Use of Administrative Data to Identify Health Plan Members With Unrecognized Bipolar Disorder: A Retrospective Cohort Study

OBJECTIVE: This retrospective cohort study used an algorithmic case-finding system on claims data from nationwide commercial health plans to validate previously identified predictors of unrecognized bipolar disorder among adults. STUDY DESIGN: Retrospective cohort design. METHODS: Using logistic regression, 2 claims data sets were evaluated to explore potential predictors; the first included claims for all healthcare encounters (all-encounters data set); the second excluded mental health provider claims (carve-out data set). A total of 280,244 members aged 18 to 64 years were included from 2 commercial health plans. RESULTS: Claims related to attention deficit-hyperactivity disorder, depression, depression treated with antipsychotics, use of 3 (of 5) classes of psychotherapeutic drugs, younger age, and sex were all significant predictors of a subsequent diagnosis of bipolar disorder. In the all-encounters data set, a predicted value of 5% or greater yielded a sensitivity of 9.8% and a specificity of 99.9%; a predicted threshold of 3% increased sensitivity to 20.7%; area under the receiver operating characteristic curve (AUC) was 0.82. Performance of the model was acceptable in the carve-out data set, with AUC 0.69. CONCLUSIONS: The case-finding system described here, which compares favorably with other screening tests used in primary care, may have significant value in helping physicians to identify patients with unrecognized bipolar disorder.