Automatic de-identification of textual documents in the electronic health record: a review of recent research.
Automatic de-identification of textual documents in the electronic health record: a review of recent research.
复制标题
DOI：
10.1186/1471-2288-10-70
复制
发表时间：
2010-08-02
影响因子：
4
通讯作者：
Samore MH
中科院分区：
文献类型：
--
作者：
Meystre SM;Friedlin FJ;South BR;Shen S;Samore MH
在美国，《健康保险流通与责任法案》（Health Insurance Portability and Accountability Act，HIPAA）保护患者数据的机密性，并要求患者知情同意和内部审查委员会批准将数据用于研究目的，但如果数据被去识别，这些要求可以免除。对于被认为是去识别的临床数据，HIPAA“安全港”技术要求删除18个数据元素（称为PHI：受保护的健康信息）。叙述性文本文件的去识别化通常是手动实现的，并且需要大量资源。意识到这些问题，一些作者已经调查了自动去识别的叙述性文本文件从电子健康记录，并在此领域的最新研究综述。这篇综述集中于最近发表的研究（1995年以后），包括PubMed中的书目查询、会议记录、ACM数字图书馆以及已收录论文中引用的有趣出版物的相关出版物。文献检索返回了200多篇出版物。大多数仅关注结构化数据去识别，而不是叙述性文本、图像去识别或描述的手动去识别，因此被排除在外。最后，选择了18篇描述自动文本去识别的出版物，对所使用的架构和方法、检测和删除的PHI类型、使用的外部资源以及目标临床文档类型进行详细分析。所有文本去识别系统都旨在识别和删除人名，许多系统还包括其他类型的PHI。大多数系统只使用一种或两种特定的临床文档类型，并且主要基于两组不同的方法：模式匹配和机器学习。许多系统针对不同类型的PHI结合了这两种方法，但大多数系统仅依赖于模式匹配、规则和字典。一般来说，基于字典的方法在临床文本中很少提到的PHI中表现得更好，但更难以推广。基于机器学习的方法往往表现更好，特别是使用所使用的字典中没有提到的PHI。最后，在本出版物中讨论了匿名化、足够的性能和“过度擦洗”的问题。
In the United States, the Health Insurance Portability and Accountability Act (HIPAA) protects the confidentiality of patient data and requires the informed consent of the patient and approval of the Internal Review Board to use data for research purposes, but these requirements can be waived if data is de-identified. For clinical data to be considered de-identified, the HIPAA "Safe Harbor" technique requires 18 data elements (called PHI: Protected Health Information) to be removed. The de-identification of narrative text documents is often realized manually, and requires significant resources. Well aware of these issues, several authors have investigated automated de-identification of narrative text documents from the electronic health record, and a review of recent research in this domain is presented here. This review focuses on recently published research (after 1995), and includes relevant publications from bibliographic queries in PubMed, conference proceedings, the ACM Digital Library, and interesting publications referenced in already included papers. The literature search returned more than 200 publications. The majority focused only on structured data de-identification instead of narrative text, on image de-identification, or described manual de-identification, and were therefore excluded. Finally, 18 publications describing automated text de-identification were selected for detailed analysis of the architecture and methods used, the types of PHI detected and removed, the external resources used, and the types of clinical documents targeted. All text de-identification systems aimed to identify and remove person names, and many included other types of PHI. Most systems used only one or two specific clinical document types, and were mostly based on two different groups of methodologies: pattern matching and machine learning. Many systems combined both approaches for different types of PHI, but the majority relied only on pattern matching, rules, and dictionaries. In general, methods based on dictionaries performed better with PHI that is rarely mentioned in clinical text, but are more difficult to generalize. Methods based on machine learning tend to perform better, especially with PHI that is not mentioned in the dictionaries used. Finally, the issues of anonymization, sufficient performance, and "over-scrubbing" are discussed in this publication.
登录
查看更多内容
DOI：
10.1197/jamia.m2408
发表时间：
2008-01-01
影响因子：
6.4
作者：
Uzuner, Oezlem;Goldstein, Ira;Kohane, Isaac
通讯作者：
Kohane, Isaac
影响因子：
3.5
作者：
Neamatullah, Ishna;Douglass, Margaret M.;Clifford, Gari D.
通讯作者：
Clifford, Gari D.
DOI：
10.1197/jamia.m2444
发表时间：
2007-09-01
影响因子：
6.4
作者：
Uzuner, Oezlem;Luo, Yuan;Szolovits, Peter
通讯作者：
Szolovits, Peter
影响因子：
3.5
作者：
Gupta, D;Saul, M;Gilbertson, J
通讯作者：
Gilbertson, J
影响因子：
7.5
作者：
Uzuner, Oezlem;Sibanda, Tawanda C.;Szovits, Peter
通讯作者：
Szovits, Peter