XU SHI
  • Home
  • Research
  • Publication
  • SOFTWARE/APP
  • Teaching
Picture
Contact Information:
shixu at umich.edu​
Links:
Google Scholar
University of Michigan
I am an Assistant Professor in the Department of Biostatistics at University of Michigan. Previously I was a postdoctoral fellow at the Harvard Data Science Initiative, working with Tianxi Cai and Eric Tchetgen Tchetgen in the Department of Biostatistics at the Harvard TH Chan School of Public Health. I did my Ph.D. in Biostatistics at University of Washington, under the supervision of Andrea Cook and Patrick Heagerty. I obtained my B.S. in Mathematics and Applied Mathematics with a minor in English at the Chu Kochen Honors College of Zhejiang University, China.

My research focuses on developing statistical methods for administrative healthcare data such as electronic health records (EHR) and claims data. I develop scalable and automated pipelines for curation and harmonization of EHR data across healthcare systems. I also develop causal inference methods that harness the full potential of EHR data to address comparative effectiveness and safety questions. I co-lead the Causal Inference Core of the FDA’s Sentinel Initiative Innovation Center to develop innovative statistical methods to monitor the safety of FDA-regulated medical products and explore novel ways to utilize information from distributed EHR data partners.

My research at a glance: data science + EHR + causal inference

Picture
Coding differences between Henry Ford Health System and Kaiser Permanente Northern California and differential utilization patterns
Picture
The future does not affect the past: past health outcome is a negative control in air pollution study to mitigate unmeasured confounding
Picture
Rare adverse event necessitates flexible propensity score methods
Picture
Medical knowledge extraction from co-occurrence pattern in EHR and ICD code translation between Partners HealthCare and Veterans Health Administration: spherical data corrupted by mismatch
Picture
Estimation of natural indirect effect robust to unmeasured confounding and measurement error in the mediator
  • Home
  • Research
  • Publication
  • SOFTWARE/APP
  • Teaching