Prediction-Oriented Transfer Learning for Survival Analysis

TL;DR

This paper introduces a transfer learning framework for survival analysis that transfers predictive knowledge without requiring source data sharing, improving prediction accuracy especially with limited target data.

Contribution

It proposes a novel transfer learning method that transfers predictive information rather than distributional parameters, using flexible models and an EM algorithm, with proven asymptotic properties.

Findings

Faster convergence rate than target-only estimators when source knowledge is accurate.

Effective in simulation studies and real breast cancer data applications.

Eliminates need for source data sharing, enhancing privacy and practicality.

Abstract

Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share similar parameters under Cox models, and most require access to individual-level source data. In this article, we propose a novel transfer learning framework that enhances model-based survival prediction by transferring predictive rather than distributional knowledge from source studies. Our approach employs flexible semiparametric transformation models for the target data while eliminating the need to model or share the source data. The ingeniously designed penalty enables simple and stable computation via an EM algorithm. We rigorously establish the asymptotic properties of the proposed estimator and show that it achieves a faster convergence rate than the target-only estimator when source knowledge is sufficiently accurate. We demonstrate the advantages of our methods through extensive simulation studies and an application to two major breast cancer studies.