Application of Intersectionality Framework and Area-level Indicators in Machine Learning Analysis of Depression Disparities in All of Us Research Program Data
2024

Understanding Depression Disparities Using Intersectionality and Area-level Factors

Sample size: 20042 publication Evidence: moderate

Author Information

Author(s): Dmitry Scherbakov, Michael T. Marrone, Leslie A. Lenert, Alexander V. Alekseyenko

Primary Institution: Medical University of South Carolina

Hypothesis

How do area-level indicators and personal identities interact to influence depression outcomes?

Conclusion

The study found that both area-level factors and personal identities significantly affect depression outcomes.

Supporting Evidence

  • Area-level religious adherence was associated with increased depression odds for women.
  • Non-binary individuals showed significantly higher depression odds when area-level religious adherence was high.
  • Younger adults unemployed for less than a year had higher depression odds.

Takeaway

This study shows that where you live and who you are can affect how likely you are to feel sad or depressed.

Methodology

This cross-sectional study analyzed electronic health records data from the All of Us research network using logistic regression and LASSO variable selection.

Potential Biases

The study may not account for all potential biases due to the limited scope of variable interactions considered.

Limitations

Not all possible variable interactions were explored, and the initial design matrix was limited to a curated list of demographic and social variables.

Participant Demographics

The cohort included 20,042 individuals, with 27.3% diagnosed with depression since 2020.

Statistical Information

Confidence Interval

95% CI 1.15–1.54

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.21203/rs.3.rs-5536130

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication