Symptom trajectories and psychosis onset in a clinical high-risk cohort: The relevance of subthreshold thought disorder

DeVylder, Jordan; Muchomba, Felix M.; Gill, Kelly E.; Ben‐David, Shelly; Walder, Deborah J.; Malaspina, Dolores; Corcoran, Cheryl

doi:10.1016/j.schres.2014.08.008

Cited by 73 publications

(53 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further, this same classifier discriminated the speech of recentonset psychosis patients from that of healthy individuals with 72% accuracy, suggesting that its discriminatory power was relatively robust across illness stages, as has been found for clinical ratings of thought disorder 1,6 . Finally, the predictive automated and manual linguistic features were highly correlated in the cohort, providing evidence of concurrent validity.…”

Section: Discussionmentioning

confidence: 56%

“…the disruption in flow of meaning in language (derailment, tangentiality) 2 . This language disturbance is an early core feature of schizophrenia, evident in subtle form prior to initial psychosis onset, in cohorts of both familial 3 and clinical [4][5][6][7] high-risk youths, as assessed using clinical ratings. Beyond clinical ratings, there has been an effort to characterize early subtle language disturbances in clinical high-risk (CHR) individuals using linguistic analysis, with the aim of improving prediction.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Prediction of psychosis across protocols and risk cohorts using automated language analysis

et al. 2018

Self Cite

View full text Add to dashboard Cite

Language and speech are the primary source of data for psychiatrists to diagnose and treat mental disorders. In psychosis, the very structure of language can be disturbed, including semantic coherence (e.g., derailment and tangentiality) and syntactic complexity (e.g., concreteness). Subtle disturbances in language are evident in schizophrenia even prior to first psychosis onset, during prodromal stages. Using computer-based natural language processing analyses, we previously showed that, among English-speaking clinical (e.g., ultra) high-risk youths, baseline reduction in semantic coherence (the flow of meaning in speech) and in syntactic complexity could predict subsequent psychosis onset with high accuracy. Herein, we aimed to cross-validate these automated linguistic analytic methods in a second larger risk cohort, also English-speaking, and to discriminate speech in psychosis from normal speech. We identified an automated machine-learning speech classifier -comprising decreased semantic coherence, greater variance in that coherence, and reduced usage of possessive pronouns -that had an 83% accuracy in predicting psychosis onset (intra-protocol), a cross-validated accuracy of 79% of psychosis onset prediction in the original risk cohort (cross-protocol), and a 72% accuracy in discriminating the speech of recent-onset psychosis patients from that of healthy individuals. The classifier was highly correlated with previously identified manual linguistic predictors. Our findings support the utility and validity of automated natural language processing methods to characterize disturbances in semantics and syntax across stages of psychotic disorder. The next steps will be to apply these methods in larger risk cohorts to further test reproducibility, also in languages other than English, and identify sources of variability. This technology has the potential to improve prediction of psychosis outcome among at-risk youths and identify linguistic targets for remediation and preventive intervention. More broadly, automated linguistic analysis can be a powerful tool for diagnosis and treatment across neuropsychiatry.Key words: Automated language analysis, prediction of psychosis, semantic coherence, syntactic complexity, high-risk youths, machine learning (World Psychiatry 2018;17:67-75) Language offers a privileged view into the mind: it is the basis by which we infer others' thought processes, such that disorganized language is considered to reflect disorder in thought. Language disturbance is prevalent in schizophrenia and is related to functional disability, given that an individual needs to think and speak clearly in order to maintain friends and a job 1 . In schizophrenia, the speaker "violates the syntactical and semantic conventions which govern language usage", yielding reduction in syntactic complexity (concrete speech, poverty of content) and loss of semantic coherence, e.g. the disruption in flow of meaning in language (derailment, tangentiality) 2. This language disturbance is an early core feature of sch...

show abstract

Section: Discussionmentioning

confidence: 56%

mentioning

confidence: 99%

Prediction of psychosis across protocols and risk cohorts using automated language analysis

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Known predictors of psychosis transition in CHR cohorts include subthreshold thought disorder (Klosterkotter et al 2001; Haroun et al 2006; Cannon et al 2008; Ruhrmann et al 2010; Bearden et al 2011; Demjaha et al 2012; Nelson et al 2013; DeVylder et al 2014), negative symptom severity (Velthorst et al 2009; Demjaha et al 2012; Piskulic et al 2012; Nelson et al 2013; Valmaggia et al 2013) and sensory processing deficits (Bodatsch et al 2011; Kayser et al 2013, 2014; Perez et al 2014). The present study examined facial and auditory emotion recognition deficits as potential additional predictors of liability for transition to schizophrenia.…”

