Camouflaged sampling and contacting of people from administrative databases: reaching target patients without knowing who they are
Bibliographic record
Abstract
BACKGROUND: Methods are needed for using confidential data to select and reach patients without compromising their health privacy. METHODS: (a) SAMPLING: we created (1) an anonymous list of encrypted personal health numbers (EPHNs) of target patients (e.g., users of the medications of interest) and (2) an anonymous list of EPHNs of people randomly sampled from the general population of non-users. The two lists were merged and randomly ordered to make a camouflaged list. People on the second list were called camouflagers. Then EPHNs were matched to names and contact information, and the EPHNs were removed from the contact list. (b) Contacting: when we contacted patients by mail or telephone, we told them their names were selected from one of two lists, and their health status was unknown to us. We invited respondents to answer (1) a short survey for the general population or (2) a longer survey concerning the target condition. RESULTS: In five studies, the percentage of camouflagers--equal to one minus the positive predictive value of the camouflaged list--has varied from 10 to over 50%. This depended on the psychosocial sensitivity of the target medications or health conditions, the natural camouflaging by the population's heterogeneity or inaccuracy of the data on the target characteristic, the degree of stratification of the sample, and the cost of contacting. CONCLUSION: Camouflaging enables administrative data to be used for contacting target patients in selected populations while adhering to current data privacy laws and ethics principles.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.127 | 0.266 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".