Table 4.

Contributions of recent studies with transfer learning.

Author and Citation	Contributions
Chai et al. [77]	Proposed a transfer learning-based Cox proportional hazards network (TCAP) to integrate multi-omics data for predicting bladder cancer prognosis.
Johnson et al. [78]	Proposed diagnostic evidence gauge of single cells, a deep transfer learning framework, to transfer disease information from patients to cells.
Shi et al. [79]	Developed a deep learning model, based on the VGG19 architecture and transfer learning strategy, for prognosis prediction in colorectal cancer based on histopathologic features of the tumor microenvironment.
Meng et al. [80]	Introduced SAVAE-Cox, a novel framework that incorporates an attention mechanism and an adversarial transfer learning strategy for survival analysis of high-dimensional transcriptome data.