LAUSR

Background: Treatment of major depression often involves a lengthy trial and error process delaying improvement and increases risk of suicide especially in late-life depression (LLD). We have demonstrated changes in neural connectivity following a single dose that depended on future remission. Here we combine connectivity and task-based activation to predict remission. Methods: Participants with LLD completed a 12-week venlafaxine treatment and underwent functional magnetic resonance imaging (fMRI, at rest and during emotion reactivity and regulation tasks) at baseline and a day following a single dose of venlafaxine. Remitted participants had Montgomery-Asberg depression rating scale (MADRS)<10 for two weeks. We employed principal components analysis, Tikhonov-regularized logistic classification, and least angle regression feature selection to predict remission by the end of the 12-week trial. We utilized ten-fold cross-validation and Receiver-OperatorCurves (ROC) analysis. To determine task-region pairs that significantly contributed to the algorithm’s ability to predict remission, we used permutation testing. Results: The fMRI data yielded a sensitivity of 80% and a specificity of 63%, a 15% increase in accuracy over baseline MADRS, which was further improved by using the change in activation following a single dose. Activation from the frontal cortex, hippocampus, parahippocampus, caudate, thalamus, medial temporal cortex, middle cingulate, and visual cortex predicted treatment remission. Conclusions: Acute, dynamic trajectories of functional imaging metrics in response to a pharmacological intervention are a valuable tool towards predicting treatment response in late-life depression and elucidating the mechanism of pharmacological therapies in the context of the brain’s functional architecture. Supported By: NIMH R01 MH076079; 5R01 AG033575; K23 MH086686; P30 MH90333; 5R01 MH083660; T32 MH019986