Perfectly Secure and Efficient Two-Party Electronic-Health-Record Linkage

Feng Chen; Xiaoqian Jiang; Shuang Wang; Lisa M Schilling; Daniella Meeker; Toan Ong; Michael E Matheny; Jason N Doctor; Lucila Ohno-Machado; Jaideep Vaidya

doi:10.1109/MIC.2018.112102542

Perfectly Secure and Efficient Two-Party Electronic-Health-Record Linkage

IEEE Internet Comput. 2018 Mar-Apr;22(2):32-41. doi: 10.1109/MIC.2018.112102542. Epub 2018 Jan 16.

Authors

Affiliations

¹ Health System Department of Biomedical Informatics, UC San Diego, La Jolla, CA, 92093.
² Department of Medicine, University of Colorado, Anschutz Medical Campus, CO, 80045.
³ Keck School of Medicine, University of Southern California, Los Angeles, CA 90089.
⁴ Geriatric Research Education and Clinical Care Service, Tennessee Valley Healthcare System VA, Nashville, TN 37212.
⁵ Departments of Biomedical Informatics, Medicine, and Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37235.
⁶ Schaeffer Center for Health Policy & Economics, University of Southern California, Los Angeles, CA 90033.
⁷ Management Science & Information Systems Department, Rutgers University, Newark, NJ 07102.

Abstract

Patient health data are often found spread across various sources. However, precision medicine and personalized care requires access to the complete medical records. The first step towards this is to enable the linkage of health records spread across different sites. Existing record linkage solutions assume that data is centralized with no privacy/security concerns restricting sharing. However, that is often untrue. Therefore, we design and implement a portable method for privacy-preserving record linkage based on garbled circuits to accurately and securely match records. We also develop a novel approximate matching mechanism that significantly improves efficiency.

Keywords: EHR linkage; Garbled circuit; Privacy preserving; Secure multi-party computation.

Abstract

Grants and funding