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

被引：386

作者：

Bedi G. ^{[1
,2
]}

Carrillo F. ^{[3
]}

Cecchi G.A. ^{[4
]}

Slezak D.F. ^{[3
]}

Sigman M. ^{[5
]}

Mota N.B. ^{[6
]}

Ribeiro S. ^{[6
]}

Javitt D.C. ^{[1
,7
]}

Copelli M. ^{[8
]}

Corcoran C.M. ^{[1
,7
]}

机构：

[1] Department of Psychiatry, College of Physicians, Columbia University, New York, NY

[2] Division on Substance Abuse, New York State Psychiatric Institute, New York, NY

[3] Department of computer Science, School of Sciences, Universidad de Buenos Aires, Buenos Aires

[4] Computational Biology Center-Neuroscience, IBM T.J. Watson Research Center, Yorktown Heights, NY

[5] Department of Physics, School of Sciences, Universidad de Buenos Aires, Buenos Aires

[6] Brain Institute, Federal University of Rio Grande do Norte, Natal

[7] Division of Experimental Therapeutics, New York State Psychiatric Institute, New York, NY

[8] Department of Physics, Federal University of Pernambuco, Recife

来源：

npj Schizophrenia | / 1卷 / 1期

关键词：

D O I：

10.1038/npjschz.2015.30

中图分类号：

学科分类号：

摘要：

BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novel computerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illness in individuals. AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predict later 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; five transitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic features predicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-out cross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features and prodromal symptom ratings was computed. RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markers of speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosis development with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantly correlated with prodromal symptoms. CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental state changes in emergent psychosis. Recent developments in computer science, including natural language processing, could provide the foundation for future development of objective clinical tests for psychiatry. © 2015 Schizophrenia International Research Society/Nature Publishing Group.

引用

共 17 条

[1]

Insel T.R., Landis S.C., Twenty-five years of progress: The view from nimh and ninds, Neuron, 80, pp. 561-567, (2013)

[2]

Adomavicius G., Tuzhilin A., Using data mining methods to build customer profiles, IEEE Comput, 34, pp. 74-82, (2001)

[3]

Elvevag B., Foltz P.W., Weinberger D.R., Goldberg T.E., Quantifying incoherence in speech: An automated methodology and novel application to schizophrenia, Schizophr Res, 93, pp. 304-316, (2007)

[4]

Poulin C., Shiner B., Thompson P., Vepstas L., Young-Xu Y., Goertzel B., Et al., Predicting the risk of suicide by analyzing the text of clinical notes, PLoS One, 9, (2014)

[5]

Bird S., Klein E., Loper E., Natural Language Processing with Python., (2009)

[6]

Bedi G., Cecchi G.A., Slezak D.F., Carrillo F., Sigman M., De Wit H., A window into the intoxicated mind? Speech as an index of psychoactive drug effects, Neuropsychopharmacology, 39, pp. 2340-2348, (2014)

[7]

Adler C.M., Malhotra A.K., Elman I., Goldberg T., Egan M., Pickar D., Et al., Comparison of ketamine-induced thought disorder in healthy volunteers and thought disorder in schizophrenia, Am J Psychiatry, 156, pp. 1646-1649, (1999)

[8]

Mota N.B., Vasconcelos N.A., Lemos N., Pieretti A.C., Kinouchi O., Cecchi G.A., Et al., Speech graphs provide a quantitative measure of thought disorder in psychosis, PLoS One, 7, (2012)

[9]

Elvevag B., Foltz P.W., Rosenstein M., Delisi L.E., An automated method to analyze language use in patients with schizophrenia and their first-degree relatives, J Neurolinguistics, 23, pp. 270-284, (2010)

[10]

DeVylder J.E., Muchomba F.M., Gill K.E., Ben-David S., Walder D.J., Malaspina D., Et al., Symptom trajectories and psychosis onset in a clinical high-risk cohort: The relevance of subthreshold thought disorder, Schizophr Res, 159, pp. 278-283, (2014)

← 1 2 →