SurvMaximin: Robust federated approach to transporting survival risk prediction models - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Journal of Biomedical Informatics Année : 2022

SurvMaximin: Robust federated approach to transporting survival risk prediction models

Xuan Wang
Xin Xiong
Griffin Weber
Gabriel Brat
Clara-Lea Bonzel
Rui Duan
  • Fonction : Auteur
Nathan Palmer
Kelly Cho
Hossein Estiri
David Hanauer
Yuk-Lam Ho
John Holmes
Sara Lozano-Zahonero
Sarah Maidlow
Bertrand Moal
  • Fonction : Auteur
Michele Morris
Gilbert Omenn
Emily Schriver
Petra Schubert
Valentina Tibollo
Patric Tippmann
Zongqi Xia
Daniela Zöller
Paul Avillach
Tianxi Cai

Résumé

Objective For multi-center heterogeneous Real-World Data (RWD) with time-to-event outcomes and high-dimensional features, we propose the SurvMaximin algorithm to estimate Cox model feature coefficients for a target population by borrowing summary information from a set of health care centers without sharing patient-level information. Materials and Methods For each of the centers from which we want to borrow information to improve the prediction performance for the target population, a penalized Cox model is fitted to estimate feature coefficients for the center. Using estimated feature coefficients and the covariance matrix of the target population, we then obtain a SurvMaximin estimated set of feature coefficients for the target population. The target population can be an entire cohort comprised of all centers, corresponding to federated learning, or can be a single center, corresponding to transfer learning. Results Simulation studies and a real-world international electronic health records application study, with 15 participating health care centers across three countries (France, Germany, and the U.S.), show that the proposed SurvMaximin algorithm achieves comparable or higher accuracy compared with the estimator using only the information of the target site and other existing methods. The SurvMaximin estimator is robust to variations in sample sizes and estimated feature coefficients between centers, which amounts to significantly improved estimates for target sites with fewer observations. Conclusions The SurvMaximin method is well suited for both federated and transfer learning in the high-dimensional survival analysis setting. SurvMaximin only requires a one-time summary information exchange from participating centers. Estimated regression vectors can be very heterogeneous. SurvMaximin provides robust Cox feature coefficient estimates without outcome information in the target population and is privacy-preserving.

Dates et versions

hal-03886953 , version 1 (06-12-2022)

Identifiants

Citer

Xuan Wang, Harrison Zhang, Xin Xiong, Chuan Hong, Griffin Weber, et al.. SurvMaximin: Robust federated approach to transporting survival risk prediction models. Journal of Biomedical Informatics, 2022, 134, pp.104176. ⟨10.1016/j.jbi.2022.104176⟩. ⟨hal-03886953⟩

Collections

INSERM U1219
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More