Yama Chang (she/her) is a PhD student in the Quantitative Biomedical Sciences (QBS) program at Dartmouth College, mentored by Dr. Nicholas Jacobson in the Artificial Intelligence and Mental Health: Innovation in Technology Guided Healthcare Lab at the Center for Technology and Behavioral Health.
Her research focuses on leveraging passive sensing, wearable devices, large language models (LLMs), and just-in-time adaptive interventions (JITAIs) to deliver scalable, personalized support for mental wellness. As part of the Evergreen AI initiative at Dartmouth, Yama is conducting research on the design and evaluation of a real-time, campus-wide intervention system that integrates multimodal data streams with LLM-based decision engines to deliver safe and adaptive support for undergraduate students. More broadly, she is interested in optimizing the timing of digital interventions and advancing clinical safety in AI-driven mental health systems.
Before beginning her PhD, Yama earned a master’s in Clinical Psychology from Columbia University and worked as a data scientist at the Lab for Scalable Mental Health.
PhD in Quantitative Biomedical Science
Dartmouth College
MA in Clinical Psychology
Columbia University
BA in Economics
National Taiwan University

In this project, we constructed an ML pipeline that predicted changes in the overall severity of depression symptoms in adolescents with high symptoms over a three-month period. We computed the residuals from a linear regression model, predicting the 3-month depression sum score based on the baseline depression sum score.

Objective Rural teens are less likely to access care for depression than urban teens. Evidence-based digital single-session interventions (SSIs), offered via social media advertisements, may be well-suited to narrowing this gap in treatment access and increasing rural adolescents’ access to support.

In the United States, the experience of minority stress among LGBTQ+ youth varies across regions with high or low levels of stigma (e.g., laws, policies and cultural norms that limit the lives of individuals with stigmatized identities).

Objectives To examine the relationship between childhood traumatic experiences and early and late-onset suicidal behavior among depressed older adults. Methods Our sample included 224 adults aged 50+ (M ± SD = 62.

In young and middle-aged adults, suicidal ideation is an important predictor of prospective suicide attempts, but its predictive power in late life remains unclear. In this study, we used Latent Profile Analysis (LPA) in a cohort of depressed older adults to identify distinct ideation profiles and their clinical correlates and test their association with risk of suicidal behavior longitudinally.

Objective To determine how a statewide indicator of structural stigma is associated with suicidal thoughts and behaviors among sexual minority (SM) adolescents. Method We examined associations between structural stigma at the state level and suicidal thoughts and behaviors in a nationwide sample of sexual minority adolescents ages 14–18 in the United States (n=489) who completed a cross-sectional online survey in 2018.

Gender diverse individuals (i.e., identifying their gender as different from the sex assigned at birth) demonstrate higher rates of non-suicidal self-injury (NSSI) compared to other sexual and gender minority (SGM) populations.
Role: Co-Investigator Collaborator: Adrienne Grzenda, M.D., Ph.D. (University of California, Los Angeles), Stefanie Kirchner, MPH (Medizinische Universität Wien), Ping Wang (Autonomous University of Madrid), & Diana E. Clarke, Ph.D (Johns Hopkins University)

Role: First author Collaborator: Kasey B. Jackman (Columbia University), Jordan D. Dworkin (Columbia University), Anneliese A. Singh (Tulane University), Allen J. LeBlanc (San Francisco State University), & Walter O. Bockting (Columbia University)
UPMC Western Psychiatric Hospital | Fall 2021
I organized and developed a R workshop with four sessions including introduction to R, data wrangling, data visualization, and data analysis. Each session includes a 10-minute presentation to cover the learning goal and concept of each topic, following by a learning-by-doing module. This workshop aimed to guide everyone with no prior experience in R to feel comfortable with coding and eventually apply R coding skills in research projects. Please find the materials including slides and R scripts on my GitHub. Please feel free to reach out for recordings.