Depression is one of the most widespread and disabling mental health disorders affecting adults worldwide, and Black women bear a disproportionate burden of this disorder. With its varied symptom presentation, depression can be difficult to diagnose. In addition, Black women may be less likely to report symptoms due to cultural stigma.
The purpose of this dissertation is to examine the associations between social determinants of health and depressive symptoms using DNA methylation data and machine learning to predict depressive symptoms in Black women. Chapter 2 contains two comprehensive literature reviews: a scoping review of machine learning methods used to analyze omics data to classify depressed cases and healthy controls and a concept analysis of depression in Black mothers.
Chapter 3 examines associations between social determinants of health, depressive symptoms, and DNA methylation. Chapter 3A focuses on socioeconomic deprivation; Chapter 3B focuses on perceived income inadequacy; and Chapter 3C identifies differential methylation associated with depressive symptoms. Chapter 4 utilizes supervised machine learning algorithms to predict depressive symptoms and perform feature selection.
These chapters show the harmful effects that perceived discrimination can have on the mental health of Black women. Additionally, the results indicate that DNA methylation is associated with depressive symptoms, an area which requires further research.
| Identifer | oai:union.ndltd.org:columbia.edu/oai:academiccommons.columbia.edu:10.7916/srn1-rk76 |
| Date | January 2024 |
| Creators | Taylor, Brittany |
| Source Sets | Columbia University |
| Language | English |
| Detected Language | English |
| Type | Theses |
Page generated in 0.0014 seconds