Automated analysis of free speech predicts psychosis onset in high-risk youths

Autores
Bedi, Gillinder; Carrillo, Facundo; Cecchi, Guillermo Alberto; Fernandez Slezak, Diego; Sigman, Mariano; Mota, Natália; Ribeiro, Sidarta; Javitt, Daniel; Copelli, Mauro; Corcoran, Cheryl
Año de publicación
2015
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novelcomputerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illnessin individuals.AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predictlater psychosis onset in youths at clinical high-risk (CHR) for psychosis.METHODS: Thirty-four CHR youths (11 females) had baseline interviews and were assessed quarterly for up to 2.5 years; fivetransitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic featurespredicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-outcross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features andprodromal symptom ratings was computed.RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markersof speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosisdevelopment with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantlycorrelated with prodromal symptoms.CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental statechanges in emergent psychosis. Recent developments in computer science, including natural language processing, could providethe foundation for future development of objective clinical tests for psychiatry.npj Schizophrenia (2015) 1, Article number: 15030; doi:10.1038/npjschz.2015.30; published online 26 August 2015
Fil: Bedi, Gillinder. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
Fil: Carrillo, Facundo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Cecchi, Guillermo Alberto. Ibm Research. Thomas J. Watson Research Center; Estados Unidos
Fil: Fernandez Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Sigman, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Mota, Natália. Universidade Federal do Rio Grande do Norte; Brasil
Fil: Ribeiro, Sidarta. Universidade Federal do Rio Grande do Norte; Brasil
Fil: Javitt, Daniel. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
Fil: Copelli, Mauro. Universidade Federal de Pernambuco; Brasil
Fil: Corcoran, Cheryl. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
Materia
SCHIZOPHRENIA
NEUROSCIENCE
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/44639
Acceder
id CONICETDig_2a762a0eb4e0e1c7793c0e821dc1262e
oai_identifier_str oai:ri.conicet.gov.ar:11336/44639
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Automated analysis of free speech predicts psychosis onset in high-risk youthsBedi, GillinderCarrillo, FacundoCecchi, Guillermo AlbertoFernandez Slezak, DiegoSigman, MarianoMota, NatáliaRibeiro, SidartaJavitt, DanielCopelli, MauroCorcoran, CherylSCHIZOPHRENIANEUROSCIENCEhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novelcomputerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illnessin individuals.AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predictlater psychosis onset in youths at clinical high-risk (CHR) for psychosis.METHODS: Thirty-four CHR youths (11 females) had baseline interviews and were assessed quarterly for up to 2.5 years; fivetransitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic featurespredicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-outcross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features andprodromal symptom ratings was computed.RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markersof speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosisdevelopment with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantlycorrelated with prodromal symptoms.CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental statechanges in emergent psychosis. Recent developments in computer science, including natural language processing, could providethe foundation for future development of objective clinical tests for psychiatry.npj Schizophrenia (2015) 1, Article number: 15030; doi:10.1038/npjschz.2015.30; published online 26 August 2015Fil: Bedi, Gillinder. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados UnidosFil: Carrillo, Facundo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; ArgentinaFil: Cecchi, Guillermo Alberto. Ibm Research. Thomas J. Watson Research Center; Estados UnidosFil: Fernandez Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; ArgentinaFil: Sigman, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; ArgentinaFil: Mota, Natália. Universidade Federal do Rio Grande do Norte; BrasilFil: Ribeiro, Sidarta. Universidade Federal do Rio Grande do Norte; BrasilFil: Javitt, Daniel. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados UnidosFil: Copelli, Mauro. Universidade Federal de Pernambuco; BrasilFil: Corcoran, Cheryl. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados UnidosNature Publishing Group2015-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/44639Bedi, Gillinder; Carrillo, Facundo; Cecchi, Guillermo Alberto; Fernandez Slezak, Diego; Sigman, Mariano; et al.; Automated analysis of free speech predicts psychosis onset in high-risk youths; Nature Publishing Group; npj Schizophrenia; 1; 8-20152334-265XCONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1038/npjschz.2015.30info:eu-repo/semantics/altIdentifier/url/https://www.nature.com/articles/npjschz201530info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:59:56Zoai:ri.conicet.gov.ar:11336/44639instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:59:56.96CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Automated analysis of free speech predicts psychosis onset in high-risk youths
title Automated analysis of free speech predicts psychosis onset in high-risk youths
