Modeling the Co-Evolution of Substance Use Behavior and Peer Networks of Risk/Support
Led by Dr. Hau ChanUniversity of Nebraska-Lincoln
Study Overview:
This project seeks to develop stochastic forecasting machine-learning models for future substance use and future peer risk/support networks at long timescales within months and for future substance use at short timescales within days using data on covariates of individual attributes and peer network features.
Specific Aims:
(Aim 1): Establish validated predictive models for future substance use and future peer risk/support networks at long timescales.
(Aim 2): Identify significant modifiable predictive factors of future substance use at short timescales.
Study Sample Population:
We will use an already existing dataset collected by RDAR’s Rural Health Cohort (RHC) Study (Cohort 1) to develop our predictive model (Aim 1) of future substance use and future peer risk/support networks. RDAR is currently collecting data from the second cohort of people who use drugs (Cohort 2). We will use Cohort 2 data to validate our predictive model and identify modifiable factors for future substance use at short timescales (Aim 2).
Unique Study Procedures:
None.
Long-Term Goals:
Our long-term goal is to develop stochastic simulations of realistic substance use disorder-related behavioral contagion in plausible dynamic networks to inform resource allocation and contingency planning.
Dr. Hau ChanPROJECT Director
Hau Chan is currently an assistant professor in the School of Computing at the University of Nebraska-Lincoln. His current research aims to address the modeling and computational aspects of societal problems (e.g., game-theoretic models for social science domains, resource distributions/allocations, and AI for substance use) from AI, data mining, and machine learning perspectives. He received his Ph.D. in Computer Science from Stony Brook University in 2015 and completed three years of Postdoctoral Fellowships at Trinity University and the Laboratory for Innovation Science at Harvard University from 2015 to 2018.
Dr. Chan is a recipient of an NSF Graduate Research Fellowship, an NSF East Asia and Pacific Summer Fellowship, a 2015 SDM Best Paper Award, a 2016 AAMAS Best Student Research Paper Award, a 2018 IJCAI Distinguished PC Member Recognition, and a 2022 WSDM Outstanding PC Member Recognition. He is an early career project leader at the Rural Drug Addiction Research Center (NIH NIGMS’s COBRE).
He has served as a Co-chair for the 2021-2022 AAMAS Doctoral Consortium, a Co-chair for the 2021-2022 AAMAS Scholarships, and a Co-chair for the 2022 AAMAS Diversity and Inclusion Activities. He has regularly given tutorials and talks on computational game theory and mechanism design at venues such as AAMAS and IJCAI since 2018, including an Early Career Spotlight at IJCAI-ECAI 2022.
Kimberly TylerMentor
Dr. Kimberly Tyler, Willa Cather Professor of Sociology at UNL, will serve as co-Director for cohort development at LNC. Dr. Tyler has a Ph.D. in sociology with specific training, experience, and expertise in key research areas relevant to current core goals of facilitating RDAR projects, including research in substance use, rural populations, hard-to-sample populations (e.g., homeless and street youth and young adults), and HIV risk behavior (i.e., sexual and drug use).
Dr. Tyler designed and successfully carried out three cohort-based NIH projects on hard to reach populations in the Great Plains region, including an NIMH-funded homeless young adult project (K01MH064897) and a NIDA-funded homeless youth R21 project (DA021079) on social networks and homeless youth and a NIDA-funded homeless youth and young adult project (DA036806) on alcohol and drug use, mental health, and social support using ecological momentary assessment (EMA) via short message service (SMS) surveying. This longitudinal project had a follow-up response rate of over 75%.
Dr. Tyler not only has expertise with sampling hard-to-reach populations, she also knows how to track and re-locate such populations. Her primary responsibilities as LNC co-Director will be to consult with Project Leaders, mentors, and the RDAR leadership team on the development, tracking, and retention of the RDAR Rural Drug User Cohort and, following this, to seek out new collaborative researchers across the Nebraska system and in the Central Plains region (such as BoysTown Hospital, Creighton Medical School, the Veterans Administration Hospital of Western Iowa and Nebraska, and universities in Iowa, Kansas, Missouri, and the Great Plains).
Bilal KhanMentor
Dr. Bilal Khan is a professor of Data Science and the director of the Health Data Warehouse at Lehigh University.