PMID- 36732110
OWN - NLM
STAT- MEDLINE
DCOM- 20230918
LR  - 20240302
IS  - 1573-2509 (Electronic)
IS  - 0920-9964 (Print)
IS  - 0920-9964 (Linking)
VI  - 259
DP  - 2023 Sep
TI  - The SPEAK study rationale and design: A linguistic corpus-based approach to 
      understanding thought disorder.
PG  - 80-87
LID - S0920-9964(22)00495-9 [pii]
LID - 10.1016/j.schres.2022.12.048 [doi]
AB  - AIM: Psychotic symptoms are typically measured using clinical ratings, but more 
      objective and sensitive metrics are needed. Hence, we will assess thought 
      disorder using the Research Domain Criteria (RDoC) heuristic for language 
      production, and its recommended paradigm of "linguistic corpus-based analyses of 
      language output". Positive thought disorder (e.g., tangentiality and derailment) 
      can be assessed using word-embedding approaches that assess semantic coherence, 
      whereas negative thought disorder (e.g., concreteness, poverty of speech) can be 
      assessed using part-of-speech (POS) tagging to assess syntactic complexity. We 
      aim to establish convergent validity of automated linguistic metrics with 
      clinical ratings, assess normative demographic variance, determine cognitive and 
      functional correlates, and replicate their predictive power for psychosis 
      transition among at-risk youths. METHODS: This study will assess language 
      production in 450 English-speaking individuals in Australia and Canada, who have 
      recent onset psychosis, are at clinical high risk (CHR) for psychosis, or who are 
      healthy volunteers, all well-characterized for cognition, function and symptoms. 
      Speech will be elicited using open-ended interviews. Audio files will be 
      transcribed and preprocessed for automated natural language processing (NLP) 
      analyses of coherence and complexity. Data analyses include canonical 
      correlation, multivariate linear regression with regularization, and 
      machine-learning classification of group status and psychosis outcome. 
      CONCLUSIONS: This prospective study aims to characterize language disturbance 
      across stages of psychosis using computational approaches, including psychometric 
      properties, normative variance and clinical correlates, important for biomarker 
      development. SPEAK will create a large archive of language data available to 
      other investigators, a rich resource for the field.
CI  - Copyright (c) 2023 Elsevier B.V. All rights reserved.
FAU - Bayer, J M M
AU  - Bayer JMM
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia. Electronic address: 
      bayerj@student.unimelb.edu.au.
FAU - Spark, J
AU  - Spark J
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Krcmar, M
AU  - Krcmar M
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Formica, M
AU  - Formica M
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Gwyther, K
AU  - Gwyther K
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Srivastava, A
AU  - Srivastava A
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - Selloni, A
AU  - Selloni A
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - Cotter, M
AU  - Cotter M
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - Hartmann, J
AU  - Hartmann J
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Polari, A
AU  - Polari A
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Bilgrami, Z R
AU  - Bilgrami ZR
AD  - Emory University, Atlanta, GA, USA.
FAU - Sarac, C
AU  - Sarac C
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - Lu, A
AU  - Lu A
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - Yung, Alison R
AU  - Yung AR
AD  - Orygen, Parkville, Victoria, Australia; Institute for Mental and Physical Health 
      and Clinical Translation (IMPACT), Deakin University, Australia; School of Health 
      Sciences, University of Manchester, United Kingdom.
FAU - McGowan, A
AU  - McGowan A
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA.
FAU - McGorry, P
AU  - McGorry P
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Shah, J L
AU  - Shah JL
AD  - McGill Department of Psychiatry & Douglas Research Hospital, Montreal, Canada.
FAU - Cecchi, G A
AU  - Cecchi GA
AD  - IBM TJ Watson Research Center, Yorktown Heights, NY, USA.
FAU - Mizrahi, R
AU  - Mizrahi R
AD  - McGill Department of Psychiatry & Douglas Research Hospital, Montreal, Canada.
FAU - Nelson, B
AU  - Nelson B
AD  - Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The 
      University of Melbourne, Parkville, Victoria, Australia.
FAU - Corcoran, C M
AU  - Corcoran CM
AD  - Icahn School of Medicine at Mount Sinai, New York, NY, USA; James J. Peters 
      Veterans Administration, Bronx, NY, USA.
LA  - eng
GR  - R01 MH115332/MH/NIMH NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
DEP - 20230131
PL  - Netherlands
TA  - Schizophr Res
JT  - Schizophrenia research
JID - 8804207
SB  - IM
MH  - Adolescent
MH  - Humans
MH  - Prospective Studies
MH  - *Psychotic Disorders/complications/diagnosis
MH  - Linguistics
MH  - Language
MH  - Speech
PMC - PMC10387495
MID - NIHMS1915690
OTO - NOTNLM
OT  - Latent semantic analysis
OT  - Natural language processing
OT  - Part-of-speech-tagging
OT  - Psychosis
OT  - Thought disorder
OT  - Ultra/clinical high risk
COIS- Declaration of competing interest The authors declare no real or potential 
      conflict of interest. All authors have reviewed and approved the manuscript 
      before submission.
EDAT- 2023/02/03 06:00
MHDA- 2023/09/18 12:43
PMCR- 2024/03/01
CRDT- 2023/02/02 22:01
PHST- 2022/09/29 00:00 [received]
PHST- 2022/12/27 00:00 [revised]
PHST- 2022/12/30 00:00 [accepted]
PHST- 2023/09/18 12:43 [medline]
PHST- 2023/02/03 06:00 [pubmed]
PHST- 2023/02/02 22:01 [entrez]
PHST- 2024/03/01 00:00 [pmc-release]
AID - S0920-9964(22)00495-9 [pii]
AID - 10.1016/j.schres.2022.12.048 [doi]
PST - ppublish
SO  - Schizophr Res. 2023 Sep;259:80-87. doi: 10.1016/j.schres.2022.12.048. Epub 2023 
      Jan 31.