Evaluation of a deidentification (De-Id) software engine to share pathology reports and clinical documents for research
Evaluation of a deidentification (De-Id) software engine to share pathology reports and clinical documents for research
复制标题
DOI：
10.1309/e6k33gbpe5c27fyu
复制
发表时间：
2004-02-01
影响因子：
3.5
通讯作者：
Gilbertson, J
中科院分区：
文献类型：
--
作者：
Gupta, D;Saul, M;Gilbertson, J
我们评估了匹兹堡大学医学中心（UPMC）的综合去识别引擎，该引擎使用一组复杂的规则，字典，模式匹配算法和统一医学语言系统来识别和替换临床报告中的识别文本，同时保留医学信息以供研究共享。在我们的967份手术病理报告的初始数据集中，该软件未抑制外部（103）、UPMC（47）和非UPMC（56）登录号;日期（7）;病例病理学家的姓名（9）或首字母缩写（25）;或医院或实验室名称（46）。在150份报告中，一些临床信息被无意中抑制（过度标记）。该引擎保留了患者姓名，例如巴雷特和格里森。在第二次评价（1000份报告）中，软件未抑制外部（90份）或UPMC（6份）登记号或病例病理学家的姓名（4份）或首字母缩写（2份）。在第三次评估中，该软件删除了患者、医院（2971300）、病理学家（2971300）、转录员、住院医生和医生的姓名、手术日期和登记号（2981300）。该系统可靠地和具体地去除了安全港标识符，并在不去除重要临床信息的情况下产生了高度可读的去识别文本。需要病理学领域专家和系统开发人员之间的合作以及持续的质量保证，以优化正在进行的去识别过程。
We evaluated a comprehensive deidentification engine at the University of Pittsburgh Medical Center (UPMC), Pittsburgh, PA, that uses a complex set of rules, dictionaries, pattern-matching algorithms, and the Unified Medical Language System to identify and replace identifying text in clinical reports while preserving medical information for sharing in research.In our initial data set of 967 surgical pathology reports, the software did not suppress outside (103), UPMC (47), and non-UPMC (56) accession numbers; dates (7); names (9) or initials (25) of case pathologists; or hospital or laboratory names (46). In 150 reports, some clinical information was suppressed inadvertently (overmarking). The engine retained eponymic patient names, e.g. Barrett and Gleason. In the second evaluation (1, 000 reports), the software did not suppress outside (90) or UPMC (6) accession numbers or names (4) or initials (2) of case pathologists. In the third evaluation, the software removed names of patients, hospitals (2971300), pathologists (2971300), transcriptionists, residents and physicians, dates of procedures, and accession numbers (2981300).By the end of the evaluation, the system was reliably and specifically removing safe-harbor identifiers and producing highly readable deidentified text without removing important clinical information. Collaboration between pathology domain experts and system developers and continuous quality assurance are needed to optimize ongoing deidentification processes.