Patterns of Pretreatment Reward Task Brain Activation Predict Individual Antidepressant Response: Key Results From the EMBARC Randomized Clinical Trial
| Autor: | Manish K. Jha, Madhukar H. Trivedi, Patrick J. McGrath, Benji T. Kurian, Alex Treacher, Kevin P. Nguyen, Maurizio Fava, Myrna M. Weissman, Cooper Mellema, Cherise Chin Fatt, Mary L. Phillips, Crystal Cooper, Albert Montillo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Calcium Phosphates
medicine.medical_specialty Biomedical Research Placebo Article Task (project management) law.invention Machine Learning Physical medicine and rehabilitation Randomized controlled trial Reward law Sertraline medicine Humans Bupropion Biological Psychiatry Depression (differential diagnoses) Depressive Disorder Major business.industry Hamilton Rating Scale for Depression Brain Antidepressive Agents Treatment Outcome Antidepressant business Biomarkers medicine.drug |
| Zdroj: | Biol Psychiatry |
| ISSN: | 1873-2402 |
| Popis: | 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 R(2) 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 R(2) of 28% (95% CI 15-42%, p < 10(−3)) and NNT of 2.95 in predicting response. The bupropion model achieved R(2) 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. CLINICAL TRIAL REGISTRATION: NCT01407094 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect