arXiv：cs.LG· Qingyang Zhang·· 7 小时前AI 评分34
用非对称监督对比学习实现跨国家医疗表征迁移
Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer
AI 导读
研究者提出 Asymmetric SupCon，一种面向任务特定预训练的非对称监督对比学习目标，避免将阴性结局轨迹相互拉近。该方法在台湾 NHIRD 的 398 万名患者纵向记录上预训练时序 Transformer 编码器，并迁移至美国 MIMIC-IV 与 EHRSHOT，在 MIMIC-IV 上持续优于随机初始化并缩小与域内预训练的差距。
正文
Abstract:Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and healthcare workflows differ substantially across institutions and countries. We introduce Asymmetric Supervised Contrastive Learning (Asymmetric SupCon), a task-specific pre-training objective motivated by the heterogeneity of negative clinical outcomes. The objective clusters patients sharing a target positive outcome without explicitly attracting negative trajectories toward one another. We pre-train temporal Transformer encoders on longitudinal records from 3.98 million patients in the Taiwanese National Health Insurance Research Database (NHIRD) and transfer them to two U.S. EHR datasets, MIMIC-IV and EHRSHOT. A hybrid semantic mapping pipeline combining direct mappings with embedding-based retrieval enables transfer across heterogeneous clinical vocabularies. On MIMIC-IV, NHIRD pre-training consistently improves over random initialization while substantially narrowing the performance gap to task-specific in-domain pre-training. On EHRSHOT, the transferred models show particularly strong few-shot performance for incident disease prediction. A controlled objective ablation under a matched pre-training scale shows that Asymmetric SupCon achieves higher mean AUPRC than direct supervised BCE transfer on all four evaluated tasks and Standard SupCon on three of four, with a 0.003 AUPRC deficit on readmission. These results support asymmetric contrastive pre-training as an effective approach for task-specific cross-national EHR representation transfer. Code is available at this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.04946 [cs.LG] |
| (or arXiv:2610.04946v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.04946 arXiv-issued DOI via DataCite |
Submission history
From: Qingyang Zhang [view email]
[v1]
Sun, 4 Oct 2026 04:39:58 UTC (26 KB)
[v2]
Tue, 6 Oct 2026 03:57:35 UTC (28 KB)
来源：arXiv：cs.LG · arxiv.org