In This Section

zeej [at]
Location - People View

2716 South Street
Philadelphia, PA 19146
United States

Research Topics
Jarcy Zee, PhD
Jarcy Zee, PhD
Assistant Professor of Biostatistics

Dr. Zee's statistical methods research includes topics in survival analysis, measurement error, observational data methods, and machine learning. Her clinical research is focused on kidney disease, specifically in clinical and pathology markers of glomerular and chronic kidney disease progression.



Subscribe to be notified of changes or updates to this page.


Dr. Jarcy Zee is an assistant professor of Biostatistics at Children's Hospital of Philadelphia and the Department of Biostatistics, Epidemiology, and Informatics at the Perelman School of Medicine of the University of Pennsylvania. Her statistical methods interests are in survival analysis, measurement error, observational data analysis methods, and machine learning. Her clinical research is focused primarily on kidney disease, with specific interests in glomerular disease and chronic kidney disease.

Dr. Zee's current research projects include investigation of surrogate endpoints for kidney disease progression, agreement measures for assessing inter-rater reproducibility, methods for identifying time-varying and high-dimensional biomarkers of time-to-event outcomes, and the application of computational pathology for kidney biopsy image analysis.

Education and Training

BS, University of Delaware (Mathematics and Economics), 2007

MS, University of Pennsylvania (Biostatistics), 2012

PhD, University of Pennsylvania (Biostatistics), 2014

Titles and Academic Titles

Assistant Professor of Biostatistics

Senior Scholar, Center for Clinical Epidemiology and Biostatistics

Faculty Member, Graduate Group in Epidemiology and Biostatistics

Professional Memberships

American Statistical Association, 2011-

Eastern North American Region, International Biometric Society, 2012-

American Society of Nephrology, 2014-

Professional Awards

American Statistical Association Biometrics Section Student Travel Award, 2014

Saul Winegrad, MD, Award for Outstanding Dissertation in Biostatistics, 2015

Rare Disease Clinical Research Travel Award, 2016

Active Grants/Contracts

Novel Outcomes and Machine Learning Approaches for Improving Prediction of CKD Progression
NIH/NIDDK Chronic Renal Insufficiency Cohort (CRIC) Study Opportunity Pool
2020 - 2021
PIs: Jarcy Zee, PhD, and Abigail Smith, PhD (Parent Study PI: Harold Feldman, MD, MSCE)
Disease progression outcomes are evaluated against kidney failure to determine the optimal progression outcome. We also assess the effect of non-linear eGFR trajectories on the ability of progression outcomes to predict kidney failure. We will compare machine learning approaches for building risk prediction models of CKD progression, including assessment of model building techniques.

Continuation of the Nephrotic Syndrome Rare Disease Clinical Research Network (NEPTUNE)
2019 - 2024
PI: Matthias Kretzler, MD
We leverage the NEPTUNE resources to catalyze discovery, training and outreach as we strive to improve health outcomes for individuals affected by nephrotic syndrome (NS). The overarching goal is to apply a precision medicine approach to NS, leveraging the extensive NEPTUNE Knowledge Network established since 2009. NEPTUNE will implement this strategy to permit discovery of novel therapeutic targets and deploy a patient stratification approach to help identify the right trial for the right patient at the right time. Training, pilot and ancillary study programs will continue with significant funding support from Nephcure Kidney International.

Computational Pathology for Proteinuric Glomerulopathies
2018 - 2021
PIs: Lawrence Holzman, MD, Laura Barisoni, MD, Jeffrey Hodgin, MD, PhD, and Brenda Gillespie, PhD
In this project, we are (1) compiling a standardized comprehensive morphologic profile of NEPTUNE cohort renal biopsies to test whether these profiles contain reproducible descriptors or groups of descriptors that can reliably assess glomerular disease pathology; and (2) identifying quantitative structural parameters that are predictive of outcomes to establish a clinically relevant categorization of proteinuric diseases.