Development and Validation of a Natural Language Processing Algorithm to Pseudonymize Documents in the Context of a Clinical Data Warehouse.

IF 1.3 4区医学 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS

Methods of Information in Medicine Pub Date : 2024-05-01 Epub Date: 2024-03-05 DOI:10.1055/s-0044-1778693

Xavier Tannier, Perceval Wajsbürt, Alice Calliger, Basile Dura, Alexandre Mouchet, Martin Hilka, Romain Bey

{"title":"Development and Validation of a Natural Language Processing Algorithm to Pseudonymize Documents in the Context of a Clinical Data Warehouse.","authors":"Xavier Tannier, Perceval Wajsbürt, Alice Calliger, Basile Dura, Alexandre Mouchet, Martin Hilka, Romain Bey","doi":"10.1055/s-0044-1778693","DOIUrl":null,"url":null,"abstract":"Objective: The objective of this study is to address the critical issue of deidentification of clinical reports to allow access to data for research purposes, while ensuring patient privacy. The study highlights the difficulties faced in sharing tools and resources in this domain and presents the experience of the Greater Paris University Hospitals (AP-HP for Assistance Publique-Hôpitaux de Paris) in implementing a systematic pseudonymization of text documents from its Clinical Data Warehouse.Methods: We annotated a corpus of clinical documents according to 12 types of identifying entities and built a hybrid system, merging the results of a deep learning model as well as manual rules.Results and discussion: Our results show an overall performance of 0.99 of F1-score. We discuss implementation choices and present experiments to better understand the effort involved in such a task, including dataset size, document types, language models, or rule addition. We share guidelines and code under a 3-Clause BSD license.","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":" ","pages":"21-34"},"PeriodicalIF":1.3000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11495938/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Methods of Information in Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1055/s-0044-1778693","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/5 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: The objective of this study is to address the critical issue of deidentification of clinical reports to allow access to data for research purposes, while ensuring patient privacy. The study highlights the difficulties faced in sharing tools and resources in this domain and presents the experience of the Greater Paris University Hospitals (AP-HP for Assistance Publique-Hôpitaux de Paris) in implementing a systematic pseudonymization of text documents from its Clinical Data Warehouse.

Methods: We annotated a corpus of clinical documents according to 12 types of identifying entities and built a hybrid system, merging the results of a deep learning model as well as manual rules.

Results and discussion: Our results show an overall performance of 0.99 of F1-score. We discuss implementation choices and present experiments to better understand the effort involved in such a task, including dataset size, document types, language models, or rule addition. We share guidelines and code under a 3-Clause BSD license.

查看原文本刊更多论文

开发和验证自然语言处理算法，在临床数据仓库中对文档进行匿名化处理。

研究目的本研究旨在解决临床报告去标识化这一关键问题，以便在确保患者隐私的前提下为研究目的获取数据。研究强调了在这一领域共享工具和资源所面临的困难，并介绍了大巴黎大学医院（AP-HP，即巴黎公立医院协会）在对其临床数据仓库中的文本文档进行系统化匿名处理方面的经验：方法：我们根据 12 种识别实体对临床文件语料库进行了注释，并建立了一个混合系统，将深度学习模型和人工规则的结果合并在一起：我们的结果显示，F1-score 的总体性能为 0.99。我们讨论了实施选择，并通过实验更好地理解了此类任务所涉及的工作，包括数据集大小、文档类型、语言模型或规则添加。我们在 3 条款 BSD 许可下共享指南和代码。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Methods of Information in Medicine 医学-计算机：信息系统

CiteScore

3.70

自引率

11.80%

发文量

审稿时长

6-12 weeks

期刊介绍： Good medicine and good healthcare demand good information. Since the journal''s founding in 1962, Methods of Information in Medicine has stressed the methodology and scientific fundamentals of organizing, representing and analyzing data, information and knowledge in biomedicine and health care. Covering publications in the fields of biomedical and health informatics, medical biometry, and epidemiology, the journal publishes original papers, reviews, reports, opinion papers, editorials, and letters to the editor. From time to time, the journal publishes articles on particular focus themes as part of a journal''s issue.