使用语义词典对医学文档进行匿名化处理。
Medical document anonymization with a semantic lexicon.
作者信息
Ruch P, Baud R H, Rassinoux A M, Bouillon P, Robert G
机构信息
Medical Informatics Division, University Hospital of Geneva, ISSCO, University of Geneva.
出版信息
Proc AMIA Symp. 2000:729-33.
Abstract
We present an original system for locating and removing personally-identifying information in patient records. In this experiment, anonymization is seen as a particular case of knowledge extraction. We use natural language processing tools provided by the MEDTAG framework: a semantic lexicon specialized in medicine, and a toolkit for word-sense and morpho-syntactic tagging. The system finds 98-99% of all personally-identifying information.
摘要
我们提出了一个用于在患者记录中定位和去除个人身份识别信息的原创系统。在这个实验中，匿名化被视为知识提取的一个特殊情况。我们使用MEDTAG框架提供的自然语言处理工具：一个专门用于医学的语义词典，以及一个用于词义和形态句法标注的工具包。该系统能找到所有个人身份识别信息的98 - 99%。
相似文献
1
Medical document anonymization with a semantic lexicon.使用语义词典对医学文档进行匿名化处理。
Proc AMIA Symp. 2000:729-33.
2
A semantic lexicon for medical language processing.用于医学语言处理的语义词典。
J Am Med Inform Assoc. 1999 May-Jun;6(3):205-18. doi: 10.1136/jamia.1999.0060205.
3
Morpho-semantic parsing of medical expressions.医学表达式的形态语义解析
Proc AMIA Symp. 1998:760-4.
4
A natural language understanding system combining syntactic and semantic techniques.一个结合了句法和语义技术的自然语言理解系统。
Proc Annu Symp Comput Appl Med Care. 1994:247-51.
5
MEDTAG: tag-like semantics for medical document indexing.MEDTAG：用于医学文档索引的类标签语义。
Proc AMIA Symp. 1999:137-41.
6
Experience with a mixed semantic/syntactic parser.使用混合语义/句法解析器的经验。
Proc Annu Symp Comput Appl Med Care. 1995:284-8.
7
Towards a multilingual medical lexicon.迈向多语言医学词汇表。
AMIA Annu Symp Proc. 2006;2006:534-8.
8
Replacing personally-identifying information in medical records, the Scrub system.Scrub系统：替换病历中的个人身份识别信息。
Proc AMIA Annu Fall Symp. 1996:333-7.
9
Semantic standards for the representation of medical records.医疗记录表示的语义标准。
Med Decis Making. 1991 Oct-Dec;11(4 Suppl):S76-80.
10
引用本文的文献
1
2
Examining the Generalizability of Pretrained De-identification Transformer Models on Narrative Nursing Notes.考察预训练去识别变换模型在叙事护理记录上的泛化能力。
Appl Clin Inform. 2024 Mar;15(2):357-367. doi: 10.1055/a-2282-4340. Epub 2024 Mar 6.
3
De-identification of free text data containing personal health information: a scoping review of reviews.去标识化包含个人健康信息的自由文本数据：综述的综述。
Int J Popul Data Sci. 2023 Dec 12;8(1):2153. doi: 10.23889/ijpds.v8i1.2153. eCollection 2023.
4
Man vs the machine in the struggle for effective text anonymisation in the age of large language models.在大语言模型时代，为实现有效的文本匿名化，人与机器展开激烈竞争。
Sci Rep. 2023 Sep 25;13(1):16026. doi: 10.1038/s41598-023-42977-3.
5
Report of the Medical Image De-Identification (MIDI) Task Group -- Best Practices and Recommendations.医学图像去识别化（MIDI）任务组报告——最佳实践与建议
ArXiv. 2025 Mar 16:arXiv:2303.10473v3.
6
Building a best-in-class automated de-identification tool for electronic health records through ensemble learning.通过集成学习构建用于电子健康记录的一流自动去识别工具。
Patterns (N Y). 2021 May 12;2(6):100255. doi: 10.1016/j.patter.2021.100255. eCollection 2021 Jun 11.
7
CAS: corpus of clinical cases in French.法语临床病例语料库。
J Biomed Semantics. 2020 Aug 6;11(1):7. doi: 10.1186/s13326-020-00225-x.
8
Leveraging existing corpora for de-identification of psychiatric notes using domain adaptation.利用现有语料库，通过领域自适应对精神科病历进行去识别化处理。
AMIA Annu Symp Proc. 2018 Apr 16;2017:1070-1079. eCollection 2017.
9
Leveraging text skeleton for de-identification of electronic medical records.利用文本骨架对电子病历进行去识别化。
BMC Med Inform Decis Mak. 2018 Mar 22;18(Suppl 1):18. doi: 10.1186/s12911-018-0598-6.
10
A hybrid approach to automatic de-identification of psychiatric notes.一种混合方法，用于自动识别精神科病历中的身份信息。
J Biomed Inform. 2017 Nov;75S:S19-S27. doi: 10.1016/j.jbi.2017.06.006. Epub 2017 Jun 7.
本文引用的文献
1
MEDTAG: tag-like semantics for medical document indexing.MEDTAG：用于医学文档索引的类标签语义。
Proc AMIA Symp. 1999:137-41.
Zotero 插件