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.

Electroconvulsive therapy (ECT) is one of the most effective treatments for major depression disorder (MDD). ECT can induce neurogenesis and synaptogenesis in hippocampus, which contains distinct subfields, e.g., the cornu ammonis (CA) subfields, a granule cell layer (GCL), a molecular layer (ML), and the subiculum. It is unclear which subfields are affected by ECT and whether we predict the future treatment response to ECT by using volumetric information of hippocampal subfields at baseline? In this study, 24 patients with severe MDD received the ECT and their structural brain images were acquired with magnetic resonance imaging before and after ECT. A state-of-the-art hippocampal segmentation algorithm from Freesurfer 6.0 was used. We found that ECT induced volume increases in CA subfields, GCL, ML and subiculum. We applied a machine learning algorithm to the hippocampal subfield volumes at baseline and were able to predict the change in depressive symptoms (r = 0.81; within remitters, r = 0.93). Receiver operating characteristic analysis also showed robust prediction of remission with an area under the curve of 0.90. Our findings provide evidence for particular hippocampal subfields having specific roles in the response to ECT. We also provide an analytic approach for generating predictions about clinical outcomes for ECT in MDD.

Cortical gyrification of the brain represents the folding characteristic of the cerebral cortex. How the brain cortical gyrification changes from childhood to old age in healthy human subjects is still unclear. Additionally, studies have shown regional gyrification alterations in patients with major psychiatric disorders, such as major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SCZ). However, whether the lifespan trajectory of gyrification over the brain is altered in patients diagnosed with major psychiatric disorders is still unknown. In this study, we investigated the trajectories of gyrification in three independent cohorts based on structural brain images of 881 subjects from age 4 to 83. We discovered that the trajectory of gyrification during normal development and aging was not linear and could be modeled with a logarithmic function. We also found that the gyrification trajectories of patients with MDD, BD and SCZ were deviated from the healthy one during adulthood, indicating altered aging in the brain of these patients.