Tackling Small Sample Survival Analysis via Transfer Learning: A Study of Colorectal Cancer Prognosis

2025-01-21

AI Summary

Survival prediction for colorectal cancer remains challenging under small-scale clinical data—only 728 cases available, with extreme low-resource settings as few as 50 samples. Method: We propose the first general-purpose transfer learning framework compatible with both parametric (e.g., DeepSurv, Cox-CC, DeepHit) and non-parametric (e.g., Random Survival Forest, RSF) survival models. It adopts a pretraining–fine-tuning paradigm and introduces Transferable Survival Forest (TSF), the first tree-based method enabling cross-institutional structural knowledge transfer and local adaptation. Contribution/Results: Evaluated on multi-center clinical datasets fused with SEER data, our framework significantly improves model performance: RSF achieves a C-index of 0.8297 (+0.0357), and Cox-CC reaches 0.8111 (+0.0243); gains are especially pronounced in ultra-low-sample regimes. This work establishes a scalable, model-agnostic transfer learning paradigm for small-sample medical survival analysis.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Survival prognosis is crucial for medical informatics. Practitioners often confront small-sized clinical data, especially cancer patient cases, which can be insufficient to induce useful patterns for survival predictions. This study deals with small sample survival analysis by leveraging transfer learning, a useful machine learning technique that can enhance the target analysis with related knowledge pre-learned from other data. We propose and develop various transfer learning methods designed for common survival models. For parametric models such as DeepSurv, Cox-CC (Cox-based neural networks), and DeepHit (end-to-end deep learning model), we apply standard transfer learning techniques like pretraining and fine-tuning. For non-parametric models such as Random Survival Forest, we propose a new transfer survival forest (TSF) model that transfers tree structures from source tasks and fine-tunes them with target data. We evaluated the transfer learning methods on colorectal cancer (CRC) prognosis. The source data are 27,379 SEER CRC stage I patients, and the target data are 728 CRC stage I patients from the West China Hospital. When enhanced by transfer learning, Cox-CC's $C^{td}$ value was boosted from 0.7868 to 0.8111, DeepHit's from 0.8085 to 0.8135, DeepSurv's from 0.7722 to 0.8043, and RSF's from 0.7940 to 0.8297 (the highest performance). All models trained with data as small as 50 demonstrated even more significant improvement. Conclusions: Therefore, the current survival models used for cancer prognosis can be enhanced and improved by properly designed transfer learning techniques. The source code used in this study is available at https://github.com/YonghaoZhao722/TSF.

Problem

• 迁移学习
• 生存分析
• 结直肠癌

Innovation

• Transfer Learning
• Survival Analysis
• Colorectal Cancer Prediction