Privacy-Preserving Record Linkage of Deidentified Records Within a Public Health Surveillance System: Evaluation Study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: The Australian Collaboration for Coordinated Enhanced Sentinel Surveillance (ACCESS) was established to monitor national testing and test outcomes for blood-borne viruses (BBVs) and sexually transmissible infections (STIs) in key populations. ACCESS extracts deidentified data from sentinel health services that include general practice, sexual health, and infectious disease clinics, as well as public and private laboratories that conduct a large volume of BBV/STI testing. An important attribute of ACCESS is the ability to accurately link individual-level records within and between the participating sites, as this enables the system to produce reliable epidemiological measures. OBJECTIVE: The aim of this study was to evaluate the use of GRHANITE software in ACCESS to extract and link deidentified data from participating clinics and laboratories. GRHANITE generates irreversible hashed linkage keys based on patient-identifying data captured in the patient electronic medical records (EMRs) at the site. The algorithms to produce the data linkage keys use probabilistic linkage principles to account for variability and completeness of the underlying patient identifiers, producing up to four linkage key types per EMR. Errors in the linkage process can arise from imperfect or missing identifiers, impacting the system's integrity. Therefore, it is important to evaluate the quality of the linkages created and evaluate the outcome of the linkage for ongoing public health surveillance. METHODS: Although ACCESS data are deidentified, we created two gold-standard datasets where the true match status could be confirmed in order to compare against record linkage results arising from different approaches of the GRHANITE Linkage Tool. We reported sensitivity, specificity, and positive and negative predictive values where possible and estimated specificity by comparing a history of HIV and hepatitis C antibody results for linked EMRs. RESULTS: Sensitivity ranged from 96% to 100%, and specificity was 100% when applying the GRHANITE Linkage Tool to a small gold-standard dataset of 3700 clinical medical records. Medical records in this dataset contained a very high level of data completeness by having the name, date of birth, post code, and Medicare number available for use in record linkage. In a larger gold-standard dataset containing 86,538 medical records across clinics and pathology services, with a lower level of data completeness, sensitivity ranged from 94% to 95% and estimated specificity ranged from 91% to 99% in 4 of the 6 different record linkage approaches. CONCLUSIONS: This study's findings suggest that the GRHANITE Linkage Tool can be used to link deidentified patient records accurately and can be confidently used for public health surveillance in systems such as ACCESS.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.279 | 0.157 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.006 | 0.003 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it