Collecting language, speech acoustics, and facial expression to predict psychosis and other clinical outcomes: strategies from the AMP® SCZ initiative

Speech-based detection of early psychosis is progressing at a rapid pace. Within this evolving field, the Accelerating Medicines Partnership® in Schizophrenia (AMP® SCZ) is uniquely positioned to deepen our understanding of how language and related behaviors reflect early psychosis. We begin with detailed standard operating procedures (SOPs) that govern every stage of collection. These SOPs specify how to elicit speech, capture facial expressions, and record acoustics in synchronized audio-video files-both on-site and through remote platforms. We then explain how we chose our sampling tasks, hardware, and software, and how we built streamlined pipelines for data acquisition, aggregation, and processing. Robust quality-assurance and quality-control (QA/QC) routines, along with standardized interviewer training and certification, ensure data integrity across sites. Using natural language processing parsers, large language models, and machine-learning classifiers, we analyzed Data Release 3.0 to uncover systematic grammatical markers of psychosis risk. Speakers at clinical high risk (CHR) produced more referential language but fewer adjectives, adverbs, and nouns than community controls (CC), a pattern that replicated across sampling tasks. Some effects were task-specific: CHR participants showed elevated use of complex syntactic embeddings in two elicitation conditions but not the third, underscoring the importance of the language sampling task. Together, these results demonstrate how computational linguistics can turn everyday speech into a scalable, objective biomarker, paving the way for earlier and more precise detection of psychosis.Video Link: https://vimeo.com/1112291965?fl=pl&fe=sh.

Authors

Institutions

Publication Details

Journal
Schizophrenia
Published
2025-10-15
DOI
https://doi.org/10.1038/s41537-025-00669-z
Citations
1
Primary Topic
Neuroscience and Music Perception
Type
article
Field-Weighted Citation Impact
1.43

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Collecting language, speech acoustics, and facial expression to predict psychosis and other clinical outcomes: strategies from the AMP® SCZ initiative

Phillip Wolff, Sylvain Bouix, Zarina Bilgrami, Celso Arango et al.
1 citations
Schizophrenia
Neuroscience and Music Perception
1.43
article

Collecting language, speech acoustics, and facial expression to predict psychosis and other clinical outcomes: strategies from the AMP® SCZ initiative

Phillip Wolff, Sylvain Bouix, Zarina Bilgrami, Celso Arango, Barbara A. Cornblatt, Alan Anticevic, John M. Kane, Diana O. Perkins, Jai L. Shah, Albert R. Powers, Carrie E. Bearden, Kerstin Langbein, Nicholas J. K. Breitborde, Jason Eric Schiffman, Gregory P. Strauss, Jijun Wang, Philippe Conus, Daniel H. Mathalon, Luis Alameda, Walid Yassin, Swapna Verma, Lana Kambeitz‐Ilankovic, Jun Soo Kwon, Dominic Dwyer, René S. Kahn, Tashrif Billah, Matthew R. Broome, Habiballah Rahimi-Eichi, Covadonga M. Díaz‐Caneja, Merete Nordentoft, Steven M. Silverstein, Jack Rogers, Isabelle Scott, Carla Gerber, Ofer Pasternak, Christy Lai Ming Hui, Barnaby Nelson, Pablo A. Gaspar, Judy L. Thompson, Jean Addington, Cheryl M. Corcoran, Jesús Pérez, Einat Liebenthal, Rachel Upthegrove, William S. Stone, Patrick D. McGorry, Paolo Fusar‐Poli, Michaela Ennis, Beau‐Luke Colton, Guillermo Cecchi, Zailyn Tamayo, Monica E. Calkins, Thomas R. Henry, Scott W. Woods, Justin T. Baker, Eduardo Castro, Stefan Smesny, Kristin S. Cadenhead, Martha E. Shenton, Daniel H. Wolf, Joseph Kambeitz, Vijay Anand Mittal, Carla Agurto, Leslie E. Horton, Jimmy Choi, Nikolaos Koutsouleris, Kang Ik K. Cho, Sung‐Wan Kim, Eric Yu Hai Chen, Louise Birkedal Glenthøj, Fred W. Sabb, Matcheri S. Keshavan, Lauren M. Ellman, Godfrey D. Pearlson, Linying Li, Mara Henecks
article en
1 citations

