Author ORCID Identifier

Date of Award

Spring 3-29-2023

Document Type

Thesis (Ph.D.)

Department or Program

Quantitative Biomedical Sciences

First Advisor

Nicholas Jacobson


Major depressive disorder (MDD) is a debilitating disorder that impacts the lives of nearly 280 million individuals worldwide, representing 5% of the overall adult population. Unfortunately, these statistics have been both trending upward and are also likely an underestimate. This can be primarily attributed to lack of screening paired with a lack of providers. Worldwide, there are roughly 450 individuals living with MDD per mental health care provider. Adding to this burden, approximately half of affected individuals that do receive care of any kind will fail to remain in remission. The goal of this thesis work is to leverage statistical and machine learning models to help close these gaps in both MDD assessment and treatment. The data used in this thesis comes from a variety of sources including cross-sectional data from a physician wellness visit, randomized controlled trial (RCT) data from various digital interventions for MDD, and longitudinal data assessing individual’s depressive symptoms over time from the Tracking Depression Study. Supervised machine learning methods were applied to the wellness visit data to predict MDD presence and the RCT data to predict treatment response. The implication of these approaches is that in practice, they could enable passive assessments of MDD followed by personalized treatment planning using scalable interventions. As an addition to these machine learning approaches, statistical models were used to analyze longitudinal MDD symptom data to further understand individual changes in symptom dynamics. This work lays the foundation for dynamic treatment allocation that adapts as an individual’s experience changes.