Patterns of Pretreatment Reward Task Brain Activation Predict Individual Antidepressant Response: Key Results From the EMBARC Randomized Clinical Trial

Published:September 22, 2021DOI:



      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 magnetic resonance imaging, clinical assessments, and demographics.


      Participants in the EMBARC (Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care) study (n = 222) underwent reward processing task-based functional magnetic resonance imaging at baseline and were randomized to 8 weeks of sertraline (n = 106) or placebo (n = 116). Subsequently, sertraline nonresponders (n = 37) switched to 8 weeks of bupropion. The change in Hamilton Depression Rating Scale was measured after treatment. Reward processing, clinical measurements, and demographics were used to train treatment-specific deep learning models.


      The predictive model for sertraline achieved R2 of 48% (95% CI, 33%–61%; p < 10−3) in predicting the change in Hamilton Depression Rating Scale 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.


      These findings demonstrate the utility of reward processing measurements and deep learning to predict antidepressant outcomes and to form multimodal treatment biomarkers.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Biological Psychiatry
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Dupuy J.M.
        • Ostacher M.J.
        • Huffman J.
        • Perlis R.H.
        • Nierenberg A.A.
        A critical review of pharmacotherapy for major depressive disorder.
        Int J Neuropsychopharmacol. 2011; 14: 1417-1431
        • Rush A.J.
        • Trivedi M.H.
        • Wisniewski S.R.
        • Nierenberg A.A.
        • Stewart J.W.
        • Warden D.
        • et al.
        Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: A STAR∗D report.
        Am J Psychiatry. 2006; 163: 1905-1917
        • Chin Fatt C.R.
        • Jha M.K.
        • Cooper C.M.
        • Fonzo G.
        • South C.
        • Grannemann B.
        • et al.
        Effect of intrinsic patterns of functional brain connectivity in moderating antidepressant treatment response in major depression.
        Am J Psychiatry. 2020; 177: 143-154
        • Davidson R.J.
        • Irwin W.
        • Anderle M.J.
        • Kalin N.H.
        The neural substrates of affective processing in depressed patients treated with venlafaxine.
        Am J Psychiatry. 2003; 160: 64-75
        • Chen C.H.
        • Ridler K.
        • Suckling J.
        • Williams S.
        • Fu C.H.Y.
        • Merlo-Pich E.
        • Bullmore E.
        Brain imaging correlates of depressive symptom severity and predictors of symptom improvement after antidepressant treatment.
        Biol Psychiatry. 2007; 62: 407-414
        • Canli T.
        • Cooney R.E.
        • Goldin P.
        • Shah M.
        • Sivers H.
        • Thomason M.E.
        • et al.
        Amygdala reactivity to emotional faces predicts improvement in major depression.
        Neuroreport. 2005; 16: 1267-1270
        • Greenberg T.
        • Fournier J.C.
        • Stiffler R.
        • Chase H.W.
        • Almeida J.R.
        • Aslam H.
        • et al.
        Reward related ventral striatal activity and differential response to sertraline versus placebo in depressed individuals.
        Mol Psychiatry. 2020; 25: 1526-1536
        • Cao H.
        • Schwarz E.
        Opportunities and challenges of machine learning approaches for biomarker signature identification in psychiatry.
        in: Baune B.T. Be B. Personalized Psychiatry. Academic Press, Amsterdam2019: 117-126
        • Kautzky A.
        • Lanzenberger R.
        • Kasper S.
        Big data guided interventions: Predicting treatment response.
        in: Passos I.C. Mwangi B. Kapczinski F. Personalized Psychiatry. Springer, Cham2019: 53-76
        • Nguyen K.P.
        • Chin Fatt C.
        • Treacher A.
        • Mellema C.
        • Trivedi M.H.
        • Montillo A.
        Predicting response to the antidepressant bupropion using pretreatment fMRI.
        Predict Intell Med. 2019; 11843: 53-62
        • Trivedi M.H.
        • McGrath P.J.
        • Fava M.
        • Parsey R.V.
        • Kurian B.T.
        • Phillips M.L.
        • et al.
        Establishing moderators and biosignatures of antidepressant response in clinical care (EMBARC): Rationale and design.
