Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation
作者: Minh-Khoi Pham, Luca Cotugno, Alina Sirbu, Tai Tan Mai, Martin Crane, Marija Bezbradica
分类: cs.LG, cs.AI
发布日期: 2026-06-10
备注: Accepted for publication at International Conference on AI in Healthcare 2026
💡 一句话要点
提出轻量级适应方法以解决临床生存分析问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 生存分析 临床决策 迁移学习 表格基础模型 多任务学习 右删失数据 深度学习
📋 核心要点
- 现有的生存分析方法通常依赖于特定任务的训练和大量标注数据,限制了其在临床应用中的广泛性。
- 本文提出了一种轻量级的适应方法,通过在预训练的表格基础模型上添加生存感知头,来解决临床生存分析问题。
- 实验结果显示,TabDPT-FT-MTLR在MIMIC-IV数据集上达到了0.856的C-index,相较于最佳非基础模型DeepSurv提升了1.4%。
📝 摘要(中文)
预测时间到事件的结果(如死亡率)是临床决策中的基本任务,通常通过生存分析来解决。尽管传统统计和深度学习方法已被广泛研究,但它们通常需要特定任务的训练和足够的标注数据。本文提出了一种轻量级适应方法,通过在预训练表示的基础上直接训练生存感知头,将表格基础模型应用于临床生存分析。我们在多个公共生存基准和两个大型ICU队列(MIMIC-IV和eICU)上评估了该方法,结果表明该迁移学习方法在性能上与强基线相比具有竞争力或优越性。
🔬 方法详解
问题定义:本文旨在解决临床生存分析中的时间到事件预测问题,现有方法通常需要大量标注数据和特定任务的训练,限制了其应用。
核心思路:提出了一种轻量级的适应方法,通过在预训练的表格基础模型上直接训练生存感知头,以适应生存分析任务。
技术框架:整体架构包括预训练的表格基础模型(如TabPFN、TabDPT和TabICL)和一个多任务逻辑回归(MTLR)头,后者用于建模右删失的时间到事件结果。
关键创新:本研究的创新点在于将预训练的表格表示与生存感知目标相结合,提供了一种有效的临床生存预测替代方案。
关键设计:在模型设计中,采用了多任务逻辑回归头来处理生存分析任务,并在多个公共生存基准和大型ICU数据集上进行了评估。
🖼️ 关键图片
📊 实验亮点
实验结果表明,TabDPT-FT-MTLR在MIMIC-IV数据集上达到了0.856的C-index,相较于最佳非基础模型DeepSurv(0.844)提升了1.4%,在eICU数据集上TabICL-FT-MTLR达到了0.797,分别较DeepSurv(0.784)提升了1.7%。这些结果突显了预训练表格表示与生存感知目标结合的重要性。
🎯 应用场景
该研究的潜在应用领域包括临床决策支持系统,尤其是在重症监护和肿瘤治疗等领域。通过提供更准确的生存预测,能够帮助医生制定更有效的治疗方案,提升患者的生存率和生活质量。未来,该方法有望推广到其他医疗领域,推动个性化医疗的发展。
📄 摘要(原文)
Predicting time-to-event outcomes such as mortality is a fundamental task in clinical decision-making, commonly addressed through survival analysis. While classical statistical and deep learning approaches have been widely studied, they typically require task-specific training and sufficient labeled data. Recent advances in tabular foundation models offer a new paradigm by learning general-purpose representations for structured data. However, their applicability to censored time-to-event prediction in clinical settings remains underexplored, as typical applications are restricted to discrete classification rather than survival analysis tasks. In this work, we propose a lightweight adaptation approach for applying tabular foundation models to clinical survival analysis by directly training a survival-aware head on top of the pretrained representations. We study representative architectures, including TabPFN, TabDPT, and TabICL, and adapt them using a multi-task logistic regression (MTLR) head to model right-censored time-to-event outcomes. We evaluate this approach on a diverse set of public survival benchmarks and two large-scale ICU cohorts, MIMIC-IV and eICU. Our results show that this transfer learning approach achieves competitive or superior performance compared to strong baselines. On MIMIC-IV, TabDPT-FT-MTLR reaches a C-index of 0.856, corresponding to a relative improvement of +1.4% over the best non-FM baseline (DeepSurv, 0.844) and +6.7% over the best zero-shot model (0.802). On eICU, TabICL-FT-MTLR achieves 0.797, yielding gains of +1.7% (DeepSurv, 0.784) and +6.4% (0.749), respectively. These findings highlight the importance of combining pretrained tabular representations with survival-aware objectives and suggest that tabular foundation models provide a practical and effective alternative for clinical survival prediction.