arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07348cs.LG
收藏

在系统分布偏移下学习临床表示

Learning Clinical Representations Under Systematic Distribution Shift

University of the Chinese Academy of Sciences（中国科学院大学）；Columbia University（哥伦比亚大学）

Yuanyun Zhang, Shi Li

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了一种实践不变的多模态临床预测框架，通过联合优化预测性能与抑制环境信息，提升模型在分布外情况下的鲁棒性和可转移性。

摘要：

临床机器学习模型越来越多地使用大规模、多模态基础范式进行训练，但部署环境往往系统性地与训练时使用的数据生成设置不同。这种偏移源于异质的测量政策、文档实践和机构工作流程，导致生理信号与特定实践的伪影之间出现表示纠缠。在本工作中，我们提出了一种多模态临床预测的实践不变表示学习框架。我们将临床观察建模为源自潜在生理因素和环境依赖过程，并引入一个目标，联合优化预测性能同时抑制嵌入中环境预测信息。具体来说，我们结合了监督风险最小化与对抗性环境正则化以及跨医院的不变风险惩罚。在多个纵向电子健康记录预测任务和跨机构评估中，我们的方法相对于屏蔽预训练和标准监督基线，将分布外AUROC提高了2到3个点，同时保持分布内性能并提高校准。这些结果表明，显式考虑系统分布偏移期间的表示学习能够产生更加稳健和可转移的临床模型，突显了结构不变性与架构规模在医疗AI中的重要性。

英文摘要：

Clinical machine learning models are increasingly trained using large scale, multimodal foundation paradigms, yet deployment environments often differ systematically from the data generating settings used during training. Such shifts arise from heterogeneous measurement policies, documentation practices, and institutional workflows, leading to representation entanglement between physiologic signal and practice specific artifacts. In this work, we propose a practice invariant representation learning framework for multimodal clinical prediction. We model clinical observations as arising from latent physiologic factors and environment dependent processes, and introduce an objective that jointly optimizes predictive performance while suppressing environment predictive information in the learned embedding. Concretely, we combine supervised risk minimization with adversarial environment regularization and invariant risk penalties across hospitals. Across multiple longitudinal EHR prediction tasks and cross institution evaluations, our method improves out of distribution AUROC by up to 2 to 3 points relative to masked pretraining and standard supervised baselines, while maintaining in distribution performance and improving calibration. These results demonstrate that explicitly accounting for systematic distribution shift during representation learning yields more robust and transferable clinical models, highlighting the importance of structural invariance alongside architectural scale in healthcare AI.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