Prediction of time-to-event data often suffers from rare event rates, small sample sizes, high dimensionality and low signal-to-noise ratios. Incorporating published prediction models from large-scale studies is expected to improve the performance of prognosis prediction on internal small-sized time-to-event data. To account for challenges including heterogeneity, data sharing, and privacy constraints, we propose a Bregman divergence-based transfer learning procedure, which is computationally efficient for high-dimensional problems and can be easily implemented with various machine learning methods.
To obtain a Zoom link, please email [email protected].