发表机构
ADAPT Centre; Dublin City University; University of Bologna; University of Pisa; Institute of Clinical Physiology, CNR; School of Computing, Dublin City University（ADAPT中心; 都柏林城市大学; 博洛尼亚大学; 比萨大学; 意大利国家研究委员会临床生理学研究所; 都柏林城市大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对删失型事件时间预测任务，将表格基础模型（TabFMs）与CoxPH、DeepHit等连接并改进训练流程，在74个单风险和4个竞争风险数据集上验证了不同适配接口的性能，明确了TabFM迁移的影响因素。
AI 中文摘要
表格基础模型（Tabular foundation models, TabFMs）在结构化数据上表现出色，尤其在标准分类和回归任务中性能优异。然而，将其扩展至删失型事件时间预测任务颇具挑战，因为该任务需妥善处理删失与事件时间动态性。基于我们的前期工作，我们进一步将TabFMs与CoxPH、DeepHit相连接，并改进了上下文重采样训练流程。我们在74个单风险数据集上评估了时间零样本重表述、基于分类的微调以及使用冻结TabFM骨干的生存头适配方法，还额外研究了4个竞争风险数据集。零样本推理在较小的单风险数据集上效果显著，而随着数据集规模扩大，监督适配的优势愈发明显。Cox提供了最可靠的强适配接口，尤其在较大数据集上的综合布雷尔分数（Integrated Brier Score, IBS）表现突出；DeepHit在时间相关一致性指数上的表现相对优于IBS；在4个数据集的竞争风险分析中，特定原因多任务逻辑回归（cause-specific MTLR）在TabFM生存头中排名最高。随着数据集规模增长，分类微调与零样本推理的竞争力增强，但在概率预测方面仍较弱。总体而言，我们的结果表明，有效的TabFM迁移取决于数据场景及所选适配接口所代表的统计结构。本研究使用的实现脚本可在该https URL获取。
英文摘要
Tabular foundation models (TabFMs) achieve strong performance on structured data, particularly for standard classification and regression problems. Yet, extending them to censored time-to-event prediction is challenging because it requires properly handling censoring and event-time dynamics. Building on our prior work, we further link TabFMs with CoxPH and DeepHit and revise the context-resampled training procedure. We evaluate temporal zero-shot reformulation, classification-based fine-tuning, and survival-head adaptation using frozen TabFM backbones on 74 single-risk data sets, and we additionally study 4 competing-risk data sets. Zero-shot inference is effective on smaller single-risk data sets, whereas supervised adaptation becomes increasingly advantageous as data sets scale. Cox provides the most reliably strong interface, especially for Integrated Brier Score (IBS) on larger data sets. DeepHit is relatively stronger for the time-dependent Concordance Index than for IBS, while cause-specific MTLR ranks highest among the TabFM survival heads in the four-data-set competing-risk analysis. Classification fine-tuning becomes more competitive with zero-shot inference as data sets grow but remains weaker for probabilistic prediction. Overall, our results indicate that effective TabFM transfer depends on the data regime and on the statistical structure represented by the chosen adaptation interface. The implementation scripts used for this work are available at https://github.com/kaylode/survival-fm.
CommentsUnder Submission. Not peer-reviewed
