Colloquium - Kevin He - November 20, 2025

Speaker: Kevin He, University of Michigan
Date/Time: Thursday, November 20, 2025, 10:00 AM - 11:00 AM ET

Title: Deep Survival Learning for Kidney Transplantation: Knowledge Distillation and Data Integration

Abstract: Prognostic prediction using survival analysis faces challenges due to complex relationships between risk factors and time-to-event outcomes. Deep learning methods have shown promise in addressing these challenges, but their effectiveness often relies on large datasets. However, when applied to moderate- or small-sized datasets, deep models frequently encounter limitations such as insufficient training data, overfitting, and difficulty in hyperparameter optimization. To mitigate these issues and enhance prognostic performance, this talk presents a flexible deep learning framework that integrates external risk scores with internal time-to-event data through a generalized Kullback–Leibler divergence regularization term. Applied to the national kidney transplant data, the proposed method demonstrates improved prediction of short-term mortality and graft failure following kidney transplantation by distilling and transferring prior knowledge from pre-policy-change teacher models to newly arrived post-policy-change cohorts.

Bio: Kevin He is an Associate Professor of Biostatistics and the Associate Director of the Kidney Epidemiology and Cost Center (KECC) at the University of Michigan. He obtained his Ph.D. in Biostatistics from the University of Michigan in 2012. His research focuses on survival analysis, knowledge distillation, data integration, transfer learning, healthcare provider profiling, organ transplantation and kidney dialysis. 

Website: https://sph.umich.edu/faculty-profiles/he-zhi.html     https://www.um-kevinhe-group.org/