Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation


We aimed to develop and validate classification models able to identify individuals at high risk for transition from a diagnosis of depressive disorder to one of bipolar disorder. This retrospective health records cohort study applied outpatient clinical data from psychiatry and nonpsychiatry practice networks affiliated with two large academic medical centers between March 2008 and December 2017. Participants included 67,807 individuals with a diagnosis of major depressive disorder or depressive disorder not otherwise specified and no prior diagnosis of bipolar disorder, who received at least one of the nine antidepressant medications. The main outcome was at least one diagnostic code reflective of a bipolar disorder diagnosis within 3 months of index antidepressant prescription. Logistic regression and random forests using diagnostic and procedure codes as well as sociodemographic features were used to predict this outcome, with discrimination and calibration assessed in a held-out test set and then a second academic medical center. Among 67,807 individuals who received at least one antidepressant medication, 925 (1.36%) subsequently received a diagnosis of bipolar disorder within 3 months. Models incorporating coded diagnoses and procedures yielded a mean area under the receiver operating characteristic curve of 0.76 (ranging from 0.73 to 0.80). Standard supervised machine learning methods enabled development of discriminative and transferable models to predict transition to bipolar disorder. With further validation, these scores may enable physicians to more precisely calibrate follow-up intensity for high-risk patients after antidepressant initiation.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Bipolar rates among all index prescriptions between 2008 and 2017 for different antidepressant categories.
Fig. 2: Area under the curve (AUC) in test set for the logistic regression classifier (left) and random forest classifier (right) for Site a and Site b.
Fig. 3: Lift histogram for the random forest classifier (1st row) and logistic regression classifier (2nd row) in Site a (1st column) and Site b (2nd column) for a single split.
Fig. 4: Positive predictive values (PPV) versus negative predictive values (NPV) for the random forest classifier (1st row) and logistic regression classifier (2nd row) in Site a (1st column) and Site b (2nd column) for a single split.


  1. 1.

    Smith DJ, Griffiths E, Kelly M, Hood K, Craddock N, Simpson SA. Unrecognised bipolar disorder in primary care patients with depression. Br J Psychiatry. 2011;199:49–56.

    Article  Google Scholar 

  2. 2.

    Dagani J, Signorini G, Nielssen O, Bani M, Pastore A, Girolamo Gde, et al. Meta-analysis of the Interval between the Onset and Management of Bipolar Disorder. Can J Psychiatry. 2017;62:247–58.

    Article  Google Scholar 

  3. 3.

    Hirschfeld RMA, Lewis L, Vornik LA. Perceptions and impact of bipolar disorder: how far have we really come? Results of the national depressive and manic-depressive association 2000 survey of individuals with bipolar disorder. J Clin Psychiatry. 2003;64:161–74.

    Article  Google Scholar 

  4. 4.

    Pacchiarotti I, Bond DJ, Baldessarini RJ, Nolen WA, Grunze H, Licht RW, et al. The International Society for Bipolar Disorders (ISBD) task force report on antidepressant use in bipolar disorders. Am J Psychiatry. 2013;170:1249–62.

    Article  Google Scholar 

  5. 5.

    Rihmer Z, Gonda X. Antidepressant-resistant depression and antidepressant-associated suicidal behaviour: the role of underlying bipolarity. Depress Res Treat. 2011;2011:906462.

    PubMed  PubMed Central  Google Scholar 

  6. 6.

    Hartmann JA, Nelson B, Ratheesh A, Treen D, McGorry PD. At-risk studies and clinical antecedents of psychosis, bipolar disorder and depression: a scoping review in the context of clinical staging. Psychol Med. 2019;49:177–89.

    Article  Google Scholar 

  7. 7.

    Ratheesh A, Davey C, Hetrick S, Alvarez-Jimenez M, Voutier C, Bechdolf A, et al. A systematic review and meta-analysis of prospective transition from major depression to bipolar disorder. Acta Psychiatr Scand. 2017;135:273–84.

    CAS  Article  Google Scholar 

  8. 8.

    Serra G, Koukopoulos A, De Chiara L, Napoletano F, Koukopoulos AE, Curto M, et al. Features preceding diagnosis of bipolar versus major depressive disorders. J Affect Disord. 2015;173:134–42.

    Article  Google Scholar 

  9. 9.

    Tondo L, Visioli C, Preti A, Baldessarini RJ. Bipolar disorders following initial depression: modeling predictive clinical factors. J Affect Disord. 2014;167:44–49.

    Article  Google Scholar 

  10. 10.

    Perlis RH, Uher R, Ostacher M, Goldberg JF, Trivedi MH, Rush AJ, et al. Association between bipolar spectrum features and treatment outcomes in outpatients with major depressive disorder. Arch Gen Psychiatry. 2011;68:351–60.

