Hostname: page-component-76fb5796d-zzh7m Total loading time: 0 Render date: 2024-04-29T20:14:06.876Z Has data issue: false hasContentIssue false
  • English
  • Français

Optimizing precision medicine for second-step depression treatment: a machine learning approach

Published online by Cambridge University Press:  27 March 2024

Joshua Curtiss Open the ORCID record for Joshua Curtiss [Opens in a new window] ,
Jordan W. Smoller  and
Paola Pedrelli
Joshua Curtiss*
Affiliation:
Depression Clinical and Research Program, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
Jordan W. Smoller
Affiliation:
Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
Paola Pedrelli
Affiliation:
Depression Clinical and Research Program, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA
*
Corresponding author: Joshua Curtiss; Email: jcurtiss@mgh.harvard.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

Background

Less than a third of patients with depression achieve successful remission with standard first-step antidepressant monotherapy. The process for determining appropriate second-step care is often based on clinical intuition and involves a protracted course of trial and error, resulting in substantial patient burden and unnecessary delay in the provision of optimal treatment. To address this problem, we adopt an ensemble machine learning approach to improve prediction accuracy of remission in response to second-step treatments.

Method

Data were derived from the Level 2 stage of the STAR*D dataset, which included 1439 patients who were randomized into one of seven different second-step treatment strategies after failing to achieve remission during first-step antidepressant treatment. Ensemble machine learning models, comprising several individual algorithms, were evaluated using nested cross-validation on 155 predictor variables including clinical and demographic measures.

Results

The ensemble machine learning algorithms exhibited differential classification performance in predicting remission status across the seven second-step treatments. For the full set of predictors, AUC values ranged from 0.51 to 0.82 depending on the second-step treatment type. Predicting remission was most successful for cognitive therapy (AUC = 0.82) and least successful for other medication and combined treatment options (AUCs = 0.51–0.66).

Conclusion

Ensemble machine learning has potential to predict second-step treatment. In this study, predictive performance varied by type of treatment, with greater accuracy in predicting remission in response to behavioral treatments than to pharmacotherapy interventions. Future directions include considering more informative predictor modalities to enhance prediction of second-step treatment response.

