Suchergebnisse

IntroductionAvailable and practical methods for privacy preserving linkage have shortcomings: methods utilising anonymous linkage codes provide limited accuracy while methods based on Bloom filters have proven vulnerable to frequency-based attacks.
ObjectivesIn this paper, we present and evaluate a novel protocol that aims to meld both the accuracy of the Bloom filter method with the privacy achievable through the anonymous linkage code methodology.
MethodsThe protocol involves creating multiple match-keys for each record, with the composition of each match-key depending on attributes of the underlying datasets being compared. The protocol was evaluated through de-duplication of four administrative datasets and two synthetic datasets; the 'answers' outlining which records belonged to the same individual were known for each dataset. The results were compared against results achieved with un-encoded linkage and other privacy preserving techniques on the same datasets.
ResultsThe multiple match-key protocol presented here achieved high quality across all datasets, performing better than record-level Bloom filters and the SLK, but worse than field-level Bloom filters.
ConclusionThe presented method provides high linkage quality while avoiding the frequency based attacks that have been demonstrated against the Bloom filter approach. The method appears promising for real world use.

Introduction The need for increased privacy protection in data linkage has driven the development of privacy-preserving record linkage (PPRL) techniques. A popular technique using Bloom filters with cryptographic analyses, modifications, and hashing variations to optimise privacy has been the focus of much research in this area. With few applications of Bloom filters within a probabilistic framework, there is limited information on whether approximate matches between Bloom filtered fields can improve linkage quality.
Objectives In this study, we evaluate the effectiveness of three approximate comparison methods for Bloom filters within the context of the Fellegi-Sunter model of recording linkage: Sørensen–Dice coefficient, Jaccard similarity and Hamming distance.
Methods Using synthetic datasets with introduced errors to simulate datasets with a range of data quality and a large real-world administrative health dataset, the research estimated partial weight curves for converting similarity scores (for each approximate comparison method) to partial weights at both field and dataset level. Deduplication linkages were run on each dataset using these partial weight curves. This was to compare the resulting quality of the approximate comparison techniques with linkages using simple cut-off similarity values and only exact matching.
Results Linkages using approximate comparisons produced significantly better quality results than those using exact comparisons only. Field level partial weight curves for a specific dataset produced the best quality results. The Sørensen-Dice coefficient and Jaccard similarity produced the most consistent results across a spectrum of synthetic and real-world datasets.
Conclusion The use of Bloom filter similarity comparisons for probabilistic record linkage can produce linkage quality results which are comparable to Jaro-Winkler string similarities with unencrypted linkages. Probabilistic linkages using Bloom filters benefit significantly from the use of similarity comparisons, with partial weight curves producing the best results, even when not optimised for that particular dataset.

Background: The statistical linkage key (SLK-581) is a common tool for record linkage in Australia, due to its ability to provide some privacy protection. However, newer privacy-preserving approaches may provide greater privacy protection, while allowing high-quality linkage. Objective: To evaluate the standard SLK-581, encrypted SLK-581 and a newer privacy-preserving approach using Bloom filters, in terms of both privacy and linkage quality. Method: Linkage quality was compared by conducting linkages on Australian health datasets using these three techniques and examining results. Privacy was compared qualitatively in relation to a series of scenarios where privacy breaches may occur. Results: The Bloom filter technique offered greater privacy protection and linkage quality compared to the SLK-based method commonly used in Australia. Conclusion: The adoption of new privacy-preserving methods would allow both greater confidence in research results, while significantly improving privacy protection.

The Centre for Data Linkage (CDL) was established at Curtin University, Western Australia, to develop infrastructure to enable cross-jurisdictional record linkage in Australia. The CDL's operating model makes use of the 'separation principle', with content data typically provided to researchers directly by the data custodian; jurisdictional linkage where available are used within the linkage process. Along with conducting record linkage, the team has also invested in establishing a research programme in record linkage methodology and in developing modern record linkage software which can handle the size and complexity of today's workloads. The Centre has been instrumental in the development of practical methods for privacy-preserving record linkage, with this methodology now regularly used for real-world linkages. While the promise of a nation-wide linkage system in Australia has yet to be met, distributed models provide a potential solution.

OBJECTIVE: To describe the challenges of obtaining state and nationally held data for linkage to a non-government national clinical registry. METHODS: We reviewed processes negotiated to achieve linkage between the Australian Stroke Clinical Registry (AuSCR), the National Death Index, and state held hospital data. Minutes from working group meetings, national workshop meetings, and documented communications with health department staff were reviewed and summarised. RESULTS: Time from first application to receipt of data was more than two years for most state data-sets. Several challenges were unique to linkages involving identifiable data from a non-government clinical registry. Concerns about consent, the re-identification of data, duality of data custodian roles and data ownership were raised. Requirements involved the development of data flow methods, separating roles and multiple governance and ethics approvals. Approval to link death data presented the fewest barriers. CONCLUSION: To our knowledge, this is the first time in Australia that person-level data from a clinical quality registry has been linked to hospital and mortality data across multiple Australian jurisdictions. Implications for Public Health: The administrative load of obtaining linked data makes projects such as this burdensome but not impossible. An improved national centralised strategy for data linkage in Australia is urgently needed.

OBJECTIVES: To determine the feasibility of linking data from the Australian Stroke Clinical Registry (AuSCR), the National Death Index (NDI), and state-managed databases for hospital admissions and emergency presentations; to evaluate data completeness and concordance between datasets for common variables. DESIGN, SETTING, PARTICIPANTS: Cohort design; probabilistic/deterministic data linkage of merged records for patients treated in hospital for stroke or transient ischaemic attack from New South Wales, Queensland, Victoria, and Western Australia. MAIN OUTCOME MEASURES: Descriptive statistics for data matching success; concordance of demographic variables common to linked databases; sensitivity and specificity of AuSCR in-hospital death data for predicting NDI registrations. RESULTS: Data for 16 214 patients registered in the AuSCR during 2009-2013 were linked with one or more state datasets: 15 482 matches (95%) with hospital admissions data, and 12 902 matches (80%) with emergency department presentations data were made. Concordance of AuSCR and hospital admissions data exceeded 99% for sex, age, in-hospital death (each κ = 0.99), and Indigenous status (κ = 0.83). Of 1498 registrants identified in the AuSCR as dying in hospital, 1440 (96%) were also recorded by the NDI as dying in hospital. In-hospital death in AuSCR data had 98.7% sensitivity and 99.6% specificity for predicting in-hospital death in the NDI. CONCLUSION: We report the first linkage of data from an Australian national clinical quality disease registry with routinely collected data from several national and state government health datasets. Data linkage enriches the clinical registry dataset and provides additional information beyond that for the acute care setting and quality of life at follow-up, allowing clinical outcomes for people with stroke (mortality and hospital contacts) to be more comprehensively assessed.