Abstract
Background: The greater presence of neurodevelopmental antecedants may differentiate schizophrenia from bipolar disorders (BD). Machine learning/pattern recognition allows us to estimate the biological age of the brain from structural magnetic resonance imaging scans (MRI). The discrepancy between brain and chronological age could contribute to early detection and differentiation of BD and schizophrenia. Methods: We estimated brain age in 2 studies focusing on early stages of schizophrenia or BD. In the first study, we recruited 43 participants with first episode of schizophrenia-spectrum disorders (FES) and 43 controls. In the second study, we included 96 offspring of bipolar parents (48 unaffected, 48 affected) and 60 controls. We used relevance vector regression trained on an independent sample of 504 controls to estimate the brain age of study participants from structural MRI. We calculated the brain-age gap estimate (BrainAGE) score by subtracting the chronological age from the brain age. Results: Participants with FES had higher BrainAGE scores than controls (F(1, 83) = 8.79, corrected P =. 008, Cohen's d = 0.64). Their brain age was on average 2.64 ± 4.15 years greater than their chronological age (matched t(42) = 4.36, P <. 001). In contrast, participants at risk or in the early stages of BD showed comparable BrainAGE scores to controls (F(2,149) = 1.04, corrected P =. 70, η2 = 0.01) and comparable brain and chronological age. Conclusions: Early stages of schizophrenia, but not early stages of BD, were associated with advanced BrainAGE scores. Participants with FES showed neurostructural alterations, which made their brains appear 2.64 years older than their chronological age. BrainAGE scores could aid in early differential diagnosis between BD and schizophrenia.
Original language | English |
---|---|
Pages (from-to) | 191-198 |
Number of pages | 8 |
Journal | Schizophrenia Bulletin |
Volume | 45 |
Issue number | 1 |
DOIs | |
Publication status | Published - Jan 1 2019 |
Bibliographical note
Funding Information:This study was supported by grants from the Canadian Institutes of Health Research (grant number 106469); the Nova Scotia Health Research Foundation; Brain and Behavioral Research Foundation grant to T.H.; the Ministry of Health, Czech Republic (grants number 16-32791A, 16-32696A); and by German Research Foundation grant (DFG; Project FR 3709/1-1) to K.F. The National Institute of Mental Health, Klecany, Czech Republic was supported by project Nr. LO1611 with funding from the MEYS under the NPU I program. The sponsors of the study had no role in the design or conduct of this study; in the collection, management, analysis, and interpretation of the data; or in the preparation, review, or approval of the manuscript.
Publisher Copyright:
© 2017 The Author(s) 2017. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center. All rights reserved. For permissions, please email: journals.permissions@oup.com.
ASJC Scopus Subject Areas
- Psychiatry and Mental health