Literature DB >> 33991405

Exploring specific predictors of psychosis onset over a 2-year period: A decision-tree model.

Jone Bjornestad1,2,3, Tore Tjora1, Johannes H Langeveld2,4, Helen J Stain2,5, Inge Joa2,4, Jan Olav Johannessen2,4, Michelle Friedman-Yakoobian6,7, Wenche Ten Velden Hegelstad1,2.   

Abstract

AIM: The fluctuating symptoms of clinical high risk for psychosis hamper conversion prediction models. Exploring specific symptoms using machine-learning has proven fruitful in accommodating this challenge. The aim of this study is to explore specific predictors and generate atheoretical hypotheses of onset using a close-monitoring, machine-learning approach.
METHODS: Study participants, N = 96, mean age 16.55 years, male to female ratio 46:54%, were recruited from the Prevention of Psychosis Study in Rogaland, Norway. Participants were assessed using the Structured Interview for Psychosis Risk Syndromes (SIPS) at 13 separate assessment time points across 2 years, yielding 247 specific scores. A machine-learning decision-tree analysis (i) examined potential SIPS predictors of psychosis conversion and (ii) hierarchically ranked predictors of psychosis conversion.
RESULTS: Four out of 247 specific SIPS symptom scores were significant: (i) reduced expression of emotion at baseline, (ii) experience of emotions and self at 5 months, (iii) perceptual abnormalities/hallucinations at 3 months and (iv) ideational richness at 6 months. No SIPS symptom scores obtained after 6 months of follow-up predicted psychosis.
CONCLUSIONS: Study findings suggest that early negative symptoms, particularly those observable by peers and arguably a risk factor for social exclusion, were predictive of psychosis. Self-expression and social behaviour might prove relevant entry points for early intervention in psychosis and psychosis risk. Testing study results in larger samples and at other sites is warranted.
© 2021 The Authors. Early Intervention in Psychiatry published by John Wiley & Sons Australia, Ltd.

Entities:  

Keywords:  clinical high risk; machine learning; negative symptoms; prediction; psychosis

Mesh:

Year:  2021        PMID: 33991405     DOI: 10.1111/eip.13175

Source DB:  PubMed          Journal:  Early Interv Psychiatry        ISSN: 1751-7885            Impact factor:   2.732


  1 in total

1.  Associations between symptom and neurocognitive dimensions in clinical high risk for psychosis.

Authors:  Ingvild Aase; Johannes H Langeveld; Inge Joa; Jan Olav Johannessen; Ingvild Dalen; Wenche Ten Velden Hegelstad
Journal:  Schizophr Res Cogn       Date:  2022-06-02
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.