Advertisement

Predicting Response to the Antidepressant Bupropion Using Pretreatment fMRI

  • Kevin P. NguyenEmail author
  • Cherise Chin Fatt
  • Alex Treacher
  • Cooper Mellema
  • Madhukar H. Trivedi
  • Albert Montillo
Conference paper
  • 396 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11843)

Abstract

Major depressive disorder is a primary cause of disability in adults with a lifetime prevalence of 6–21% worldwide. While medical treatment may provide symptomatic relief, response to any given antidepressant is unpredictable and patient-specific. The standard of care requires a patient to sequentially test different antidepressants for 3 months each until an optimal treatment has been identified. For 30–40% of patients, no effective treatment is found after more than one year of this trial-and-error process, during which a patient may suffer loss of employment or marriage, undertreated symptoms, and suicidal ideation. This work develops a predictive model that may be used to expedite the treatment selection process by identifying for individual patients whether the patient will respond favorably to bupropion, a widely prescribed antidepressant, using only pretreatment imaging data. This is the first model to do so for individuals for bupropion. Specifically, a deep learning predictor is trained to estimate the 8-week change in Hamilton Rating Scale for Depression (HAMD) score from pretreatment task-based functional magnetic resonance imaging (fMRI) obtained in a randomized controlled antidepressant trial. An unbiased neural architecture search is conducted over 800 distinct model architecture and brain parcellation combinations, and patterns of model hyperparameters yielding the highest prediction accuracy are revealed. The winning model identifies bupropion-treated subjects who will experience remission with the number of subjects needed-to-treat (NNT) to lower morbidity of only 3.2 subjects. It attains a substantially high neuroimaging study effect size explaining 26% of the variance (\(R^2 = 0.26\)) and the model predicts post-treatment change in the 52-point HAMD score with an RMSE of 4.71. These results support the continued development of fMRI and deep learning-based predictors of response for additional depression treatments.

Keywords

Depression Treatment response fMRI Neuroimaging Deep learning Neural architecture search 

