Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings
IntroductionSpeech 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...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1571647/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849705530503725056 |
|---|---|
| author | Michelle Worthington Michelle Worthington Georgios Efstathiadis Vijay Yadav Vijay Yadav Isaac Galatzer-Levy Isaac Galatzer-Levy Isaac Galatzer-Levy Alan Kott Emanuel Pintilii Tejendra Patel Colin Sauder Inder Kaul Stephen Brannan Anzar Abbas |
| author_facet | Michelle Worthington Michelle Worthington Georgios Efstathiadis Vijay Yadav Vijay Yadav Isaac Galatzer-Levy Isaac Galatzer-Levy Isaac Galatzer-Levy Alan Kott Emanuel Pintilii Tejendra Patel Colin Sauder Inder Kaul Stephen Brannan Anzar Abbas |
| author_sort | Michelle Worthington |
| collection | DOAJ |
| description | IntroductionSpeech 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.MethodsPositive 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.ResultsOur 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.DiscussionA 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. |
| format | Article |
| id | doaj-art-346ebd2dfe104fad97b2003c9e62d17e |
| institution | DOAJ |
| issn | 1664-0640 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj-art-346ebd2dfe104fad97b2003c9e62d17e2025-08-20T03:16:26ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402025-06-011610.3389/fpsyt.2025.15716471571647Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordingsMichelle Worthington0Michelle Worthington1Georgios Efstathiadis2Vijay Yadav3Vijay Yadav4Isaac Galatzer-Levy5Isaac Galatzer-Levy6Isaac Galatzer-Levy7Alan Kott8Emanuel Pintilii9Tejendra Patel10Colin Sauder11Inder Kaul12Stephen Brannan13Anzar Abbas14Brooklyn Health, Brooklyn, NY, United StatesDepartment of Psychiatry, Yale University School of Medicine, New Haven, CT, United StatesBrooklyn Health, Brooklyn, NY, United StatesBrooklyn Health, Brooklyn, NY, United StatesSchool of Psychology, University of New South Wales, Sydney, AustraliaBrooklyn Health, Brooklyn, NY, United StatesGoogle LLC, Mountain View, CA, United StatesDepartment of Psychiatry, Grossman School of Medicine, New York, NY, United StatesSignant Health, Iasi, RomaniaSignant Health, Iasi, RomaniaBristol Myers Squibb, New York, NY, United StatesBristol Myers Squibb, New York, NY, United StatesBristol Myers Squibb, New York, NY, United StatesBristol Myers Squibb, New York, NY, United StatesBrooklyn Health, Brooklyn, NY, United StatesIntroductionSpeech 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.MethodsPositive 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.ResultsOur 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.DiscussionA 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.https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1571647/fulldigital phenotypingdigital health measuresnatural language processingschizophrenia spectrum disordersspeech characteristicspsychosis |
| spellingShingle | Michelle Worthington Michelle Worthington Georgios Efstathiadis Vijay Yadav Vijay Yadav Isaac Galatzer-Levy Isaac Galatzer-Levy Isaac Galatzer-Levy Alan Kott Emanuel Pintilii Tejendra Patel Colin Sauder Inder Kaul Stephen Brannan Anzar Abbas Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings Frontiers in Psychiatry digital phenotyping digital health measures natural language processing schizophrenia spectrum disorders speech characteristics psychosis |
| title | Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings |
| title_full | Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings |
| title_fullStr | Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings |
| title_full_unstemmed | Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings |
| title_short | Measurement of schizophrenia symptoms through speech analysis from PANSS interview recordings |
| title_sort | measurement of schizophrenia symptoms through speech analysis from panss interview recordings |
| topic | digital phenotyping digital health measures natural language processing schizophrenia spectrum disorders speech characteristics psychosis |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1571647/full |
| work_keys_str_mv | AT michelleworthington measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT michelleworthington measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT georgiosefstathiadis measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT vijayyadav measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT vijayyadav measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT isaacgalatzerlevy measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT isaacgalatzerlevy measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT isaacgalatzerlevy measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT alankott measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT emanuelpintilii measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT tejendrapatel measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT colinsauder measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT inderkaul measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT stephenbrannan measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings AT anzarabbas measurementofschizophreniasymptomsthroughspeechanalysisfrompanssinterviewrecordings |