Abstract Background Recent studies have reported significant advances in modeling the biological basis of heterogeneity in major depressive disorder (MDD), but investigators have also identified important technical challenges, including scanner-related artifacts, a propensity for multivariate models to overfit, and a need for larger samples with deeper clinical phenotyping. The goals of this work were to develop and evaluate dimensional and categorical solutions to parsing heterogeneity in depression that are stable and generalizable in a large, deeply phenotyped, single-site sample. Methods We used regularized canonical correlation analysis (RCCA) to identify data-driven brain-behavior dimensions explaining individual differences in depression symptom domains in a large, single-site dataset comprising clinical assessments and resting state fMRI data for N=328 patients with MDD and N=461 healthy controls. We examined the stability of clinical loadings and model performance in held-out data. Finally, hierarchical clustering on these dimensions was used to identify categorical depression subtypes Results The optimal RCCA model yielded three robust and generalizable brain-behavior dimensions explaining individual differences in depressed mood and anxiety, anhedonia, and insomnia. Hierarchical clustering identified four depression subtypes, each with distinct clinical symptom profiles, abnormal RSFC patterns, and antidepressant responsiveness to repetitive transcranial magnetic stimulation. Conclusions Our results define dimensional and categorical solutions to parsing neurobiological heterogeneity in MDD that are stable, generalizable, and capable of predicting treatment outcomes, each with distinct advantages in different contexts. They also provide additional evidence that RCCA and hierarchical clustering are effective tools for investigating associations between functional connectivity and clinical symptoms.

Dimensional and Categorical Solutions to Parsing Depression Heterogeneity in a Large Single-Site Sample