Subscribe to RSS
DOI: 10.1055/a-1910-4154
Real-World Matching Performance of Deidentified Record-Linking Tokens
Funding This work was supported in part by the National Center for Advancing Translational Sciences (NCATS) under awards UL1TR003167 and U01TR002393; the Cancer Prevention and Research Institute of Texas (CPRIT), under award RP170668, Datavant, Inc., and the Reynolds and Reynolds Professorship in Clinical Informatics.
Abstract
Objective Our objective was to evaluate tokens commonly used by clinical research consortia to aggregate clinical data across institutions.
Methods This study compares tokens alone and token-based matching algorithms against manual annotation for 20,002 record pairs extracted from the University of Texas Houston's clinical data warehouse (CDW) in terms of entity resolution.
Results The highest precision achieved was 99.9% with a token derived from the first name, last name, gender, and date-of-birth. The highest recall achieved was 95.5% with an algorithm involving tokens that reflected combinations of first name, last name, gender, date-of-birth, and social security number.
Discussion To protect the privacy of patient data, information must be removed from a health care dataset to obscure the identity of individuals from which that data were derived. However, once identifying information is removed, records can no longer be linked to the same entity to enable analyses. Tokens are a mechanism to convert patient identifying information into Health Insurance Portability and Accountability Act-compliant deidentified elements that can be used to link clinical records, while preserving patient privacy.
Conclusion Depending on the availability and accuracy of the underlying data, tokens are able to resolve and link entities at a high level of precision and recall for real-world data derived from a CDW.
Protection of Human and Animal Subjects
This study has been approved by the Committee for the Protection of Human Subjects (the UTHSC-H IRB) under protocol HSC-SBMI-13–0549.
Author Contributions
R.J.A. and A.Y. wrote the initial manuscript. R.J.A., D.C., A.Y., A.C., and T.L. performed the data analysis. J.L. and J.L. revised the manuscript. E.V.B. provided the data. All authors reviewed and approved the manuscript prior to submission.
Data Availability Statement
The data underlying this article cannot be shared publicly due to the fact that these data are individually identifiable and represent real-world patients.
Publication History
Received: 12 July 2022
Accepted: 22 July 2022
Accepted Manuscript online:
27 July 2022
Article published online:
14 September 2022
© 2022. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
-
References
- 1 Fellegi IP, Sunter AB. A theory for record linkage. J Am Stat Assoc 1969; 64 (328) 1183-1210
- 2 Bian J, Loiacono A, Sura A. et al. Implementing a hash-based privacy-preserving record linkage tool in the OneFlorida clinical research network. JAMIA Open 2019; 2 (04) 562-569
- 3 Stausberg J, Waldenburger A, Borgs C, Schnell R. Combining different privacy-preserving record linkage methods for hospital admission data. Stud Health Technol Inform 2017; 235: 161-165
- 4 Nguyen L, Stoové M, Boyle D. et al. Privacy-preserving record linkage of deidentified records within a public health surveillance system: evaluation study. J Med Internet Res 2020; 22 (06) e16757
- 5 Joffe E, Byrne MJ, Reeder P. et al. A benchmark comparison of deterministic and probabilistic methods for defining manual review datasets in duplicate records reconciliation. J Am Med Inform Assoc 2014; 21 (01) 97-104
- 6 Baxter R, Christen P, Churches T. A Comparison of Fast Blocking Methods for Record Linkage. In: Kdd 2003 Workshops.; 2003: 25-27
-
7 Soundex System|The Soundex Indexing System. Published online 2007. Accessed July 16, 2021 at: https://www.archives.gov/research/census/soundex
- 8 Campbell KM, Deck D, Krupski A. Record linkage software in the public domain: a comparison of Link Plus, The Link King, and a 'basic' deterministic algorithm. Health Informatics J 2008; 14 (01) 5-15
-
9
Penard W,
van Werkhoven T.
On the secure hash algorithm family. In: Cryptography in Context.; 2008:1–18. Accessed July 16, 2021 at: https://web.archive.org/web/20160330153520/http://www.staff.science.uu.nl/~werkh108/docs/study/Y5_07_08/infocry/project/Cryp08.pdf
-
10
Announcing the ADVANCED ENCRYPTION STANDARD (AES).
Published online November 26, 2001. Accessed July 16, 2021 at: https://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.197.pdf
- 11 Budiman A, Ruiz NG. Asian Americans are the fastest-growing racial or ethnic group in the U.S. Pew Research Center. Accessed June 28, 2022 at: https://www.pewresearch.org/fact-tank/2021/04/09/asian-americans-are-the-fastest-growing-racial-or-ethnic-group-in-the-u-s/
- 12 Palloni A, Arias E. Paradox lost: explaining the Hispanic adult mortality advantage. Demography 2004; 41 (03) 385-415
- 13 Lariscy JT. Differential record linkage by Hispanic ethnicity and age in linked mortality studies: implications for the epidemiologic paradox. J Aging Health 2011; 23 (08) 1263-1284
- 14 Irvine K, Smith M, de Vos R. et al. Real world performance of privacy preserving record linkage. Int J Popul Data Sci 2018; 3 (04) DOI: 10.23889/ijpds.v3i4.990.
- 15 Brown AP, Borgs C, Randall SM, Schnell R. Evaluating privacy-preserving record linkage using cryptographic long-term keys and multibit trees on large medical datasets. BMC Med Inform Decis Mak 2017; 17 (01) 83
- 16 Houston Still Most Diverse City in the Nation. Report Finds. Accessed July 16, 2021 at: https://www.houston.org/news/houston-still-most-diverse-city-nation-report-finds