        J Psychiatr Res. 2016; 78: 11-23
        • Greenberg T.
        • Chase H.W.
        • Almeida J.R.
        • Stiffler R.
        • Zevallos C.R.
        • Aslam H.A.
        • et al.
        Moderation of the relationship between reward expectancy and prediction error-related ventral striatal reactivity by anhedonia in unmedicated major depressive disorder: Findings from the EMBARC study.
        Am J Psychiatry. 2015; 172: 881-891
        • Delgado M.R.
        • Nystrom L.E.
        • Fissell C.
        • Noll D.C.
        • Fiez J.A.
        Tracking the hemodynamic responses to reward and punishment in the striatum.
        J Neurophysiol. 2000; 84: 3072-3077
        • Shorten C.
        • Khoshgoftaar T.M.
        A survey on image data augmentation for deep learning.
        J Big Data. 2019; 6: 60
        • Nguyen K.P.
        • Chin Fatt C.
        • Treacher A.
        • Mellema C.
        • Trivedi M.H.
        • Montillo A.
        Anatomically-informed data augmentation for functional MRI with applications to deep learning.
        Proc SPIE Int Soc Opt Eng. 2020; 11313: 113130T
        • Nguyen K.P.
        • Raval V.
        • Minhajuddin A.
        • Carmody T.
        • Trivedi M.H.
        • Dewey R.B.
        • et al.
        The BLENDS method for data augmentation of 4-dimensional brain images.
        bioRxiv. 2021;
        • Varma S.
        • Simon R.
        Bias in error estimation when using cross-validation for model selection.
        BMC Bioinformatics. 2006; 7: 91
        • Vabalas A.
        • Gowen E.
        • Poliakoff E.
        • Casson A.J.
        Machine learning algorithm validation with a limited sample size.
        PLoS One. 2019; 14e0224365
        • Ojala M.
        • Garriga G.C.
        Permutation tests for studying classifier performance.
        J Mach Learn Res. 2010; 11: 1833-1863
        • Dimopoulos Y.
        • Bourret P.
        • Lek S.
        Use of some sensitivity criteria for choosing networks with good generalization ability.
        Neural Process Lett. 1995; 2: 1-4
        • Olden J.D.
        • Joy M.K.
        • Death R.G.
        An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data.
        Ecol Modell. 2004; 178: 389-397
        • Roose S.P.
        • Rutherford B.R.
        • Wall M.M.
        • Thase M.E.
        Practising evidence-based medicine in an era of high placebo response: Number needed to treat reconsidered.
        Br J Psychiatry. 2016; 208: 416-420
        • Etkin A.
        • Patenaude B.
        • Song Y.J.C.
        • Usherwood T.
        • Rekshan W.
        • Schatzberg A.F.
        • et al.
        A cognitive-emotional biomarker for predicting remission with antidepressant medications: A report from the iSPOT-D trial.
        Neuropsychopharmacology. 2015; 40: 1332-1342
        • Gordon E.
        • Rush A.J.
        • Palmer D.M.
        • Braund T.A.
        • Rekshan W.
        Toward an online cognitive and emotional battery to predict treatment remission in depression.
        Neuropsychiatr Dis Treat. 2015; 11: 517-531
        • Dunlop B.W.
        • Rajendra J.K.
        • Craighead W.E.
        • Kelley M.E.
        • McGrath C.L.
        • Choi K.S.
        • et al.
        Functional connectivity of the subcallosal cingulate cortex and differential outcomes to treatment with cognitive-behavioral therapy or antidepressant medication for major depressive disorder.
        Am J Psychiatry. 2017; 174: 533-545
        • Fonzo G.A.
        • Etkin A.
        • Zhang Y.
        • Wu W.
        • Cooper C.
        • Chin-Fatt C.
        • et al.
        Brain regulation of emotional conflict predicts antidepressant treatment response for depression.
        Nat Hum Behav. 2019; 3: 1319-1331
        • Wu W.
        • Zhang Y.
        • Jiang J.
        • Lucas M.V.
        • Fonzo G.A.
        • Rolle C.E.
        • et al.
        An electroencephalographic signature predicts antidepressant response in major depression.
        Nat Biotechnol. 2020; 38: 439-447
        • Pizzagalli D.A.
        • Webb C.A.
        • Dillon D.G.
        • Tenke C.E.
        • Kayser J.
        • Goer F.
        • et al.
        Pretreatment rostral anterior cingulate cortex theta activity in relation to symptom improvement in depression: A randomized clinical trial.
