B1465
Title: Accommodating time-varying heterogeneity in risk estimation under the Cox model: A transfer learning approach
Authors: Ziyi Li - The University of Texas MD (United States) [presenting]
Yu Shen - UT MD Anderson Cancer Center (United States)
Jing Ning - The University of Texas MD Anderson Cancer Center (United States)
Abstract: In recent years, transfer learning has attracted increasing attention for adaptively borrowing information across different data cohorts in various settings. The method is motivated by the question of how to utilize cancer registry data as a complement to improve the estimation precision of individual risks of death for inflammatory breast cancer (IBC) patients at MD Anderson Cancer Center. When transferring information for risk estimation based on the cancer registries (i.e., source cohort) to a single cancer centre (i.e., target cohort), time-varying population heterogeneity needs to be appropriately acknowledged. However, there is no literature on how to adaptively transfer knowledge on risk estimation with time-to-event data from the source cohort to the target cohort while adjusting for time-varying differences in event risks between the two sources. The aim is to address this statistical challenge by developing a transfer learning approach under the Cox proportional hazards model. The proposed method yields more precise individualized risk estimation than using the target cohort alone. Meanwhile, the method demonstrates satisfactory robustness against cohort differences compared with the method that directly combines the target and source data in the Cox model.
