Skip to header Skip to Content Skip to Footer

Substance Use & Data Science

Research

The Substance Use and Data Science (SUDS) Pillar focuses on improving the understanding, prevention, and treatment of substance use and addictive behaviors through advanced data science and machine learning. By combining clinical expertise with computational modeling, this pillar develops new ways to detect, predict, and respond to substance use patterns using large-scale behavioral and biomedical data.

What We Do

This pillar integrates psychology, mathematics, and data science to analyze complex datasets and develop predictive models of substance use behavior. Using wearable devices and large healthcare datasets, researchers identify physiological and behavioral markers of substance use, including stimulant use, vaping, and opioid-related behaviors. These tools support the development of machine learning algorithms that can improve early detection, personalize treatment strategies, and enhance clinical decision-making.

Impact

Through partnerships with industry and healthcare data providers, this pillar translates data-driven insights into practical applications for treatment and prevention. The work supports early intervention strategies, informs public health policy, and improves personalized care for individuals affected by substance use disorders. It also strengthens external funding opportunities and advances scalable digital health solutions.

Explore Our Projects

The Substance Use and Data Science (SUDS) Lab is dedicated to advancing the understanding and treatment of substance use and addictive behaviors through cutting-edge data science and machine learning methodologies, paired with strong experimental design and domain knowledge. SUDS’ mission is to leverage the power of data to unravel the complexities of addiction, inform evidence-based interventions, and improve outcomes for individuals and communities affected by substance use disorders.

Through interdisciplinary collaboration, innovative research, and the development of state-of-the-art machine learning models, the center aims to improve substance use treatment and prevention by 1) better leveraging existing data sets generated in the context of substance use research and/or treatment and 2) utilizing novel data collection strategies, coupled with data science, to acquire the data most relevant to clinical decision-making.