@article{NGUYEN2021,
title = {Patterns of Pre-Treatment Reward Task Brain Activation Predict Individual Antidepressant Response: Key Results from the EMBARC Randomized Clinical Trial},
journal = {Biological Psychiatry},
year = {2021},
issn = {0006-3223},
doi = {https://doi.org/10.1016/j.biopsych.2021.09.011},
url = {https://www.sciencedirect.com/science/article/pii/S0006322321016000},
author = {Kevin P. Nguyen and Cherise Chin Fatt and Alex Treacher and Cooper Mellema and Crystal Cooper and Manish K. Jha and Benji Kurian and Maurizio Fava and Patrick J. McGrath and Myrna Weissman and Mary L. Phillips and Madhukar H. Trivedi and Albert Montillo},
keywords = {antidepressants, depression, treatment selection, fMRI, deep learning, precision medicine},
abstract = {ABSTRACT
Background
The lack of biomarkers to inform antidepressant selection is a key challenge in personalized depression treatment. This work identifies candidate biomarkers by building deep learning predictors of individual treatment outcomes using reward processing measures from functional MRI, clinical assessments, and demographics.
Methods
Participants in the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study (n = 222) underwent reward processing task-based functional MRI at baseline and were randomized to 8 weeks of sertraline (n = 106) or placebo (n = 116). Subsequently, sertraline non-responders (n = 37) switched to 8 weeks of bupropion. The change in Hamilton Rating Scale for Depression (ΔHAMD) was measured after treatment. Reward processing, clinical measurements, and demographics were used to train treatment-specific deep learning models.
Results
The predictive model for sertraline achieved R2 of 48% (95% CI 33-61%, p < 10-3) in predicting ΔHAMD and number-needed-to-treat (NNT) of 4.86 participants in predicting response. The placebo model achieved R2 of 28% (95% CI 15-42%, p < 10-3) and NNT of 2.95 in predicting response. The bupropion model achieved R2 of 34% (95% CI 10-59%, p < 10-3) and NNT of 1.68 in predicting response. Brain regions where reward processing activity was predictive included the prefrontal cortex and cerebellar crus 1 for sertraline and the cingulate cortex, caudate, orbitofrontal cortex, and crus 1 for bupropion.
Conclusions
These findings demonstrate the utility of reward processing measurements and deep learning to predict antidepressant outcomes and to form multimodal treatment biomarkers.}
}