Faculty Profile

Kevin He

Kevin He, PhD

  • Associate Professor, Biostatistics

Kevin He is the Associate Director of the Kidney Epidemiology and Cost Center (KECC). His primary research interests include survival analysis, statistical machine learning, knowledge distillation, data integration, transfer learning, healthcare provider profiling, organ transplantation, dialysis outcomes research, causal inference, and statistical genetics. His methodological work is motivated by the analysis of large, complex data sources, including national disease registries, administrative claims, and high-dimensional genomic, epigenomic, and transcriptomic data.

  • PhD, Biostatistics, University of Michigan, 2012
  • MS, Biostatistics, University of Michigan, 2008
  • BS, Statistics, Queen's University, 2006
  • MS, Epidemiology, Queen's University, 2004
  • BM, Clinical Medicine, Dalian Medical University, 2002

Research Interest:

Survival analysis; statistical machine learning; knowledge distillation; data integration; transfer learning; healthcare provider profiling; organ transplantation; dialysis outcomes research; causal inference; statistical genetics.


Research Projects:

From 2017 to 2019, Dr. He served as the Biostatistical Lead for the United States Renal Data System (USRDS). He currently is the principal investigator of an NIH R01 focused on developing improved statistical methods for profiling healthcare providers. In addition, he is currently serving as the Biostatistical Lead for two Centers for Medicare & Medicaid Services (CMS) contracts: the Kidney Disease Quality Measure Development, Maintenance, and Support project and the Utilization of Data Indicators in the ESRD Survey Process project. In these roles, he has led national efforts to develop, evaluate, and refine quality measures used to assess U.S. dialysis facilities, organ procurement organizations (OPOs), and transplant centers.

Wang, D., Ye, W., Zhu, J., Xu, G., Tang, W., Zawistowski, M., Fritsche L. and He, K. (2026). Incorporating external risk information with the Cox model under population heterogeneity: applications to trans-ancestry polygenic hazard scores. Journal of the Royal Statistical Society: Series A, In Press.

Wang, D., Ye, W., Sung, R., Jiang, H., Taylor, J.M.G., Ly, L. and He, K. (2025). Kullback-Leibler-based discrete failure time models for integration of published prediction models with new time-to-event dataset. Annals of Applied Statistics, 19(2): 1167-1189.

Hartman, N., Messana, J.M., Kang, J., Naik, S.A., Shearon, T. and He, K. (2024). Composite scores for transplant center evaluation: a new individualized empirical null method. Annals of Applied Statistics, 18(1), 729-748.

Ding, X., He, K. and Kalbfleisch, J.D. (2024). Models and methods for analyzing clustered recurrent hospitalizations in the presence of COVID-19 effect. Journal of the Royal Statistical Society: Series C, 73(1), 2846.

Tang, W., He, K., Xu, G. and Zhu, J. (2022). Survival analysis via ordinary differential equations. Journal of the American Statistical Association, 32(4), 1685-1697.

Wu, W., Taylor, J.M.G., Brouwer, A. F., Luo, L., Kang, J., Jiang, H. and He, K. (2022). Scalable proximal methods for cause-specific hazard modeling with time-varying coefficients. Lifetime Data Analysis, 28(2), 194-218.

He, K., Kang, J., Zhu, J. and Li, Y. (2022). Stratified Cox models with time-varying effects for national kidney transplant patients: a new block-wise steepest ascent method. Biometrics, 78(3), 1221-1232.

He, K., Dahlerus, C., Xia, L., Li, Y.M. and Kalbfleisch, J.D. (2020). The profiling inter-unit reliability. Biometrics, 76(2), 654-663.

Suite 3645, Room 3655 SPH I
1415 Washington Heights
Ann Arbor, MI 48109

Email: kevinhe@umich.edu
Office: 734-764-2279

For media inquiries: sph.media@umich.edu

Areas of Expertise: Biostatistics,  Cancer,  Chronic Disease,  COVID-19,  Genetics,  Global Public Health,  Health Care,  Health Equity,  Precision Health