arXiv cs.AI· Jose D. Posada, Somalee Datta, Priya Desai·· 10 天前AI 评分37
TIDE 2.0：面向临床笔记键控去标识化的开源模型无关引擎
TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes
AI 导读
TIDE 2.0 是一款 MIT 许可的开源引擎，将临床笔记去标识化拆分为可替换的识别器与键控匿名化两个阶段，全部在机构自有硬件上运行。其默认配置在两个机构的人工标注语料上实现域内 span 级召回率 0.88、第二家机构语料 0.77，精确率分别为 0.88 和 0.87。引擎开源，识别器 TIDE2-Sentry 由大语言模型蒸馏而来，需通过受限研究用途协议获取。
正文 · 原文
Abstract:Clinical notes capture most of what is documented about a patient's care, but they cannot be used for research until protected health information (PHI) is removed. De-identification is often treated as a detection problem. Detection alone is not sufficient: redaction strips clinical content along with identifiers, date blanking destroys the temporal intervals needed for longitudinal analysis, and assigning a fresh random surrogate at each occurrence breaks links between a patient's notes. We present TIDE 2.0, an MIT-licensed engine with two separable stages: an interchangeable recognizer and a keyed anonymizer. Both run on hardware the institution owns. Surrogates are generated cryptographically with no stored linkage table. Dates shift by a per-patient, interval-preserving offset; each value receives the same surrogate across all occurrences under a given key; and a release produced under a new key cannot be linked to earlier releases. We also release TIDE2-Sentry, a recognizer distilled from a large language model. On two gold-annotated corpora from two institutions, the default configuration reached span-level recall of 0.88 in-domain and 0.77 on the second institution's corpus, at precision 0.88 and 0.87. We report recall and precision per category alongside these aggregates. The engine is open source, and the recognizer is available under a gated research-use agreement, so institutions can run, inspect and extend both within their own environments.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07224 [cs.CL] |
| (or arXiv:2610.07224v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07224 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jose D Posada [view email]
[v1]
Mon, 5 Oct 2026 18:31:40 UTC (460 KB)
来源：arXiv cs.AI · arxiv.org