    Article  Google Scholar 

  11. 11.

    Kessing LV, Willer I, Andersen PK, Bukh JD. Rate and predictors of conversion from unipolar to bipolar disorder: a systematic review and meta-analysis. Bipolar Disord. 2017;19:324–35.

    Article  Google Scholar 

  12. 12.

    Bernardini F, Attademo L, Cleary SD, Luther C, Shim RS, Quartesan R, et al. Risk prediction models in psychiatry: toward a new frontier for the prevention of mental illnesses. J Clin Psychiatry. 2017;78:572–83.

    Article  Google Scholar 

  13. 13.

    Murphy SN, Mendis M, Hackett K, Kuttan R, Pan W, Phillips LC, et al. Architecture of the open-source clinical research chart from informatics for integrating biology and the bedside. In AMIA Annual Symposium Proceedings. 2007. p. 548–52.

  14. 14.

    Pedregosa F, Veroquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–30.

    Google Scholar 

  15. 15.

    Musliner KL, Østergaard SD. Patterns and predictors of conversion to bipolar disorder in 91 587 individuals diagnosed with unipolar depression. Acta Psychiatr Scand. 2018;137:422–32.

    CAS  Article  Google Scholar 

  16. 16.

    Angst J, Sellaro R, Stassen HH, Gamma A. Diagnostic conversion from depression to bipolar disorders: results of a long-term prospective study of hospital admissions. J Affect Disord. 2005;84:149–57.

    Article  Google Scholar 

  17. 17.

    Tondo L, Vázquez G, Baldessarini RJ. Mania associated with antidepressant treatment: comprehensive meta-analytic review. Acta Psychiatr Scand. 2010;121:404–14.

    CAS  Article  Google Scholar 

  18. 18.

    Marangoni C, Faedda GL, Baldessarini RJ. Clinical and environmental risk factors for bipolar disorder: review of prospective studies. Harv Rev Psychiatry. 2018;26:1–7.

    Article  Google Scholar 

  19. 19.

    Fiedorowicz JG, Endicott J, Leon AC, Solomon DA, Keller MB, Coryell WH. Subthreshold hypomanic symptoms in progression from unipolar major depression to bipolar disorder. Am J Psychiatry. 2011;168:40–48.

    Article  Google Scholar 

  20. 20.

    Ratheesh A, Cotton SM, Betts JK, Chanen A, Nelson B, Davey CG, et al. Prospective progression from high-prevalence disorders to bipolar disorder: exploring characteristics of pre-illness stages. J Affect Disord. 2015;183:45–48.

    Article  Google Scholar 

  21. 21.

    Gilman SE, Dupuy JM, Perlis RH. Risks for the transition from major depressive disorder to bipolar disorder in the National Epidemiologic Survey on alcohol and related conditions. J Clin Psychiatry. 2012;73:829–36.

    Article  Google Scholar 

  22. 22.

    Angst J, Adolfsson R, Benazzi F, Gamma A, Hantouche E, Meyer T, et al. The HCL-32: towards a self-assessment tool for hypomanic symptoms in outpatients. J Affect Disord. 2005;88:217–33.

    Article  Google Scholar 

  23. 23.

    Regier DA, Narrow WE, Clarke DE, Kraemer HC, Kuramoto SJ, Kuhl EA, et al. DSM-5 field trials in the United States and Canada, Part II: test–retest reliability of selected categorical diagnoses. Am J Psychiatry. 2013;170:59–70.

    Article  Google Scholar 

  24. 24.

    Perlis R. Translating biomarkers to clinical practice. Mol Psychiatry. 2011;16:1076–87.

    CAS  Article  Google Scholar 

  25. 25.

    McCombs JS, Ahn J, Tencer T, Shi L. The impact of unrecognized bipolar disorders among patients treated for depression with antidepressants in the fee-for-services California Medicaid (Medi-Cal) program: a 6-year retrospective analysis. J Affect Disord. 2007;97:171–9.

    Article  Google Scholar 

Download references


The authors thank Victor Castro for assistance with dataset generation.

Author information




MFP: Analyzed data, interpreted results, and assisted in drafting manuscript. MH: Interpreted results and edited manuscript. THM: Interpreted results and edited manuscript. SAB: Assisted in drafting manuscript. FD-V: Oversaw analysis and edited manuscript. RHP: Conceived and drafted manuscript.

Corresponding authors

Correspondence to Finale Doshi-Velez or Roy H. Perlis.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Pradier, M.F., Hughes, M.C., McCoy, T.H. et al. Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation. Neuropsychopharmacol. 46, 455–461 (2021).

Download citation


Quick links