Embedded Files
Assessing Alcohol Use Disorder using Machine Learning techniques:
(1) This study examines lifestyle, background, and family history factors associated with Alcohol Use Disorder (AUD) using data from the All of Us Research Program. Using interpretable machine learning and statistical analyses, we identify key contributors to AUD risk, including annual income, residential stability, recreational drug use, sex/gender, marital status, education, and family history. The findings confirm the robustness of these determinants and highlight the need for multi-level prevention strategies addressing behavioral, familial, and structural risk factors.
(2) This study uses large language models (LLMs) to synthesize risk factors for alcohol use disorder (AUD) from fifty highly cited articles published between 2021 and 2025. Results identify major determinants, including hazardous drinking patterns, genetic predisposition, adverse childhood experiences, psychiatric comorbidities, and socioeconomic status. The findings demonstrate the value of AI-driven literature reviews for understanding the multifactorial nature of AUD and informing prevention and intervention strategies.
Related publications:
Synthesizing Risk Factors for Alcohol Use Disorder Using a Large Language Model. (pdf)
Wang, C., Riener, K., Luo, Y. Preprint on Figshare
Enhanced Insights into Alcohol Use Disorder from Lifestyle, Background, and Family History in a Large-Scale Machine Learning Study. (pdf)
Wang, C., Luo, Y. , Huang, G., & Zhou, W.
Preprint on MedRxiv
Assessing Alcohol Use Disorder: Insights from Lifestyle, Background, and Family History with Machine Learning Techniques. (pdf)
Wang, C., Huang, G., & Luo, Y.
In Proceedings of the International Symposium on Human Factors and
Ergonomics in Health Care, 2025
Modeling the formation of groups using Game Theory:
(1) Sequential Games: Temporal Group Formation
Real-world Application: Flock formation among migratory birds
This project studies the trade-off between cooperation and competition in group formation. Agents with different strengths compete for better resources while forming groups to reduce individual costs and gain benefits such as protection, energy efficiency, and more accurate navigation. Using sequential game models, we analyze how arrival times affect grouping behavior, characterize Subgame Perfect Equilibria (SPEs), and identify conditions that lead to grand groups, no groups, and more diverse grouping outcomes under relaxed definitions of group formation.
Related Publications:
A theoretical model of flock formation to understand trade-offs between cooperation and competition. (pdf)
Wang, C., Moharrami, M., DuBay, S. G., Liu, M.
In Ecosphere 17(2): e70535
A Stackelberg Game Model of Flocking. (pdf)
Wang, C., Moharrami, M., & Liu, M.
Accepted by the 63rd IEEE Conference on Decision and Control (CDC), 2024
Cooperation and Competition: A Sequential Game Model of Flocking
Wang, C., DuBay, S. G., & Liu, M.
In the 62nd IEEE Conference on Decision and Control (CDC), 2023
(2) Simultaneous Games: Spatial Group Formation
Real-world Application: Los Angeles gang groups
This project studies the trade-off between resource pooling and spatial cohesion in group formation. Agents with resources and spatial locations form disjoint groups, balancing collective strength against geographic dispersion. We study the stability and structure of such groups through Individually Stable Equilibrium (ISE) and Strong Individually Stable Equilibrium (SISE), derive spatial properties of equilibria, represent group relationships using directed graphs and DAGs, and apply the model to criminal gang groups in Los Angeles.
Related publications:
Structural Stability of a Family of Spatial Group Formation Games.
Wang, C., Moharrami, M., Jin, K., Kempe, D., Brantingham, P. J., & Liu, M.
In IEEE Transactions on Network Science and Engineering (TNSE), 2024
Modeling human trust in automation using Machine Learning:
Research shows that through repeated interactions with automation, human operators are able to learn how reliable the automation is and update their trust in automation. The goal of the present study is to investigate if this learning and inference process approximately follows the principle of Bayesian probabilistic inference. First, we applied Bayesian inference to estimate human operators’ perceived system reliability and found high correlations between the Bayesian estimates and the perceived reliability for the majority of the participants. We then correlated the Bayesian estimates with human operators’ reported trust and found moderate correlations for a large portion of the participants. Our results suggest that human operators’ learning and inference process for automation reliability can be approximated by Bayesian inference.
Related publication:
Automation reliability and trust: A Bayesian inference approach
Wang, C., Zhang, C., & Yang, X. J.
In Proceedings of the Human Factors and Ergonomics Society Annual Meeting (HFES), 2018
Page updated
Report abuse