spellingShingle Automated analysis of free speech predicts psychosis onset in high-risk youths
Bedi, Gillinder
SCHIZOPHRENIA
NEUROSCIENCE
title_short Automated analysis of free speech predicts psychosis onset in high-risk youths
title_full Automated analysis of free speech predicts psychosis onset in high-risk youths
title_fullStr Automated analysis of free speech predicts psychosis onset in high-risk youths
title_full_unstemmed Automated analysis of free speech predicts psychosis onset in high-risk youths
title_sort Automated analysis of free speech predicts psychosis onset in high-risk youths
dc.creator.none.fl_str_mv Bedi, Gillinder
Carrillo, Facundo
Cecchi, Guillermo Alberto
Fernandez Slezak, Diego
Sigman, Mariano
Mota, Natália
Ribeiro, Sidarta
Javitt, Daniel
Copelli, Mauro
Corcoran, Cheryl
author Bedi, Gillinder
author_facet Bedi, Gillinder
Carrillo, Facundo
Cecchi, Guillermo Alberto
Fernandez Slezak, Diego
Sigman, Mariano
Mota, Natália
Ribeiro, Sidarta
Javitt, Daniel
Copelli, Mauro
Corcoran, Cheryl
author_role author
author2 Carrillo, Facundo
Cecchi, Guillermo Alberto
Fernandez Slezak, Diego
Sigman, Mariano
Mota, Natália
Ribeiro, Sidarta
Javitt, Daniel
Copelli, Mauro
Corcoran, Cheryl
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv SCHIZOPHRENIA
NEUROSCIENCE
topic SCHIZOPHRENIA
NEUROSCIENCE
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novelcomputerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illnessin individuals.AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predictlater psychosis onset in youths at clinical high-risk (CHR) for psychosis.METHODS: Thirty-four CHR youths (11 females) had baseline interviews and were assessed quarterly for up to 2.5 years; fivetransitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic featurespredicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-outcross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features andprodromal symptom ratings was computed.RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markersof speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosisdevelopment with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantlycorrelated with prodromal symptoms.CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental statechanges in emergent psychosis. Recent developments in computer science, including natural language processing, could providethe foundation for future development of objective clinical tests for psychiatry.npj Schizophrenia (2015) 1, Article number: 15030; doi:10.1038/npjschz.2015.30; published online 26 August 2015
Fil: Bedi, Gillinder. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
Fil: Carrillo, Facundo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Cecchi, Guillermo Alberto. Ibm Research. Thomas J. Watson Research Center; Estados Unidos
Fil: Fernandez Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Sigman, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Mota, Natália. Universidade Federal do Rio Grande do Norte; Brasil
Fil: Ribeiro, Sidarta. Universidade Federal do Rio Grande do Norte; Brasil
Fil: Javitt, Daniel. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
Fil: Copelli, Mauro. Universidade Federal de Pernambuco; Brasil
Fil: Corcoran, Cheryl. Columbia University; Estados Unidos. New York State Psychiatric Institute; Estados Unidos
description BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novelcomputerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illnessin individuals.AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predictlater psychosis onset in youths at clinical high-risk (CHR) for psychosis.METHODS: Thirty-four CHR youths (11 females) had baseline interviews and were assessed quarterly for up to 2.5 years; fivetransitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic featurespredicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-outcross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features andprodromal symptom ratings was computed.RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markersof speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosisdevelopment with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantlycorrelated with prodromal symptoms.CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental statechanges in emergent psychosis. Recent developments in computer science, including natural language processing, could providethe foundation for future development of objective clinical tests for psychiatry.npj Schizophrenia (2015) 1, Article number: 15030; doi:10.1038/npjschz.2015.30; published online 26 August 2015
publishDate 2015
dc.date.none.fl_str_mv 2015-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/44639
Bedi, Gillinder; Carrillo, Facundo; Cecchi, Guillermo Alberto; Fernandez Slezak, Diego; Sigman, Mariano; et al.; Automated analysis of free speech predicts psychosis onset in high-risk youths; Nature Publishing Group; npj Schizophrenia; 1; 8-2015
2334-265X
CONICET Digital
CONICET
url http://hdl.handle.net/11336/44639
identifier_str_mv Bedi, Gillinder; Carrillo, Facundo; Cecchi, Guillermo Alberto; Fernandez Slezak, Diego; Sigman, Mariano; et al.; Automated analysis of free speech predicts psychosis onset in high-risk youths; Nature Publishing Group; npj Schizophrenia; 1; 8-2015
2334-265X
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1038/npjschz.2015.30
info:eu-repo/semantics/altIdentifier/url/https://www.nature.com/articles/npjschz201530
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Nature Publishing Group
publisher.none.fl_str_mv Nature Publishing Group
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613775462760448
score 13.070432

Publicaciones similares