Selection Models to Improve Prediction of Response to Cognitive Behavior Therapy for Adolescent Depression (DSI-SRP)
This DSI-SRP fellowship funded Anh Dao to work in the laboratory of Professor Autumn Kujawain the Department of Psychology and Human Development during the summer of 2020. Anh graduated in May 2021 with majors in Psychology and Medicine, Health, and Society.
The project funded by this fellowship aimed to understand Cognitive behavioral therapy as an efficacious treatment for adolescent depression. One of the core features of depression is anhedonia, or the absence of pleasure and interest in potentially rewarding activities, which is often characterized by poor long-term outcomes and decreased response to treatment. Due to its association with anhedonia, low reward reactivity specifically appears to be implicated in depression and is a potential target for interventions. Currently, clinicians lack the ability to match individuals to the most effective treatments. Anh’s project aimed to improve depression treatment response predictions, with a focus on the reward positivity component (RewP) derived from the electroencephalograph (EEG). Enhanced reward responsiveness to monetary rewards predicted increased severity of depression post-treatment. Relative increases in reward responsiveness pre and post-treatment were correlated with decreases in symptoms of depression and anhedonia. Anh also expanded her research to examine the extent to which the interaction between stress and reward reactivity predicted symptoms of depression and anxiety in response to the COVID-19 pandemic. Reward responsiveness did not emerge as a significant predictor or moderator of the association between stress and the development of depression for the pandemic stress events. Due to the Mood, Emotion, and Development lab’s focus on both monetary and social reward reactivity, Anh was able to continue examining rewards responsiveness in her Honors project, and provide assistance in managing data from the same tasks across different populations. Because DSI-SRP offered workshops using both Python and R Studio Cloud, Anh was able to complete her summer project analyses in R Studio, and began to apply data science methods to parse and manage complex unstructured data files in Python following DSI-SRP. Lastly, the program’s workshops focusing on Github have allowed Anh to stay organized while working on different projects, find other useful analytical resources, and share her own work.
In addition to receiving support through a DSI-SRP fellowship, this project was supported and facilitated by the DSI Data Science Team through their regular summer workshops and demo sessions.