Header

UZH-Logo

Maintenance Infos

Prediction of psychosis using neural oscillations and machine learning in neuroleptic-naïve at-risk patients


Ramyead, Avinash; Studerus, Erich; Kometer, Michael; Uttinger, Martina; Gschwandtner, Ute; Fuhr, Peter; Riecher-Rössler, Anita (2016). Prediction of psychosis using neural oscillations and machine learning in neuroleptic-naïve at-risk patients. World Journal of Biological Psychiatry, 17(4):285-295.

Abstract

OBJECTIVES: This study investigates whether abnormal neural oscillations, which have been shown to precede the onset of frank psychosis, could be used towards the individualised prediction of psychosis in clinical high-risk patients.
METHODS: We assessed the individualised prediction of psychosis by detecting specific patterns of beta and gamma oscillations using machine-learning algorithms. Prediction models were trained and tested on 53 neuroleptic-naïve patients with a clinical high-risk for psychosis. Of these, 18 later transitioned to psychosis. All patients were followed up for at least 3 years. For an honest estimation of the generalisation capacity, the predictive performance of the models was assessed in unseen test cases using repeated nested cross-validation.
RESULTS: Transition to psychosis could be predicted from current-source density (CSD; area under the curve [AUC] = 0.77), but not from lagged phase synchronicity data (LPS; AUC = 0.56). Combining both modalities did not improve the predictive accuracy (AUC = 0.78). The left superior temporal gyrus, the left inferior parietal lobule and the precuneus most strongly contributed to the prediction of psychosis.
CONCLUSIONS: Our results suggest that CSD measurements extracted from clinical resting state EEG can help to improve the prediction of psychosis on a single-subject level.

Abstract

OBJECTIVES: This study investigates whether abnormal neural oscillations, which have been shown to precede the onset of frank psychosis, could be used towards the individualised prediction of psychosis in clinical high-risk patients.
METHODS: We assessed the individualised prediction of psychosis by detecting specific patterns of beta and gamma oscillations using machine-learning algorithms. Prediction models were trained and tested on 53 neuroleptic-naïve patients with a clinical high-risk for psychosis. Of these, 18 later transitioned to psychosis. All patients were followed up for at least 3 years. For an honest estimation of the generalisation capacity, the predictive performance of the models was assessed in unseen test cases using repeated nested cross-validation.
RESULTS: Transition to psychosis could be predicted from current-source density (CSD; area under the curve [AUC] = 0.77), but not from lagged phase synchronicity data (LPS; AUC = 0.56). Combining both modalities did not improve the predictive accuracy (AUC = 0.78). The left superior temporal gyrus, the left inferior parietal lobule and the precuneus most strongly contributed to the prediction of psychosis.
CONCLUSIONS: Our results suggest that CSD measurements extracted from clinical resting state EEG can help to improve the prediction of psychosis on a single-subject level.

Statistics

Citations

Dimensions.ai Metrics
41 citations in Web of Science®
37 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > Psychiatric University Hospital Zurich > Clinic for Psychiatry, Psychotherapy, and Psychosomatics
Dewey Decimal Classification:610 Medicine & health
Scopus Subject Areas:Health Sciences > Psychiatry and Mental Health
Life Sciences > Biological Psychiatry
Language:English
Date:2016
Deposited On:04 Feb 2016 10:36
Last Modified:26 Jan 2022 08:49
Publisher:Informa Healthcare
ISSN:1562-2975
OA Status:Closed
Publisher DOI:https://doi.org/10.3109/15622975.2015.1083614
PubMed ID:26453061
Full text not available from this repository.