A De-identification method for bilingual clinical texts of various note types.

De-identification of personal health information is essential in order not to require written patient informed consent. Previous de-identification methods were proposed using natural language processing technology in order to remove the identifiers in clinical narrative text, although these methods only focused on narrative text written in English. In this study, we propose a regular expression-based de-identification method used to address bilingual clinical records written in Korean and English. To develop and validate regular expression rules, we obtained training and validation datasets composed of 6,039 clinical notes of 20 types and 5,000 notes of 33 types, respectively. Fifteen regular expression rules were constructed using the development dataset and those rules achieved 99.87% precision and 96.25% recall for the validation dataset. Our de-identification method successfully removed the identifiers in diverse types of bilingual clinical narrative texts. This method will thus assist physicians to more easily perform retrospective research.

Establishing the role of honest broker: bridging the gap between protecting personal health data and clinical research efficiency.

Background. The objective of this study is to propose the four conditions for the roles of honest brokers through a review of literature published by ten institutions that are successfully utilizing honest brokers. Furthermore, the study aims to examine whether the Asan Medical Center's (AMC) honest brokers satisfy the four conditions, and examine the need to enhance their roles. Methods. We analyzed the roles, tasks, and types of honest brokers at 10 organizations by reviewing the literature. We also established a Task Force (TF) in our institution for setting the roles and processes of the honest broker system and the honest brokers. The findings of the literature search were compared with the existing systems at AMC-which introduced the honest broker system for the first time in Korea. Results. Only one organization employed an honest broker for validating anonymized clinical data and monitoring the anonymity verifications of the honest broker system. Six organizations complied with HIPAA privacy regulations, while four organizations did not disclose compliance. By comparing functions with those of the AMC, the following four main characteristics of honest brokers were determined: (1) de-identification of clinical data; (2) independence; (3) checking that the data are used only for purposes approved by the IRB; and (4) provision of de-identified data to researchers. These roles were then compared with those of honest brokers at the AMC. Discussion. First, guidelines that regulate the definitions, purposes, roles, and requirements for honest brokers are needed, since there are no currently existing regulations. Second, Korean clinical research institutions and national regulatory departments need to reach a consensus on a Korean version of Limited Data Sets (LDS), since there are no lists that describe the use of personal identification information. Lastly, satisfaction surveys on honest brokers by researchers are necessary to improve the quality of honest brokers.

Experience of de-identification system development for clinical research in tertiary hospital.

To protect patients' privacy and to improve the convenience of research, Asan Medical Center (AMC) has been developing a de-identification system for biomedical research, which mainly consists of three components: de-identification tool, search tool, and chart review tool. The de-identification tool can substitute a randomly assigned research ID for a hospital patient ID, remove the identifiers in the structured format, and mask them in the unstructured format, i.e., texts. The search tool can find the number of patients which satisfies given criteria. The chart review tool can provide de-identified patient's clinical data for review. We found that clinical data warehouse was essential for successful implementation of de-identification system, and this system should be tightly linked to an electronic institutional review board system for easy operation of honest brokers.

Lessons Learned from Development of De-identification System for Biomedical Research in a Korean Tertiary Hospital.

OBJECTIVES: The Korean government has enacted two laws, namely, the Personal Information Protection Act and the Bioethics and Safety Act to prevent the unauthorized use of medical information. To protect patients' privacy by complying with governmental regulations and improve the convenience of research, Asan Medical Center has been developing a de-identification system for biomedical research. METHODS: We reviewed Korean regulations to define the scope of the de-identification methods and well-known previous biomedical research platforms to extract the functionalities of the systems. Based on these review results, we implemented necessary programs based on the Asan Medical Center Information System framework which was built using the Microsoft. NET Framework and C#. RESULTS: The developed de-identification system comprises three main components: a de-identification tool, a search tool, and a chart review tool. The de-identification tool can substitute a randomly assigned research ID for a hospital patient ID, remove the identifiers in the structured format, and mask them in the unstructured format, i.e., texts. This tool achieved 98.14% precision and 97.39% recall for 6,520 clinical notes. The search tool can find the number of patients which satisfies given search criteria. The chart review tool can provide de-identified patient's clinical data for review purposes. CONCLUSIONS: We found that a clinical data warehouse was essential for successful implementation of the de-identification system, and this system should be tightly linked to an electronic Institutional Review Board system for easy operation of honest brokers. Additionally, we found that a secure cloud environment could be adopted to protect patients' privacy more thoroughly.