Abstract

Speech-based detection of early psychosis is progressing at a rapid pace. Within this evolving field, the Accelerating Medicines Partnership® in Schizophrenia (AMP® SCZ) is uniquely positioned to deepen our understanding of how language and related behaviors reflect early psychosis. We begin with detailed standard operating procedures (SOPs) that govern every stage of collection. These SOPs specify how to elicit speech, capture facial expressions, and record acoustics in synchronized audio-video files-both on-site and through remote platforms. We then explain how we chose our sampling tasks, hardware, and software, and how we built streamlined pipelines for data acquisition, aggregation, and processing. Robust quality-assurance and quality-control (QA/QC) routines, along with standardized interviewer training and certification, ensure data integrity across sites. Using natural language processing parsers, large language models, and machine-learning classifiers, we analyzed Data Release 3.0 to uncover systematic grammatical markers of psychosis risk. Speakers at clinical high risk (CHR) produced more referential language but fewer adjectives, adverbs, and nouns than community controls (CC), a pattern that replicated across sampling tasks. Some effects were task-specific: CHR participants showed elevated use of complex syntactic embeddings in two elicitation conditions but not the third, underscoring the importance of the language sampling task. Together, these results demonstrate how computational linguistics can turn everyday speech into a scalable, objective biomarker, paving the way for earlier and more precise detection of psychosis.Video Link: https://vimeo.com/1112291965?fl=pl&fe=sh.

SchizophreniaVol. 11(1)
Rutgers, The State University of New Jersey (US), Chonnam National University (KR), Northwestern University (US), University of North Carolina at Chapel Hill (US), University of Copenhagen (DK), Brigham and Women's Hospital (US), Beth Israel Deaconess Medical Center (US), Feinstein Institute for Medical Research (US), Harvard University (US), Emory University (US), University of California, Los Angeles (US), University of Georgia (US), The University of Melbourne (AU), University of Calgary (CA), University of Pittsburgh (US), Douglas College (CA), University of California, San Francisco (US), University of Cologne (DE), University of Oregon (US), King's College London (GB), Universidad de Salamanca (ES), University of California, Irvine (US), Washington University in St. Louis (US), Heidelberg University (DE), University of Pavia (IT), PeaceHealth St. John Medical Center (US), Mental Health Services (DK), McLean Hospital (US), Instituto de Salud Carlos III (ES), University Hospital Heidelberg (DE), Copenhagen University Hospital (DK), Shanghai Mental Health Center (CN), University of Rochester Medical Center (US), Hospital General Universitario Gregorio Marañón (ES), Yale University (US), University of California San Diego (US), Centro de Investigación Biomédica en Red de Salud Mental (ES), Orygen Youth Health (AU), Hôpital de Cery (CH), Neurobehavioral Systems (US), Central Institute of Mental Health (DE), Donald & Barbara Zucker School of Medicine at Hofstra/Northwell (US), Hôpital Orthopédique de la Suisse Romande (CH), Instituto de Investigación Biomédica de Salamanca (ES), Jena University Hospital (DE), Behavioral Health Network (US), Institute of Mental Health (SG), Hanyang University Seoul Hospital (KR), San Francisco VA Health Care System (US), Cambridgeshire and Peterborough NHS Foundation Trust (GB), University Hospital Cologne (DE), Birmingham Women’s and Children’s NHS Foundation Trust (GB), Connecticut Mental Health Center (US), Hotchkiss Brain Institute (CA), Hanyang University (KR), McGill University (CA), The Ohio State University (US), University of Chile (CL), University of Pennsylvania (US), University of Birmingham (GB), Temple University (US), University of Hong Kong (HK), École de Technologie Supérieure (CA), University of Lausanne (CH), Icahn School of Medicine at Mount Sinai (US)
Wellcome Trust, National Institutes of Health, National Institute of Mental Health
Openalex Percentile: Top 15%
Neuroscience and Music Perception
1.43
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.