Keywords

depressionmachine learningprecision medicine
Type
Original Article
Information
Psychological Medicine , First View , pp. 1 - 8
Check for updates
Copyright
Copyright © The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bennabi, D., Charpeaud, T., Yrondi, A., Genty, J. B., Destouches, S., Lancrenon, S., … Dorey, J. M. (2019). Clinical guidelines for the management of treatment-resistant depression: French recommendations from experts, the French Association for Biological Psychiatry and Neuropsychopharmacology and the foundation FondaMental. BMC Psychiatry, 19(1), 1–12.Google ScholarPubMed
Bernardini, F., Attademo, L., Cleary, S. D., Luther, C., Shim, R., Quartesan, R., & Compton, M. T. (2017). Risk prediction models in psychiatry: Toward a new frontier for the prevention of mental illnesses. Journal of Clinical Psychiatry, 78, 572–583.CrossRefGoogle Scholar
Boehmke, B., & Greenwell, B. M. (2019). Hands-on machine learning with R. New York: CRC Press.CrossRefGoogle Scholar
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.CrossRefGoogle Scholar
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., … Corlett, P. R. (2016). Cross-trial prediction of treatment outcome in depression: A machine learning approach. The Lancet Psychiatry, 3(3), 243–250.CrossRefGoogle ScholarPubMed
Cusin, C., & Peyda, S. (2019). Treatment-Resistant depression. In Shapero, B. G., Mischoulon, D., & Cusin, C. (Eds.), The Massachusetts general hospital guide to depression: New treatment insights and options (pp. 3–19). Cham: Springer International Publishing.CrossRefGoogle Scholar
Endicott, J., Nee, J., Harrison, W., & Blumenthal, R. (1993). Quality of life enjoyment and satisfaction questionnaire: A new measure. Psychopharmacology Bulletin, 29(2), 321–326.Google ScholarPubMed
Flygare, O., Enander, J., Andersson, E., Ljótsson, B., Ivanov, V. Z., Mataix-Cols, D., & Rück, C. (2020). Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: A machine learning approach. BMC Psychiatry, 20, 1–9.CrossRefGoogle ScholarPubMed
Gelenberg, A. J., Freeman, M. P., Markowitz, J. C., Rosenbaum, J. F., Thase, M. E., Trivedi, M. H., & Van Rhoads, R. S. (2010). American Psychiatric association practice guidelines for the treatment of patients with major depressive disorder. American Journal of Psychiatry, 167(Suppl 10), 9–118.Google Scholar
Hamilton, M. (1960). The hamilton depression scale – accelerator or break on antidepressant drug discovery. Psychiatry, 23, 56–62.Google Scholar
Hughes, M. C., Pradier, M. F., Ross, A. S., McCoy, T. H., Perlis, R. H., & Doshi-Velez, F. (2020). Assessment of a prediction model for antidepressant treatment stability using supervised topic models. JAMA Network Open, 3(5), e205308–e205308.CrossRefGoogle ScholarPubMed
Kazdin, A. E., & Blase, S. L. (2011). Rebooting psychotherapy research and practice to reduce the burden of mental illness. Perspectives on Psychological Science, 6(1), 21–37.CrossRefGoogle ScholarPubMed
Kessler, R. C. (2018). The potential of predictive analytics to provide clinical decision support in depression treatment planning. Current Opinion in Psychiatry, 31(1), 32–39.CrossRefGoogle ScholarPubMed
Kuhn, M. (2022). caret: Classification and regression training (R package version 6.0-93) [Computer software]. The Comprehensive R Archive Network. Available from https://CRAN.Rproject.org/package=caretGoogle Scholar
Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. New York: Springer.CrossRefGoogle Scholar
Kuhn, M., & Johnson, K. (2019). Feature engineering and selection: A practical approach for predictive models. New York: CRC Press.CrossRefGoogle Scholar
Lage, I., McCoy, T. H. Jr, Perlis, R. H., & Doshi-Velez, F. (2022). Efficiently identifying individuals at high risk for treatment resistance in major depressive disorder using electronic health records. Journal of Affective Disorders, 306, 254–259.CrossRefGoogle ScholarPubMed
Lee, Y., Ragguett, R. M., Mansur, R. B., Boutilier, J. J., Rosenblat, J. D., Trevizol, A., … McIntyre, R. S. (2018). Applications of machine learning algorithms to predict therapeutic outcomes in depression: A meta-analysis and systematic review. Journal of Affective Disorders, 241, 519–532.CrossRefGoogle ScholarPubMed
