arXiv：cs.LG（机器学习，全量分类）· Xinye Yang, Yuli Wang, Cheng Ting Lin, Harrison Bai·· 5 小时前AI 评分45
EHR2Trace：面向患者世界模型与临床智能体的可审计 EHR 数据基础设施
EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents
AI 导读
EHR2Trace 将不同来源的电子健康记录转换为可追溯的患者事件，用于患者世界模型与临床智能体的训练和评估。该系统在三个临床数据集上转换了 8.464 亿条事件，除 MIMIC-IV 上一项单位一致性检查外全部通过，并检测出全部 28 个注入故障。对照预测实验显示，把较晚的诊断归到入院时间会大幅虚高测量性能，且此类数据训练的模型在按信息可用性过滤的病史部署时精度下降。
正文
Abstract:Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires reliable histories of patient conditions, treatments, and the information available at each decision. Electronic health records (EHRs) contain these histories, but differences in how events are recorded make them difficult to use consistently. We present EHR2Trace, a system that converts EHRs from different sources into traceable patient events for model training and evaluation. It links events to source records, separates event time from information availability, and distinguishes medication orders, dispensing, and administration. A shared event representation supports both OMOP and MEDS exports, with automated validation and reproducible builds. Across three clinical datasets, EHR2Trace converted 846.4 million events, with every applicable check passing except one unit-consistency check on MIMIC-IV, and detected all 28 injected faults. A controlled prediction experiment showed that assigning later diagnoses to admission time substantially inflated measured performance, and that a model trained on such data lost accuracy when deployed on histories filtered by availability. EHR2Trace provides a reusable data foundation for patient world models and clinical agents, helping researchers inspect patient histories, check conversion decisions, and evaluate models with explicit data rules.
| Comments: | 13 pages, 3 figures, 6 tables. Code and experiment records: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Databases (cs.DB); Quantitative Methods (q-bio.QM) |
| ACM classes: | J.3; H.2.8; I.2.6 |
| Cite as: | arXiv:2609.38193 [cs.LG] |
| (or arXiv:2609.38193v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38193 arXiv-issued DOI via DataCite |
Submission history
From: Xinye Yang [view email]
[v1]
Fri, 18 Sep 2026 04:00:10 UTC (41 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org