and Brooklyn Health played a role in data analysis and preparation of manuscript.
Figures