Lewis, M., Spiliopoulou, A., & Goldmann, K. (2022). nestedcv: Nested cross-validation with ‘glmnet’ and ‘caret’ (R package version 0.3.6) [Computer software]. The Comprehensive R Archive Network. Available from https://github.com/myles-lewis/nestedcvGoogle Scholar
Mehltretter, J., Fratila, R., Benrimoh, D. A., Kapelner, A., Perlman, K., Snook, E., … Turecki, G. (2020). Differential treatment benefit prediction for treatment selection in depression: A deep learning analysis of STAR*D and CO-MED data. Computational Psychiatry, 4, 61–75.CrossRefGoogle Scholar
Mundt, J. C., Marks, I. M., Shear, M. K., & Greist, J. M. (2002). The work and social adjustment scale: A simple measure of impairment in functioning. The British Journal of Psychiatry, 180(5), 461–464.CrossRefGoogle Scholar
Nie, Z., Vairavan, S., Narayan, V. A., Ye, J., & Li, Q. S. (2018). Predictive modeling of treatment resistant depression using data from STAR* D and an independent clinical study. PloS One, 13, e0197268.CrossRefGoogle Scholar
Olfson, M., Blanco, C., & Marcus, S. C. (2016). Treatment of adult depression in the United States. JAMA Internal Medicine, 176(10), 1482–1491.CrossRefGoogle ScholarPubMed
Papakostas, G. I., & Fava, M. (2008). Predictors, moderators, and mediators (correlates) of treatment outcome in major depressive disorder. Dialogues in Clinical Neuroscience, 10(4), 439–451.CrossRefGoogle ScholarPubMed
Perlman, K., Benrimoh, D., Israel, S., Rollins, C., Brown, E., Tunteng, J. F., … Berlim, M. T. (2019). A systematic meta-review of predictors of antidepressant treatment outcome in major depressive disorder. Journal of Affective Disorders, 243, 503–515.CrossRefGoogle ScholarPubMed
Polley, E., LeDell, E., Kennedy, C., & Laan, M. V. D. (2021). SuperLearner: Super learner prediction (R package version 2.0-28) [Computer software]. The Comprehensive R Archive Network. Available from https://CRAN.R-project.org/package=SuperLearnerGoogle Scholar
Pradier, M. F., McCoy, T. H. Jr, Hughes, M., Perlis, R. H., & Doshi-Velez, F. (2020). Predicting treatment dropout after antidepressant initiation. Translational Psychiatry, 10(1), 60.CrossRefGoogle ScholarPubMed
Reilly, M. C., Zbrozek, A. S., & Dukes, E. M. (1993). The validity and reproducibility of a work productivity and activity impairment instrument. Pharmacoeconomics, 4(5), 353–365.CrossRefGoogle ScholarPubMed
Rush, A. J., Trivedi, M. H., Ibrahim, H. M., Carmody, T. J., Arnow, B., Klein, D. N., … Thase, M. E. (2003). The 16-item Quick Inventory of Depressive Symptomatology (QIDS), clinician rating (QIDS-C), and self-report (QIDS-SR): A psychometric evaluation in patients with chronic major depression. Biological psychiatry, 54(5), 573–583.CrossRefGoogle ScholarPubMed
Sheu, Y. H., Magdamo, C., Miller, M., Das, S., Blacker, D., & Smoller, J. W. (2023). AI-assisted prediction of differential response to antidepressant classes using electronic health records. NPJ Digital Medicine, 6(1), 73.CrossRefGoogle ScholarPubMed
Spielmans, G. I., & Flückiger, C. (2018). Moderators in psychotherapy meta-analysis. Psychotherapy Research: Journal of the Society for Psychotherapy Research, 28(3), 333–346.CrossRefGoogle ScholarPubMed
Trivedi, M. H., Rush, A. J., Wisniewski, S. R., Nierenberg, A. A., Warden, D., Ritz, L., … Star* D Study Team. (2006). Evaluation of outcomes with citalopram for depression using measurement-based care in STAR* D: Implications for clinical practice. American Journal of Psychiatry, 163(1), 28–40.CrossRefGoogle Scholar
Van der Laan, M. J., Polley, E. C., & Hubbard, A. E. (2007). Super learner. Statistical Applications in Genetics and Molecular Biology, 6(1), 25.CrossRefGoogle ScholarPubMed
Van der Laan, M. J., & Rose, S. (2011). Targeted learning: Causal inference for observational and experimental data (Vol. 10, pp. 978–971). New York: Springer.CrossRefGoogle Scholar
Ware, J. E., Kosinski, M., & Keller, S. D. (1996). A 12-item short-form health survey: Construction of scales and preliminary tests of reliability and validity. Medical Care, 34(3), 220–233.CrossRefGoogle ScholarPubMed
Zimmerman, M., & Mattia, J. I. (2001). A self-report scale to help make psychiatric diagnoses: The psychiatric diagnostic screening questionnaire. Archives of General Psychiatry, 58(8), 787–794.CrossRefGoogle ScholarPubMed
Supplementary material: File

Curtiss et al. supplementary material

Curtiss et al. supplementary material
Download Curtiss et al. supplementary material(File)
File 15.1 KB