用本地部署的LLM融合多模态数据，精准预测生存期并生成可信结论。
Multimodal Survival Analysis with Locally Deployable Large Language Models
- 通过师生蒸馏与多模态融合，联合建模生存概率与医学文本生成
- 在TCGA数据集上优于传统基线，校准精度更高
- 适合隐私敏感场景，避免云端服务和幻觉风险
我们研究了结合临床文本、表格协变量和基因组数据的多模态生存分析，采用可在本地部署的大型语言模型（LLMs）。由于许多机构面临计算资源和隐私保护的严格限制，这一设置推动了轻量级、本地化模型的应用。我们的方法通过教师-学生蒸馏和合理的多模态融合，联合估计校准后的生存概率，并生成简洁、基于证据的预后文本。在TCGA队列上的实验表明，该方法优于标准基线，无需依赖云服务及相关的隐私问题，同时降低了基础LLM中常见的幻觉或校准偏差风险。
原文摘要 · Abstract (English)
We study multimodal survival analysis integrating clinical text, tabular covariates, and genomic profiles using locally deployable large language models (LLMs). As many institutions face tight computational and privacy constraints, this setting motivates the use of lightweight, on-premises models. Our approach jointly estimates calibrated survival probabilities and generates concise, evidence-grounded prognosis text via teacher-student distillation and principled multimodal fusion. On a TCGA cohort, it outperforms standard baselines, avoids reliance on cloud services and associated privacy concerns, and reduces the risk of hallucinated or miscalibrated estimates that can be observed in base LLMs.
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。