Application of Intersectionality Framework and Area-level Indicators in Machine Learning Analysis of Depression Disparities in All of Us Research Program Data

Background/objective: Depression is a complex mental health disorder influenced by various social determinants of health (SDOH) at individual and community levels. Area-level factors and the intersectionality framework, which considers overlapping personal identities, are used in this paper to get a nuanced picture of depression disparities. Methods This cross-sectional study uses electronic health records data from the All of Us research network. Our study cohort includes 36,868 individuals who completed the SDOH surveys in All of Us and had at least one inpatient visit, with 31.9% diagnosed with depression between 2020 and 2025. We used depression diagnosis as an outcome, while independent variables include US Religious Census and American Community Survey responses, area-level variables, sociodemographic characteristics: age group, income, gender, sexual orientation, immigration status, marital status, and race/ethnicity – and the interactions of the latter with each other and with other variables. The association between depression diagnosis and the variables is reported by fitting the logistic regression model on the subset of variables identified by the LASSO method. Results Key findings include reduced depression odds for non-heterosexual individuals living in less religious areas (OR 0.65, 95% CI 0.52–0.80), while high religious adherence in the area was protective for Hispanics (OR 0.24, 95% CI 0.14–0.40). Identity interaction effects revealed heightened risks, such as never-married MENA individuals (OR 2.83, 95% CI 1.38–5.77) and Hispanic active-duty members (OR 1.76, 95% CI 1.25–2.46). Food insecurity (OR 1.44, 95% CI 1.21–1.71) and discrimination (OR 1.43, 95% CI 1.26–1.62) also increased odds. Discussion/Conclusion: The findings underscore the importance of considering all types of factors: individual, area-level, and intersectional in depression research and public health interventions.