Section: Discussionmentioning

confidence: 99%

“…To date, the strongest and most reliable predictors of transition to psychosis among at-risk individuals are symptom severity (Cannon et al 2008; Lemos-Giraldez et al 2009; Ruhrmann et al 2010; Demjaha et al 2012; Nelson et al 2013), particularly of negative symptoms (Velthorst et al 2009; Demjaha et al 2012; Piskulic et al 2012; Nelson et al 2013; Valmaggia et al 2013) and subthreshold thought disorder (Klosterkotter et al 2001; Haroun et al 2006; Bearden et al 2011; Demjaha et al 2012; Kantrowitz et al 2014; Nelson et al 2013; DeVylder et al 2014). While neuropsychological deficits exist in schizophrenia and in at-risk individuals, to date they have not been found to be of value in predicting transition over and above the contribution of symptoms (Seidman et al 2010; Fusar-Poli et al 2012b; Lin et al 2013).…”

Section: Introductionmentioning

confidence: 99%

Emotion recognition deficits as predictors of transition in individuals at clinical high risk for schizophrenia: a neurodevelopmental perspective

et al. 2015

View full text Add to dashboard Cite

Background Schizophrenia is characterized by profound and disabling deficits in the ability to recognize emotion in facial expression and tone of voice. Although these deficits are well documented in established schizophrenia using recently validated tasks, their predictive utility in at-risk populations has not been formally evaluated. Method The Penn Emotion Recognition and Discrimination tasks, and recently developed measures of auditory emotion recognition, were administered to 49 clinical high-risk subjects prospectively followed for 2 years for schizophrenia outcome, and 31 healthy controls, and a developmental cohort of 43 individuals aged 7–26 years. Deficit in emotion recognition in at-risk subjects was compared with deficit in established schizophrenia, and with normal neurocognitive growth curves from childhood to early adulthood. Results Deficits in emotion recognition significantly distinguished at-risk patients who transitioned to schizophrenia. By contrast, more general neurocognitive measures, such as attention vigilance or processing speed, were non-predictive. The best classification model for schizophrenia onset included both face emotion processing and negative symptoms, with accuracy of 96%, and area under the receiver-operating characteristic curve of 0.99. In a parallel developmental study, emotion recognition abilities were found to reach maturity prior to traditional age of risk for schizophrenia, suggesting they may serve as objective markers of early developmental insult. Conclusions Profound deficits in emotion recognition exist in at-risk patients prior to schizophrenia onset. They may serve as an index of early developmental insult, and represent an effective target for early identification and remediation. Future studies investigating emotion recognition deficits at both mechanistic and predictive levels are strongly encouraged.

show abstract

“…Furthermore, 'disorganized communication' was the sole predictor of psychosis in a UHR sample (12-30-year-olds) with a 26% conversion rate at 2.5-year follow-up, and suggested as a potential endophenotype or stable trait marker for schizophrenia risk (DeVylder et al, 2014). A relationship between communication deviances and 2-year conversion (38.9%) was also revealed in speech analyses of mixed-age UHR patients (17 ± 4 years), using audio recordings and transcripts (Bearden et al, 2011).…”

Section: Conversion To Psychosis At One-year Follow-upmentioning

confidence: 95%

Twelve-month psychosis-predictive value of the ultra-high risk criteria in children and adolescents

Armando

Pontillo

Crescenzo

et al. 2015

Schizophrenia Research

View full text Add to dashboard Cite

Objective: The validity of current ultra-high risk (UHR) criteria is under-examined in help-seeking minors, particularly, in children below the age of 12 years. Thus, the present study investigated predictors of one-year outcome in children and adolescents (CAD) with UHR status.Method: Thirty-five children and adolescents (age 9-17 years) meeting UHR criteria according to the Structured Interview for Psychosis-Risk Syndromes were followed-up for 12 months.Regression analyses were employed to detect baseline predictors of conversion to psychosis and of outcome of non-converters (remission and persistence of UHR versus conversion).

show abstract

Symptom trajectories and psychosis onset in a clinical high-risk cohort: The relevance of subthreshold thought disorder

Cited by 73 publications

References 38 publications

Prediction of psychosis across protocols and risk cohorts using automated language analysis

Prediction of psychosis across protocols and risk cohorts using automated language analysis

Emotion recognition deficits as predictors of transition in individuals at clinical high risk for schizophrenia: a neurodevelopmental perspective

Twelve-month psychosis-predictive value of the ultra-high risk criteria in children and adolescents

Contact Info

Product

Resources

About