J Psychiatry Neurosci 2015;40(5):316-324
Tomas Hajek, MD, PhD; Christopher Cooke, MSc; Miloslav Kopecek, MD, PhD; Tomas Novak, MD, PhD; Cyril Hoschl, MD; Martin Alda, MD
Background: Brain imaging is of limited diagnostic use in psychiatry owing to clinical heterogeneity and low sensitivity/specificity of between- group neuroimaging differences. Machine learning (ML) may better translate neuroimaging to the level of individual participants. Studying unaffected offspring of parents with bipolar disorders (BD) decreases clinical heterogeneity and thus increases sensitivity for detection of biomarkers. The present study used ML to identify individuals at genetic high risk (HR) for BD based on brain structure.
Methods: We studied unaffected and affected relatives of BD probands recruited from 2 sites (Halifax, Canada, and Prague, Czech Republic). Each participant was individually matched by age and sex to controls without personal or family history of psychiatric disorders. We applied support vector machines (SVM) and Gaussian process classifiers (GPC) to structural MRI.
Results: We included 45 unaffected and 36 affected relatives of BD probands matched by age and sex on an individual basis to healthy controls. The SVM of white matter distinguished unaffected HR from control participants (accuracy = 68.9%, p = 0.001), with similar accuracy for the GPC (65.6%, p = 0.002) or when analyzing data from each site separately. Differentiation of the more clinically heterogeneous affected familiar group from healthy controls was less accurate (accuracy = 59.7%, p = 0.05). Machine learning applied to grey matter did not distinguish either the unaffected HR or affected familial groups from controls. The regions that most contributed to between-group discrimination included white matter of the inferior/middle frontal gyrus, inferior/middle temporal gyrus and precuneus.
Limitations: Although we recruited 126 participants, ML benefits from even larger samples.
Conclusion: Machine learning applied to white but not grey matter distinguished unaffected participants at high and low genetic risk for BD based on regions previously implicated in the pathophysiology of BD.
Submitted May 29, 2014; Revised Oct. 16, 2014; Accepted Dec. 23, 2014; Early-released Apr. 8, 2015.
Acknowledgements: This study was supported by funding from the Canadian Institutes of Health Research (103703, 106469), the Nova Scotia Health Research Foundation and grant from the Ministry of Health (NT13891) of Czech Republic. 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. The authors report no biomedical financial interests or potential conflicts of interest.
Affiliations: Department of Psychiatry, Dalhousie University, Halifax, NS, Canada (Hajek, Cooke, Alda); Prague Psychiatric Centre/ National Institute of Mental Health, Prague, Czech Republic (Hajek, Kopecek, Novak, Hoschl, Alda); Charles University, 3rd Faculty of Medicine, Prague, Czech Republic (Kopecek, Novak, Hoschl, Alda).
Competing interests: The authors are supported by grants from the Canadian Institutes of Health Research (103703, 106469), the Nova Scotia Health Research Foundation and the Ministry of Health of Czech Republic (NT13891). C. Höschl declares personal fees from Servier, Lundbeck International Neuroscience Foundation, Eli Lily and Janssen-Cilag. No other competing interests declared.
Contributors: T. Hajek and M. Alda designed the study. T. Hajek, M. Kopecek, T. Novak and M. Alda acquired the data, which T. Hajek, C. Cooke and C. Höschl analyzed. T. Hajek wrote the article, which all authors reviewed and approved for publication.
Correspondence to:T. Hajek, Department of Psychiatry, Dalhousie University, QEII HSC, A.J. Lane Bldg., Rm. 3093, 5909 Veteran’s Memorial Lane, Halifax, NS B3H 2E2; firstname.lastname@example.org