The relationship between cognitive deficits and impaired short-term functional outcome in clinical high-risk for psychosis participants: a machine learning and modelling approach

Haining, K. , Brunner, G., Gajwani, R. , Gross, J. , Gumley, A. I. , Lawrie, S. M., Schwannauer, M., Schultze-Lutter, F. and Uhlhaas, P. J. (2021) The relationship between cognitive deficits and impaired short-term functional outcome in clinical high-risk for psychosis participants: a machine learning and modelling approach. Schizophrenia Research, 231, pp. 24-31. (doi: 10.1016/j.schres.2021.02.019) (PMID:33744682)

[img] Text
236251.pdf - Accepted Version
Restricted to Repository staff only until 18 March 2022.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

1MB
[img] Text
236251Suppl.pdf - Supplemental Material
Restricted to Repository staff only until 18 March 2022.

1MB

Abstract

Poor functional outcomes are common in individuals at clinical high-risk for psychosis (CHR-P), but the contribution of cognitive deficits remains unclear. We examined the potential utility of cognitive variables in predictive models of functioning at baseline and follow-up with machine learning methods. Additional models fitted on baseline functioning variables were used as a benchmark to evaluate model performance. Data were available for 1) 146 CHR-P individuals of whom 118 completed a 6- and/or 12-month follow-up, 2) 47 participants not fulfilling CHR criteria (CHR-Ns) but displaying affective and substance use disorders and 3) 55 healthy controls (HCs). Predictors of baseline global assessment of functioning (GAF) scores were selected by L1-regularised least angle regression and then used to train classifiers to predict functional outcome in CHR-P individuals. In CHR-P participants, cognitive deficits together with clinical and functioning variables explained 41% of the variance in baseline GAF scores while cognitive variables alone explained 12%. These variables allowed classification of functional outcome with an average balanced accuracy (BAC) of 63% in both mixed- and cross-site models. However, higher accuracies (68%–70%) were achieved using classifiers fitted only on baseline functioning variables. Our findings suggest that cognitive deficits, alongside clinical and functioning variables, displayed robust relationships with impaired functioning in CHR-P participants at baseline and follow-up. Moreover, these variables allow for prediction of functional outcome. However, models based on baseline functioning variables showed a similar performance, highlighting the need to develop more accurate algorithms for predicting functional outcome in CHR-P participants.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Uhlhaas, Professor Peter and Brunner, Gina and Gajwani, Dr Ruchika and Gross, Professor Joachim and Gumley, Professor Andrew and Haining, Kate
Authors: Haining, K., Brunner, G., Gajwani, R., Gross, J., Gumley, A. I., Lawrie, S. M., Schwannauer, M., Schultze-Lutter, F., and Uhlhaas, P. J.
College/School:College of Medical Veterinary and Life Sciences > Institute of Health and Wellbeing > Mental Health and Wellbeing
College of Medical Veterinary and Life Sciences > Institute of Neuroscience and Psychology
Journal Name:Schizophrenia Research
Publisher:Elsevier
ISSN:0920-9964
ISSN (Online):1573-2509
Published Online:18 March 2021
Copyright Holders:Copyright © 2021 Elsevier B.V.
First Published:First published in Schizophrenia Research 231:24-31
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
190713Using Magnetoencephalography to Investigate Aberrant Neural Synchrony in Prodromal Schizophrenia: A Translational Biomarker ApproachPeter UhlhaasMedical Research Council (MRC)MR/L011689/1NP - Centre for Cognitive Neuroimaging (CCNi)