        JAMA Psychiatry. 2018; 75: 547-554
        • Phillips M.L.
        • Chase H.W.
        • Sheline Y.I.
        • Etkin A.
        • Almeida J.R.C.
        • Deckersbach T.
        • Trivedi M.H.
        Identifying predictors, moderators, and mediators of antidepressant response in major depressive disorder: Neuroimaging approaches.
        Am J Psychiatry. 2015; 172: 124-138
        • Forbes E.E.
        • Christopher May J.
        • Siegle G.J.
        • Ladouceur C.D.
        • Ryan N.D.
        • Carter C.S.
        • et al.
        Reward-related decision-making in pediatric major depressive disorder: An fMRI study.
        J Child Psychol Psychiatry. 2006; 47: 1031-1040
        • Forbes E.E.
        • Olino T.M.
        • Ryan N.D.
        • Birmaher B.
        • Axelson D.
        • Moyles D.L.
        • Dahl R.E.
        Reward-related brain function as a predictor of treatment response in adolescents with major depressive disorder.
        Cogn Affect Behav Neurosci. 2010; 10: 107-118
        • Lener M.S.
        • Iosifescu D.V.
        In pursuit of neuroimaging biomarkers to guide treatment selection in major depressive disorder: A review of the literature.
        Ann N Y Acad Sci. 2015; 1344: 50-65
        • Doya K.
        Complementary roles of basal ganglia and cerebellum in learning and motor control.
        Curr Opin Neurobiol. 2000; 10: 732-739
        • Tanaka S.C.
        • Doya K.
        • Okada G.
        • Ueda K.
        • Okamoto Y.
        • Yamawaki S.
        Prediction of immediate and future rewards differentially recruits cortico-basal ganglia loops.
        Nat Neurosci. 2004; 7: 887-893
        • Tepfer L.J.
        • Alloy L.B.
        • Smith D.V.
        Family history of depression is associated with alterations in task-dependent connectivity between the cerebellum and ventromedial prefrontal cortex.
        Depress Anxiety. 2021; 38: 508-520
        • Cheng W.
        • Rolls E.T.
        • Qiu J.
        • Yang D.
        • Ruan H.
        • Wei D.
        • et al.
        Functional connectivity of the precuneus in unmedicated patients with depression.
        Biol Psychiatry Cogn Neurosci Neuroimaging. 2018; 3: 1040-1049
        • Rolls E.T.
        • Cheng W.
        • Du J.
        • Wei D.
        • Qiu J.
        • Dai D.
        • et al.
        Functional connectivity of the right inferior frontal gyrus and orbitofrontal cortex in depression.
        Soc Cogn Affect Neurosci. 2020; 15: 75-86
        • Gabbay V.
        • Ely B.A.
        • Li Q.
        • Bangaru S.D.
        • Panzer A.M.
        • Alonso C.M.
        • et al.
        Striatum-based circuitry of adolescent depression and anhedonia.
        J Am Acad Child Adolesc Psychiatry. 2013; 52: 628-641.e13
        • Campbell S.
        • MacQueen G.
        The role of the hippocampus in the pathophysiology of major depression.
        J Psychiatry Neurosci. 2004; 29: 417-426
        • Sapolsky R.M.
        Depression, antidepressants, and the shrinking hippocampus.
        Proc Natl Acad Sci U S A. 2001; 98: 12320-12322
        • Robertson B.
        • Wang L.
        • Diaz M.T.
        • Aiello M.
        • Gersing K.
        • Beyer J.
        • et al.
        Effect of bupropion extended release on negative emotion processing in major depressive disorder: A pilot functional magnetic resonance imaging study.
        J Clin Psychiatry. 2007; 68: 261-267

      Linked Article

      • Advancing Psychiatric Biomarker Discovery Through Multimodal Machine Learning
        Biological PsychiatryVol. 91Issue 6
        • Preview
          The fundamental promise of machine learning is that combinations of variables can do a better job in predicting a given outcome than the individual variables could do alone (1). There are few, if any, medical indications where this promise would be of higher relevance than in psychiatry. Almost unequivocally, biological research has shown that illness-associated changes are small in effect size and thus of limited use for biomarker applications that are based on single parameters (2). The clinical validity of biomarkers, however, hinges on their ability to accurately index illness- and treatment-relevant biological processes.
        • Full-Text
        • PDF

      CHORUS Manuscript

      View Open Manuscript