Vol. 16 No. 1 (2018)
Reflections

Deep Learning: A New Horizon for Personalized Treatment of Depression?

PDF
  • David Benrimoh,
  • Robert Fratila,
  • Sonia Israel,
  • Kelly Perlman
David Benrimoh
McGill University University College London
Bio
Robert Fratila
McGill University
Bio
Sonia Israel
McGill University
Bio
Kelly Perlman
McGill University
Bio
DOI: https://doi.org/10.26443/mjm.v16i1.99

Published 2018-07-06

Keywords

  • depression,
  • personalized medicine,
  • artificial intelligence

How to Cite

1.
Benrimoh D, Fratila R, Israel S, Perlman K. Deep Learning: A New Horizon for Personalized Treatment of Depression?. McGill J Med [Internet]. 2018 Jul. 6 [cited 2025 Oct. 6];16(1). Available from: https://mjm.mcgill.ca/article/view/99

Copyright (c) 2020 McGill Journal of Medicine

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC

Abstract

Globally, depression affects 300 million people and is projected be the leading cause of disability by 2030. While different patients are known to benefit from different therapies, there is no principled way for clinicians to predict individual patient responses or side effect profiles. A form of machine learning based on artificial neural networks, deep learning, might be useful for generating a predictive model that could aid in clinical decision making. Such a model’s primary outcomes would be to help clinicians select the most effective treatment plans and mitigate adverse side effects, allowing doctors to provide greater personalized care to a larger number of patients. In this commentary, we discuss the need for personalization of depression treatment and how a deep learning model might be used to construct a clinical decision aid.


PDF

Downloads

Download data is not yet available.

References

  1. Fushiki T. Estimation of prediction error by using K-fold cross-validation. Statistics and Computing. 2011;21(2):137-46.
  2. Greenberg PE, Fournier AA, Sisitsky T, Pike CT, Kessler RC. The economic burden of adults with major depressive disorder in the United States (2005 and 2010). The Journal of clinical psychiatry. 2015;76(2):155-62.
  3. Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. Journal of Machine Learning Research 11 (2010) 3371-3408
  4. Günter Klambauer TU, Andreas Mayr, Sepp Hochreiter. Self-Normalizing Neural Networks. arXiv. 2017.
  5. Haffner YLLBYBP. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998;86(11):2278-324.
  6. Hajian-Tilaki K. Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation. Caspian Journal of Internal Medicine. 2013;4(2):627-35.
  7. Karen Simonyan AV, Andrew Zisserman. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv. 2013.
  8. Kennedy SH, Lam RW, McIntyre RS, Tourjman SV, Bhat V, Blier P, et al. Canadian Network for Mood and Anxiety Treatments (CANMAT) 2016 Clinical Guidelines for the Management of Adults with Major Depressive Disorder: Section 3. Pharmacological Treatments. Can J Psychiatry. 2016;61(9):540-60.
  9. Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554.
  10. Bengio, Y., Courville, A., & Vincent, P. (2012). Representation Learning: A Review and New Perspectives. arXiv:1206.5538 [Cs]. Retrieved from
  11. http://arxiv.org/abs/1206.5538
  12. SABCS 2016: IBM Watson for Oncology Platform Shows High Degree of Concordance With Physician Recommendations - The ASCO Post. (n.d.). Retrieved November 16, 2017, from http://www.ascopost.com/News/44214
  13. Ferrari, A. J., Charlson, F. J., Norman, R. E., Patten, S. B.,
  14. Freedman, G., Murray, C. J. L., . . . Whiteford, H. A. (2013).
  15. Burden of Depressive Disorders by Country, Sex, Age, and
  16. Year: Findings from the Global Burden of Disease Study
  17. PLOS Medicine, 10(11), e1001547.
  18. doi:10.1371/journal.pmed.1001547
  19. Bromet, E., Andrade, L. H., Hwang, I., Sampson, N. A.,
  20. Alonso, J., de Girolamo, G., … Kessler, R. C. (2011).
  21. Cross-national epidemiology of DSM-IV major depressive
  22. episode. BMC Medicine, 9, 90.
  23. https://doi.org/10.1186/1741-7015-9-90
  24. Depression. (n.d.). Retrieved August 16, 2017, from
  25. http://www.who.int/mediacentre/factsheets/fs369/en/
  26. Kennedy, S. H., Lam, R. W., Parikh, S. V., MacQueen, G. M., Milev, R. V., Ravindran, A. V., & the, C. D.
  27. W. G. (2016). Canadian Network for Mood and Anxiety Treatments (CANMAT) 2016 Clinical Guidelines for
  28. the Management of Adults with Major Depressive Disorder: Introduction and Methods. Canadian Journal of
  29. Psychiatry. Revue Canadienne de Psychiatrie, 61(9), 506-509. doi:10.1177/0706743716659061
  30. Leuchter, A. F., Cook, I. A., Hunter, A. M., & Korb, A. S. (2009). A new paradigm for the prediction of
  31. antidepressant treatment response. Dialogues Clin Neurosci, 11(4), 435-446.
  32. Young, J. J., Silber, T., Bruno, D., Galatzer-Levy, I. R., Pomara, N., & Marmar, C. R. (2016). Is there
  33. Progress? An Overview of Selecting Biomarker Candidates for Major Depressive Disorder. Frontiers in
  34. Psychiatry, 7, 72. http://doi.org/10.3389/fpsyt.2016.00072
  35. Labermaier, C., Masana, M., & Müller, M. B. (2013). Biomarkers Predicting Antidepressant Treatment
  36. Response: How Can We Advance the Field? Disease markers, 35(1), 23-31. doi:10.1155/2013/984845
  37. Rush, A. J., Fava, M., Wisniewski, S. R., Lavori, P. W., Trivedi, M. H., Sackeim, H. A., . . . for the, S. D. I.
  38. G. (2004). Sequenced treatment alternatives to relieve depression (STAR*D): rationale and design. Controlled
  39. Clinical Trials, 25(1), 119-142. doi:10.1016/S0197-2456(03)00112-0
  40. Maaten, L., Hinton, G. (2008). Visualizing Data using t-SNE. JMLR 9(Nov):2579--2605.
  41. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural netoworks from overfitting. Journal of machine learning. 15(Jun):1929-1958