Pharmacotherapy for TRD is more viable over past 15 years in part due to advances in clinical trials such as the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) and the US Department of Veterans Affairs Augmentation and Switching Treatments for Improving Depression Outcomes (VAST-D) study.
Patients with major depressive disorder who entered level 3 of the STAR*D were included in the TRD group, while patients who responded to treatment and entered follow-up from level 1 or 2 were included in the non-TRD group.
We used features from enrollment and level 1 treatment (up to week 2 response only) of STAR*D to explore the feature space comprehensively and applied machine learning methods to model TRD outcome at level 2.