用生存分析结果训练大模型，让其学会生成患者风险预测。
From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model
- 将临床数据转为文本提示，以Cox模型输出为目标微调大模型。
- 在3个数据集上表现媲美传统生存分析方法，校准与区分度俱佳。
- 隐藏层空间呈现平滑风险梯度，说明模型理解连续风险结构。
我们探究能否将由Cox比例风险模型估算的时间至事件风险信息迁移到生成式大语言模型中。提出一种基于文本的生存建模流程：将结构化临床协变量转换为文本提示，并以Qwen为基础的大语言模型进行微调，使其生成个体患者的生存风险预测，训练目标为Cox模型的输出。在GBSG2、ACTG320和WHAS500三个数据集上，该模型尽管是以文本生成任务训练，仍展现出具有竞争力的外部区分度与校准能力。进一步分析模型隐藏状态的几何结构，t-SNE可视化显示隐空间中存在平滑的风险梯度，表明模型将生存风险表示为连续结构而非离散类别。这些发现共同说明大语言模型可内化生存风险结构并支持校准预测，为语言模型实现时间至事件推理提供了新路径。
原文摘要 · Abstract (English)
We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large language model. We propose a text-based survival modelling pipeline in which structured clinical covariates are converted into text prompts and a Qwen-based large language model is fine-tuned to generate patient-specific survival risk using Cox model predictions as a training target. Across GBSG2, ACTG320, and WHAS500, the model achieves competitive held-out discrimination and calibration despite being trained as a text-generation task rather than with a conventional survival-analysis loss. We further analyse the geometry of the model's hidden states, where t-SNE visualisations reveal smooth risk gradients in latent space, suggesting that the model represents survival risk as a continuous structure rather than isolated risk categories. Together, these findings suggest that large language models can internalise survival-risk structure while supporting calibrated prediction, providing a route towards time-to-event reasoning in language models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。