Thuy Le

Dr. Thuy Le serves as an Assistant Research Scientist in the Department of Health Management and Policy at the University of Michigan School of Public Health. Her expertise bridges mathematical modeling, machine learning, and public health policy with a focus on tobacco regulatory science and cancer research. She develops computational frameworks to evaluate breast cancer screening protocols, predict leukemia treatment outcomes, and quantify population-level tobacco impacts.

Education:

• PhD, University of Padua, Italy (2016)
• Diploma, Belarusian State University (2012)

Dr. Le's research integrates mathematical modeling, machine learning, and causal inference to address critical public health challenges. She has pioneered models assessing mammography benefits, white blood cell dynamics during leukemia therapy, and the disproportionate harm of menthol cigarettes on African American communities. Her current work applies advanced machine learning to tobacco regulatory science, analyzing large-scale datasets like the PATH study to predict smoking cessation and understand initiation risk factors. This research directly informs FDA tobacco product regulation and health equity initiatives.

Analysis of Dr. Le's publication trajectory (2020-2025) reveals three dominant themes: 1) Quantifying tobacco-related disease burden through mathematical modeling, 2) Developing machine learning tools for smoking behavior prediction, and 3) Analyzing health disparities in tobacco impacts. Her work increasingly combines Kalman filtering for trend analysis with deep learning for feature extraction, demonstrating methodological innovation in public health modeling. Key applications include cessation rate forecasting, menthol cigarette harm estimation, and electronic nicotine delivery system risk assessment.

Scientific Awards: No awards listed in available sources.

Dr. Le co-leads a pilot project on machine learning-based smoking behavior prediction and contributes to the Center for the Assessment of Tobacco Regulations. Her research is supported by tobacco regulatory science initiatives, likely involving NIH/FDA funding mechanisms. While specific grant details aren't public, her projects align with FDA Center for Tobacco Products priorities including product standards and health disparities research.

She collaborates with the Center for the Assessment of Tobacco Regulations and leads computational research teams applying mathematical modeling to tobacco regulatory questions. Her lab integrates stochastic simulation, causal inference, and machine learning to address complex public health challenges, maintaining strong connections with clinical researchers and policy analysts at Michigan Public Health.