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

Abstract

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