References

  1. 1.
    Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. M. L. Res. 13, 281–305 (2012)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Calhoun, V.D., et al.: The impact of T1 versus epi spatial normalization templates for fMRI data analyses. Hum. Brain Mapp. 38, 5331–5342 (2017).  https://doi.org/10.1002/hbm.23737CrossRefGoogle Scholar
  3. 3.
    Chan, M.Y., et al.: Socioeconomic status moderates age-related differences in the brain’s functional network organization and anatomy across the adult lifespan. PNAS 115, E5144–E5153 (2018).  https://doi.org/10.1073/pnas.1714021115CrossRefGoogle Scholar
  4. 4.
    Chau, D.T., et al.: The neural circuitry of reward and its relevance to psychiatric disorders. Curr. Psych. Rep. 6(5), 391–399 (2004).  https://doi.org/10.1007/s11920-004-0026-8CrossRefGoogle Scholar
  5. 5.
    Craddock, R.C., et al.: A whole brain fMRI atlas generated via spatially constrained spectral clustering. Hum. Brain Mapp. 33(8), 1914–1928 (2012).  https://doi.org/10.1002/hbm.21333CrossRefGoogle Scholar
  6. 6.
    Dohmatob, E., et al.: Inter-subject registration of functional images: do we need anatomical images? Front. Neurosci. 12, 64 (2018).  https://doi.org/10.3389/fnins.2018.00064CrossRefGoogle Scholar
  7. 7.
    Dupuy, J.M., et al.: A critical review of pharmacotherapy for major depressive disorder. Int. J. Neuropsychopharmacol. 14(10), 1417–1431 (2011).  https://doi.org/10.1017/S1461145711000083CrossRefGoogle Scholar
  8. 8.
    Etkin, A., et al.: Resolving emotional conflict: a role for the rostral anterior cingulate cortex in modulating activity in the amygdala. Neuron 51(6), 871–882 (2006).  https://doi.org/10.1016/j.neuron.2006.07.029CrossRefGoogle Scholar
  9. 9.
    Etkin, A., et al.: A cognitive-emotional biomarker for predicting remission with antidepressant medications: a report from the iSPOT-D trial. Neuropsychopharmacol. Off. Publ. Am. Coll. Neuropsychopharmacol. 40(6), 1332–1342 (2015).  https://doi.org/10.1038/npp.2014.333CrossRefGoogle Scholar
  10. 10.
    Gordon, E., et al.: Toward an online cognitive and emotional battery to predict treatment remission in depression. Neuropsychiatr. Dis. Treat. 11, 517–531 (2015).  https://doi.org/10.2147/NDT.S75975CrossRefGoogle Scholar
  11. 11.
    Greenberg, P.E., et al.: The economic burden of adults with major depressive disorder in the United States (2005 and 2010). J. Clin. Psych. 76(2), 155–162 (2015).  https://doi.org/10.4088/JCP.14m09298CrossRefGoogle Scholar
  12. 12.
    Kessler, R.C., Bromet, E.J.: The epidemiology of depression across cultures. Ann. Rev. Public Health 34, 119–138 (2013).  https://doi.org/10.1146/annurev-publhealth-031912-114409CrossRefGoogle Scholar
  13. 13.
    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. NYAS 1344, 50–65 (2015).  https://doi.org/10.1111/nyas.12759CrossRefGoogle Scholar
  14. 14.
    Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search (2019). arXiv:1902.07638
  15. 15.
    Patel, K., et al.: Bupropion: a systematic review and meta-analysis of effectiveness as an antidepressant. Ther. Adv. Psychopharm. 6, 99–144 (2016).  https://doi.org/10.1177/2045125316629071CrossRefGoogle Scholar
  16. 16.
    Phillips, M.L., et al.: Identifying predictors, moderators, and mediators of antidepressant response in major depressive disorder: neuroimaging approaches. AJP 172(2), 124–138 (2015).  https://doi.org/10.1176/appi.ajp.2014.14010076CrossRefGoogle Scholar
  17. 17.
    Pizzagalli, D.A.: Frontocingulate dysfunction in depression: toward biomarkers of treatment response. Neuropsychopharmacology 36(1), 183–206 (2011).  https://doi.org/10.1038/npp.2010.166CrossRefGoogle Scholar
  18. 18.
    Roose, S.P., et al.: Practising evidence-based medicine in an era of high placebo response: number needed to treat reconsidered. Brit. J. Psych. 208(5), 416–420 (2016).  https://doi.org/10.1192/bjp.bp.115.163261CrossRefGoogle Scholar
  19. 19.
    Rush, A.J., et al.: Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: a STAR* D report. AJP 163(11), 1905–1917 (2006).  https://doi.org/10.1176/ajp.2006.163.11.1905CrossRefGoogle Scholar
  20. 20.
    Schaefer, A., et al.: Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity MRI. Cereb. Cortex 28(9), 3095–3114 (2018).  https://doi.org/10.1093/cercor/bhx179CrossRefGoogle Scholar
  21. 21.
    Somerville, L.H., et al.: Interactions between transient and sustained neural signals support the generation and regulation of anxious emotion. Cereb. Cortex 23, 49–60 (2012).  https://doi.org/10.1093/cercor/bhr373CrossRefGoogle Scholar
  22. 22.
    Trivedi, M.H., et al.: Evaluation of outcomes with citalopram for depression using measurement-based care in STAR* D: implications for clinical practice. AJP 163(1), 28–40 (2006).  https://doi.org/10.1176/appi.ajp.163.1.28CrossRefGoogle Scholar
  23. 23.
    Trivedi, M.H., et al.: Establishing moderators and biosignatures of antidepressant response in clinical care (EMBARC): rationale and design. J. Psych. Res. 78, 11–23 (2016).  https://doi.org/10.1016/j.jpsychires.2016.03.001CrossRefGoogle Scholar
  24. 24.
    Varma, S., Simon, R.: Bias in error estimation when using cross-validation for model selection. BMC Bioinform. 7, 91–99 (2006).  https://doi.org/10.1186/1471-2105-7-91CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kevin P. Nguyen
    • 1
    Email author
  • Cherise Chin Fatt
    • 1
  • Alex Treacher
    • 1
  • Cooper Mellema
    • 1
  • Madhukar H. Trivedi
    • 1
  • Albert Montillo
    • 1
  1. 1.University of Texas Southwestern Medical CenterDallasUSA

Personalised recommendations