Applying Machine-Learning and Deep-Learning to Predict Depression from Brain MRI and Identify Depression-Related Brain Biology

The accuracy of grey-matter predictors of depression has remained limited. In this study, brain-based predictors of major depressive disorder (MDD) were trained using machine-learning (Best Linear Unbiased Predictors [BLUP]) and deep-learning (ResNet3D) techniques applied to high-dimensional (voxel-wise) grey-matter structure extracted from T1-weighted structural MRI. The training sample comprised 987 MDD cases and 3,934 controls from the UK Biobank. Predictors were evaluated in an independent sub-cohort of 483 MDD cases and 1,939 controls from the UK Biobank and replicated in a clinical cohort (DEP-ARREST CLIN) of 64 cases and 32 controls. In the UK Biobank, logistic regression showed a significant association between the BLUP predictor and MDD status (AUC=0.57; OR=1.28 [1.15-1.43]; p-value=1.1×10 ⁻⁵ ), which was confirmed in both males and females. By partitioning the BLUP predictor by brain regions of interest (ROI), we found nominal significance supporting the contribution of previously identified MDD-related ROIs (e.g. hippocampus and amygdala). The BLUP predictor overlapped partially with a polygenic score (PGS) of major depression but also captured a signal that was not captured by the genetic score (combined AUC=0.66, p-value=0.024 when compared to PGS alone). No association passed multiple testing correction in the DEP-ARREST CLIN cohort, likely due to the small sample size. In contrast, the deep-learning predictor did not show a significant association with MDD after multiple testing corrections. Our novel application of the BLUP method shows promising predicting accuracy and suggests new leads to overcome the remaining challenges in predicting MDD from brain imaging.