The Benefits of a Complex Identification and Stratification Model for Depression: Insights from a Large Claims Analysis Study

OBJECTIVES: To investigate an analytics-enabled identification and stratification (IDS) framework for evaluating depression, and its severity, using health insurance claims data.

METHODS: This is a retrospective analysis of 2022 claims and electronic health record data from Highmark Health and affiliated insurers. Members aged 18+ with Highmark coverage and a healthcare encounter were included. The depression IDS framework used diagnosis codes, pharmacy claims, and Optum, Milliman, and John Hopkins analytics software data. Alignment of identification and stratification criteria was evaluated.

RESULTS: The IDS framework identified 762,753 members with depression (18.8% of the population). The identification rules revealed variability in prevalence, with 2% identified by PHQ-9 scores, 11% by diagnoses, 9% by treatment groups, and 11% by adjusted clinical groups. The framework identified 306,394 more members (7.6% of the population) compared to using diagnoses alone. The IDS rules escalated 46% of mild and 19% of moderate cases to higher severity compared to single parameter assessments. Expenses for severe depression were 159% higher than for minimal severity.

CONCLUSIONS: The analytics-enabled IDS framework demonstrates utility in identifying members with depression by linking fragmented data sources. Aligning multiple parameters provides a more nuanced severity evaluation compared to individual data elements. Enhanced phenotyping enables the targeting of cost-effective digital self-care tools to milder cases while reserving expensive interventions for the most severely ill, potentially reducing overall costs while maintaining health outcomes. Implementation of this integrative platform can help focus efforts on those with the highest need and bridge the gap in treating depression.