Tian Gu, PhD

  • Assistant Professor of Biostatistics
Profile Headshot

Overview

Dr. Gu's research focuses on developing statistical and machine-learning approaches to advance precision medicine and improve patient outcomes in diverse populations. Her work spans predictive modeling with large-scale biobank and EHR data, generative models for synthetic data generation and medical imaging, and fine-tuning large language models for health applications. She also develops federated learning and other privacy-preserving approaches to enable secure analysis of sensitive health data. The methods and software she developed have supported studies in infectious disease epidemiology, pulmonary diseases, cardiovascular diseases, and cancer.

Academic Appointments

  • Assistant Professor of Biostatistics

Credentials & Experience

Education & Training

  • BS, 2015 Statistics, East China Normal University
  • BS (Dual Degree), 2015 Mathematics, Colorado State University
  • MS, 2017 Biostatistics, University of Michigan
  • PhD, 2021 Biostatistics, University of Michigan
  • Fellowship: 2023 Harvard University

Honors & Awards

  • 2023: ASA Statistic in Epidemiology Section Young Investigator Award
  • 2022: Harvard Data Science Initiative Postdoc Fellow Research Award
  • 2022: Biometrics Excellent Referee Award

Research

Research Interests

  • Artificial Intelligence (AI)
  • Data integration
  • Electronic Health Records (EHR/EMR)
  • Federated learning
  • Machine Learning (ML)
  • Synthetic data
  • Transfer learning

Selected Publications

Gu, T., Han, Y., & Duan, R. (2023). Robust angle-based transfer learning in high dimensions. Journal of the Royal Statistical Society Series B: Statistical Methodology. qkae111

Gu, T., Lee, P, & Duan, R. (2023). COMMUTE: Communication-efficient transfer learning for multi-site risk prediction. Journal of Biomedical Informatics. DOI: 10.1016/j.jbi.2022.104243

Gu, T., Taylor, J. M. G., & Mukherjee, B. (2023). A synthetic data integration framework to leverage external summary?level information from heterogeneous populations. Biometrics. PMCID: PMC10480346. DOI: 10.1111/biom.13852

Labaki, W. W., Gu, T., Murray, S., Curtis, J. L., et al. (2023). Causes of and Clinical Features Associated with Death in Tobacco Cigarette Users by Lung Function Impairment. American Journal of Respiratory and Critical Care Medicine. PMCID: PMC10449063. DOI: 10.1164/rccm.202210-1887OC