Faculty Profile

Lili  Zhao, PhD

Lili Zhao, PhD

  • Research Associate Professor, Biostatistics Department
  • 1415 Washington Heights
  • M4509, SPH II
  • Ann Arbor, Michigan 48109-2029

Lili Zhao is a Research Associate Professor in the Department of Biostatistics. She received her PhD in Statistics from the University of Iowa in 2006. She was a senior statistician at Becton, Dickinson and Company from 2006-2007, came to the Comprehensive Cancer Center at the University of Michigan in 2007 as a Statistician Lead, and joined the Department of Biostatistics in 2011 as a faculty member.  She has collaborated with researchers in disease areas, including Cancer, Cardiology, Pathology, Cirrhosis, Neurology, Endocrinology, Obstructive Sleep Apnea, Infectious Diseases, Diabetes, and Surgery. She has strived to develop, translate and promote the use of innovative statistical methodologies in biomedical research. As a Co-Investigator on numerous NIH and foundation-funded studies, she has adapted methodologies, including Bayesian data analysis, causal inference, generalized linear models, longitudinal data analysis, multivariate analysis, survival data analysis and machine learning methods, in response to the unique needs of individual studies and objectives without compromising the integrity of the research and results. 

Biostat 523 in OJOC program

Biostat 524 in OJOC program

  • PhD, Statistics, University of Iowa, 2006
  • M.A., Statistics, University of Iowa, 2004
  • B.S., Business and Economics, Capital University of Economics and Business, Beijing, 1999

Vaccine Safety Study:

Effective and rigorous analyses of post-vaccination adverse events is critical to ensure the safety of vaccines. In this study, we will develop a series of methods for vaccine safety surveillance while incorporating adverse event ontology. The current interests focus on studying safety of COVID19 vaccine using data from the national vaccine safety surveillance program, electronic health record data and insurance claims data.

This research is funded through my R01 grant from the National Institutes of Health entitled "Incorporation of multilevel ontologies of adverse events and vaccines for vaccine safety surveillance "

Safety of Immunotherapy in Patients with Cancer and Autoimmune Disease

Immune-checkpoint inhibitors (ICIs) are arguably the most important development in cancer therapy over the past decade, reshaping many of the previous standard-of-care approaches. However, a very large group of patients with autoimmune disease (AID) are not being helped because we do not fully understand the toxicity immunotherapy might present to this group. This study will objectively estimate the safety and efficacy of ICIs in patients with advanced cancer and concomitant AID, using a large, nationally representative dataset.

The publications cover a wide spectrum of research and reflect my broad portfolio of collaborations.

Zhao L and Dai Feng. “Deep neural networks for survival analysis using pseudo values”. IEEE Journal of Biomedical and health Informatics.24 (11), 3308-3314, 2020.

Zhao L. “Deep neural networks for predicting restricted mean survival times”."  Bioinformatics. Published online on 5 Jan 2020. https://doi.org/10.1093/bioinformatics/btaa1082.

Zhao, L., Murray, S., Mariani, L. H., and Ju, W. “Incorporating longitudinal biomarkers for dynamic risk prediction in the era of big data: A pseudo‐observation approach”. Stat Med, 39(26), 3685-3699, 2020.

Zhao L, Lee S, Li R, Ong E, He Y and Freed G. “Improvement in the Analysis of Vaccine Adverse Event Reporting System Database”. Statistics in Biopharmaceutical Research. 12(3): 303-310, 2020.

Zhao L, Anderson MT, Wu W, T Mobley HL, Bachman MA: “TnseqDiff: identification of conditionally essential genes in transposon sequencing studies”. BMC Bioinformatics: 18(1):326, 2017

Zhao L, Wu W, Feng D, Jiang H and Nguyen X. Bayesian Analysis of RNA-Seq Data Using a Family of Negative Binomial Models. Bayesian Analysis: 13(2):144-436, 2018.

Zhao L, Lee J, Mody, R and Braun TM: “The Superiority of the Time-to-Event Continual Reassessment Method to the Rolling Six Design in Pediatric Phase I Cancer Trials.” Clinical Trials, 8(4):361-369, 2011

Zhao L, Shi J, Shearon TH, and Li Y: “A Dirichlet process mixture model for survival outcome data:  assessing nationwide kidney transplant centers.” Stat Med, 34(8): 1404-1416, 2015

Zhao L, Taylor JMG, Schuetze SM: “Bayesian decision theoretic two-stage design in phase II clinical trials with survival endpoint.” Stat Med, 31(17): 1804-1820, 2012

Zhao L and Carl Koschmann. Integrating subgroups with mixed-type endpoints in early phase oncology trials. Statistical Methods in Medical Research,  29(2): 498-508,2019

Zhao L, Feng D, Neelon B and Buyse M:Evaluation of treatment efficacy using a Bayesian mixture piecewise linear model of longitudinal biomarkers.” Stat Med, 34(10): 1733-1746, 2015.

Zhao L, Morgan MA, Parsels LA, Maybaum J, Lawrence TS, Normolle D: “Bayesian Hierachical changepoint methods in modeling the tumor growth profiles in xenograft experiments.”  Clin Cancer Res, 17(5):1057-64, 2011

  • American Statistical Association
  • International Society for Bayesian Analysis