生存预测中用于表格基础模型的删失感知目标接口
SurvFM enables tabular foundation models for right-censored survival prediction
浏览论文内容
中文总结 AI 辅助
研究针对表格患者数据事件发生时间预测中右删失问题，提出SurvFM-RMST框架，将生存结果转换为伪观察目标用于RMST回归，在模拟和多数据集测试中表现良好，支持其作为删失生存数据与表格基础模型预测的接口。
中文摘要 AI 辅助
从表格患者数据进行事件发生时间预测对于预后和生物医学决策支持至关重要，但右删失随访阻碍了普通回归标签的直接使用。表格基础模型为适度异构数据集提供了可重复使用的预测机制，但其通常假设结果是完全观察到的。我们引入了SurvFM-RMST，这是一个删失感知目标接口框架，它将生存结果转换为受限平均生存时间的留一法伪观察目标，使多个表格主干能够在无需特定于生存的微调情况下执行特定时间范围的RMST回归。在具有已知条件RMST的受控模拟中，SurvFM-RMST准确恢复了受限无事件时间，且伪RMST目标优于朴素的受限观察时间和仅事件目标。在36个符合条件的静态SurvSet数据集上，SurvFM主干与既定的生存和RMST回归比较器具有竞争力，尽管相对性能因终点、时间范围和实际约束而异。预测的RMST进一步将留出的患者分层为具有有序观察到的无事件时间和事件富集的组。总体而言，结果支持伪RMST目标构建作为删失生存数据和表格基础模型预测之间的可移植接口。
英文摘要
General-purpose tabular foundation models can be adapted across prediction tasks, but right censoring leaves many event times unknown and prevents their direct use as regression labels. SurvFM converts censored follow-up into observation-level targets for restricted mean survival time (RMST), the expected event-free time accumulated up to a chosen horizon. These targets allow multiple tabular foundation models to predict RMST without architectural modification. In simulations with known RMST, SurvFM achieved leading RMST accuracy and competitive discrimination across heterogeneous settings. Its targets were more accurate than simpler outcome constructions, with larger gains as censoring increased. Across 55 public datasets, SurvFM models remained in the leading performance band under full and restricted training. Models fitted in either of two public myelodysplastic syndrome cohorts retained competitive performance in the other without refitting. SurvFM separates censoring handling from prediction architecture, allowing advances in general-purpose tabular prediction to enter survival analysis without model-specific redesign.
发表机构
- The University of Texas MD Anderson Cancer Center（德克萨斯大学安德森癌症中心）
机构由 AI 辅助整理，请以论文原文为准。
