CMStatistics 2021: Start Registration
View Submission - CMStatistics
Title: Targeting underrepresented populations in precision medicine: A federated transfer learning approach Authors:  Rui Duan - Harvard University (United States) [presenting]
Abstract: One serious challenge in precision medicine research is the limited representation of minorities and disadvantaged populations, such as populations with low socioeconomic status and racial and ethnic minority groups. To advance prediction medicine, it is crucial to improve the performance of statistical and machine learning models in underrepresented populations so as not to exacerbate health disparities. We address the lack of representation and disparities in model performance through two strategies: (1) leverage the shared knowledge from diverse populations, and (2) integrate larger bodies of data from multiple healthcare organizations. More specifically, we develop transfer learning strategies to transfer the shared knowledge learned from diverse populations to an underrepresented population, so that comparable model performance can be reached with much fewer data. On the other hand, we propose federated learning methods to increase the sample sizes of underrepresented populations and the diversity of the data through multi-center collaborative research via a safe and efficient way. Our methods have solid theoretical foundations. We demonstrate the feasibility and validity of our methods through numerical experiments and a real application to a multi-center study for constructing polygenic risk prediction models for Type II Diabetes.