Research Interest
I have a broad interest in developing innovative statistical methods and easy-to-use computational tools to advance precision health by integrating real-world data and evidence collected from diverse populations and large datasets. My research aims to characterize similarity and heterogeneity across populations and diseases, and leverage the shared knowledge to improve the population-specific prevention, diagnosis, and treatment of diseases, focusing on under-represented populations where limited data is available.
-
Transfer learning methods to leverage pre-trained models for improving risk prediction in underrepresented populations
-
Statistical and computational methods for integrative analysis in large distributed research networks and biobank data
-
Statistical methods to incorporate external summary-level data from heterogeneous populations
-
Understanding racial/ethnic disparities in COVID-19 outcomes & vaccine effectiveness using electronic health record (EHR) data
-
Collaborative research to discover early disease and predict disease progression in Chronic Obstructive Pulmonary Disease (COPD)
Statistical methods to incorporate external summary-level data from heterogeneous populations
In 3 papers from my Ph.D. dissertation, we considered several aspects to aim for more flexible and general data integration frameworks, including
- Top: incorporating multiple external studies;
- Left: allowing flexible external model forms;
- Right: accounting for population heterogeneity;
- Bottom: making improved statistical inference for the external populations.
-
Gu T, Taylor JMG, Cheng W, Mukherjee B. (2019) Synthetic data method to incorporate external information into a current study. Canadian Journal of Statistics, 47(4): 580-603. [Link]
-
Gu T, Taylor JMG, Mukherjee B. (2021) A meta-inference framework to integrate multiple external models into a current study. Biostatistics. [Link]
-
Gu T, Taylor JMG, Mukherjee B. (2022) A synthetic data integration framework to leverage external summary-level information from heterogeneous populations. Biometrics. [Link]
Racial/ethnic disparities in COVID-19 outcomes & vaccine effectiveness using EHR data
In response to the worldwide pandemic and associated public health crisis, I began to actively participate in the COVID-19 research since early 2020 utilizing integrated data from various sources, including Electronic Health Record (EHR) data.
Featured Publication (view full list in Publication)
-
Gu T, Mack JA, Salvatore M,.., Mukherjee B. (2020). Characteristics associated with racial/ethnic disparities in COVID-19 outcomes in an academic health care system. JAMA Network Open, 3(10): e2025197. [Link]
-
Salvatore M, Gu T, Mack JA, .., Mukherjee B. A phenome-wide association study (PheWAS) of COVID-19 outcomes by race using the electronic health records data in Michigan Medicine (2021). Journal of Clinical Medicine, 10(7), 1351. [Link]
-
Roberts E, Gu T, Mukherjee B, Fritsche LG. (2022) Estimating COVID-19 vaccination Effectiveness using electronic health records of an academic medical center in Michigan. American Journal of Preventive Medicine Focus. [Link]
Collaborative research to discover early disease and predict disease progression in COPD
I have collaborated with pulmonary experts on several projects to discover early disease and diversity in the pathways towards disease progression in Chronic Obstructive Pulmonary Disease (COPD).
Featured Publication (view full list in Publication)
-
Belloli EA, Gu T, Vummidi D,..., Lama VN. (2021). Radiographic graft surveillance in lung transplantation: prognostic role of parametric response mapping. American Journal of Respiratory and Critical Care Medicine, 204(8):967-976. [Link]
-
Salisbury M, Gu T, Murray S,..., Flaherty K. (2019). Hypersensitivity Pneumonitis: Radiologic Phenotypes are Associated with Distinct Survival Time and Pulmonary Function Trajectory. Chest, 155(4): 699-711. [Link]
-
Labaki WW, Gu T, Murray S,..., Han MK. (2019). Voxel-Wise Longitudinal Parametric Response Mapping Analysis of Chest Computed Tomography in Smokers. Academic Radiology, 26(2): 217-223. [Link]