City Research Online

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Belov, V., Erwin-Grabner, T., Aghajani, M. , Aleman, A., Amod, A. R., Basgoze, Z., Benedetti, F., Besteher, B., Bülow, R., Ching, C. R. K., Connolly, C. G., Cullen, K., Davey, C. G., Dima, D. ORCID: 0000-0002-2598-0952, Dols, A., Evans, J. W., Fu, C. H. Y., Gonul, A. S., Gotlib, I. H., Grabe, H. J., Groenewold, N., Hamilton, J. P., Harrison, B. J., Ho, T. C., Mwangi, B., Jaworska, N., Jahanshad, N., Klimes-Dougan, B., Koopowitz, S-M., Lancaster, T., Li, M., Linden, D. E. J., MacMaster, F. P., Mehler, D. M. A., Melloni, E., Mueller, B. A., Ojha, A., Oudega, M. L., Penninx, B. W. J. H., Poletti, S., Pomarol-Clotet, E., Portella, M. J., Pozzi, E., Reneman, L., Sacchet, M. D., Sämann, P. G., Schrantee, A., Sim, K., Soares, J. C., Stein, D. J., Thomopoulos, S. I., Uyar-Demir, A., van der Wee, N. J. A., van der Werff, S. J. A., Völzke, H., Whittle, S., Wittfeld, K., Wright, M. J., Wu, M-J., Yang, T. T., Zarate, C., Veltman, D. J., Schmaal, L., Thompson, P. M. & Goya-Maldonado, R. (2024). Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures. Scientific Reports, 14(1), article number 1084. doi: 10.1038/s41598-023-47934-8


Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.

Publication Type: Article
Additional Information: This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit
Publisher Keywords: ENIGMA Major Depressive Disorder working group, Brain, Humans, Magnetic Resonance Imaging, Depressive Disorder, Major, Benchmarking, Neuroimaging, Machine Learning, Humans, Depressive Disorder, Major, Benchmarking, Brain, Neuroimaging, Machine Learning, Magnetic Resonance Imaging
Subjects: B Philosophy. Psychology. Religion > BF Psychology
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Departments: School of Health & Psychological Sciences
School of Health & Psychological Sciences > Psychology
SWORD Depositor:
[thumbnail of Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures.pdf]
Text - Published Version
Available under License Creative Commons: Attribution International Public License 4.0.

Download (2MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login