Healthc Inform Res.  2013 Jun;19(2):102-109. 10.4258/hir.2013.19.2.102.

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

• Shin SY
• Lyu Y
• Shin Y
• Choi HJ
• Park J
• Kim WS
• Lee JH

• KMID: 2229491
• DOI: http://doi.org/10.4258/hir.2013.19.2.102

Abstract

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.

Keyword

Access to Information; Information Systems; Research Design; Research Ethics; Biomedical Research

MeSH Terms

Access to Information
Bioethics
Computer Security
Electronics
Electrons
Ethics Committees, Research
Ethics, Research
Humans
Information Systems
Jurisprudence
Masks
Privacy
Research Design
Social Control, Formal
Tertiary Care Centers

Figure

• 

  Figure 1 Diagram of Asan Medical Center de-identification system. EMR: Electronic Medical Record, COPE: computerized physician order entry, LIS: laboratory information system, CDW: clinical data warehouse, IRB: International Review Board, eCRF: electronic case report form, DB: database.

• 

  Figure 2 Overall system architecture of Asan Medical Center (AMC) biomedical research platform. ICD: International Classification of Diseases.

• 

  Figure 3 Flowchart for generating Research ID.

• 

  Figure 4 The PHIs such as two phone numbers are masked with asterisks in the outpatient progress note.

• 

  Figure 5 User interface of search tool. In the left panel, user can choose the search criteria such as medication, order, lab results, and diagnosis. User can set the detailed search parameter in the upper right panel. In this figure, user searched the total number of outpatients in October 9, 2012. The lower right panel shows the search results.

• 

  Figure 6 User interface of chart review tool. (A) Diagnosis & medication, (B) lab results, (C) radiology & pathology reports, and (D) operative reports.

Reference

1. Office for Civil Rights. Guidance regarding methods for de-identification of protected health information in accordance with the Health Insurance Portability and Accountability Act (HIPAA) privacy rule [Internet]. Washington (DC): US Department of Health & Human Service;c2013. cited at 2013 Mar 28. Available from: http://www.hhs.gov/ocr/privacy/hipaa/understanding/coveredentities/De-identification/hhs_deid_guidance.pdf.

2. Korea Ministry of Government Legislation. The Personal Information Protection Act [Internet]. Seoul, Korea: Korea Ministry of Government Legislation;c2013. cited at 2013 Mar 28. Available from: http://www.law.go.kr/lsEfInfoP.do?lsiSeq=136728#0000.

3. Korea Ministry of Government Legislation. The Bioethics and Safety Act [Internet]. Seoul, Korea: Korea Ministry of Government Legislation;c2013. cited at 2013 Mar 28. Available from: http://www.law.go.kr/lsEfInfoP.do?lsiSeq=137037#0000.

4. Ryu HJ, Kim WS, Lee JH, Min SW, Kim SJ, Lee YS, et al. Asan medical information system for healthcare quality improvement. Healthc Inform Res. 2010; 16(3):191–197.

5. Lowe HJ, Ferris TA, Hernandez PM, Weber SC. STRIDE: an integrated standards-based translational research informatics platform. AMIA Annu Symp Proc. 2009; 2009:391–395.

6. Murphy SN, Weber G, Mendis M, Gainer V, Chueh HC, Churchill S, et al. Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2). J Am Med Inform Assoc. 2010; 17(2):124–130.

7. Nalichowski R, Keogh D, Chueh HC, Murphy SN. Calculating the benefits of a Research Patient Data Repository. AMIA Annu Symp Proc. 2006; 1044.

8. Stanford Center for Clinical Informatics, Stanford School of Medicine. Stanford Translational Research Integrated Database Environment (STRIDE) [Internet]. Stanford (CA): Stanford School of Medicine;c2013. cited at 2013 Mar 28. Available from: https://clinicalinformatics.stanford.edu/research/stride.html.

9. National Center for Biomedical Computing. Informatics for Integrating Biology & the Bedside [Internet]. Bethesda (MD): National Institutes of Health;c2013. cited at 2013 Mar 28. Available from: https://www.i2b2.org/.

10. Partners Healthcare. Research Patient Data Registry (RPDR) [Internet]. Boston (MA): Partners HealthCare;c2013. cited at 2013 March 28. Available from: http://rc.partners.org/rpdr.

11. El Emam K. Methods for the de-identification of electronic health records for genomic research. Genome Med. 2011; 3(4):25.

12. Fraser R, Willison D. Tools for de-identification of personal health information. [Toronto]: Pan Canadian Health Information Privacy Group;2009. cited at 2013 Apr 3. Available from: https://www.infoway-inforoute.ca/index.php/resources/video-gallery/doc_download/624-tools-for-de-identification-of-pseronal-health-information.

13. Meystre SM, Friedlin FJ, South BR, Shen S, Samore MH. Automatic de-identification of textual documents in the electronic health record: a review of recent research. BMC Med Res Methodol. 2010; 10:70.

14. Deleger L, Molnar K, Savova G, Xia F, Lingren T, Li Q, et al. Large-scale evaluation of automated clinical note de-identification and its impact on information extraction. J Am Med Inform Assoc. 2013; 20(1):84–94.

15. Shin SY, Shin Y, Choi HJ, Park J, Lyu LM, Kim WS, et al. Deidentification method for bilingual EMR free texts. In : Proceedings of the 14th World Congress on Medical and Health Informatics; 2013 Aug 20-23; Copenhagen, Denmark.

16. El Emam K. Heuristics for de-identifying health data. IEEE Secur Priv. 2008; 6(4):58–61.

17. El Emam K, Dankar FK, Issa R, Jonker E, Amyot D, Cogo E, et al. A globally optimal k-anonymity method for the de-identification of health data. J Am Med Inform Assoc. 2009; 16(5):670–682.

18. Liu J, Erdal S, Silvey SA, Ding J, Riedel JD, Marsh CB, et al. Toward a fully de-identified biomedical information warehouse. AMIA Annu Symp Proc. 2009; 2009:370–374.