OBJECTIVES:

The objective of this study was to identify which social determinants of health (SDoHs) are more impactful to the health outcomes of participants with major depressive disorder (MDD) versus participants without MDD.

METHODS:

In order to detect differences in how each SDoH impacts health outcomes, our team compared the results of statistical inference between MDD and non-MDD cohorts. The variables used for this process were comprised of demographic, socioeconomic, survey, and electronic health record data supplied by the All of Us database. The AoU database, consisting of this data plus whole genome and Fitbit data, is collected from participants across the United States with a focus of diversity and inclusion. With forward stepwise linear regression and principal component analysis, we were able to examine the importance of SDoH categories on health outcomes. Lasso regression was used to identify the individual survey questions that are important to these outcomes.

RESULTS:

A review of the forward stepwise regression results for our MDD models yielded notable differences in SDoH importance from our non-MDD models. The number of inpatient hospital visits for participants with MDD seemed to be more dependent upon features pertaining to neighborhood and built environment, such as infrastructure or cleanliness and safety of a neighborhood, whereas this outcome for non-MDD participants was more determined by healthcare quality and access.

Results from the lasso regression models found that the general quality of life for a participant with MDD was more greatly affected by negative emotional stimulus, fatigue, and lack of supportive relationships than that of non-MDD participants.

CONCLUSIONS:

This study was able to highlight key factors in determining participant health outcomes, which can be taken for further, more focused study with a policy perspective in mind.