MétaCan
Menu
Back to cohort
Record W2484962737 · doi:10.1016/j.jbi.2016.07.015

A unified framework for evaluating the risk of re-identification of text de-identification tools

2016· article· en· W2484962737 on OpenAlexafffund
Martin Scaiano, Grant Middleton, Luk Arbuckle, Varada Kolhatkar, Liam Peyton, Moira Dowling, Debbie S. Gipson, Khaled El Emam

Bibliographic record

VenueJournal of Biomedical Informatics · 2016
Typearticle
Languageen
FieldHealth Professions
TopicElectronic Health Records Systems
Canadian institutionsChildren's Hospital of Eastern OntarioPrivacy Analytics (Canada)University of Ottawa
FundersNatural Sciences and Engineering Research Council of CanadaMitacsUniversity of Ottawa
KeywordsIdentification (biology)IdentifierComputer scienceContext (archaeology)Data miningSet (abstract data type)Information retrieval

Abstract

fetched live from OpenAlex

OBJECTIVES: It has become regular practice to de-identify unstructured medical text for use in research using automatic methods, the goal of which is to remove patient identifying information to minimize re-identification risk. The metrics commonly used to determine if these systems are performing well do not accurately reflect the risk of a patient being re-identified. We therefore developed a framework for measuring the risk of re-identification associated with textual data releases. METHODS: We apply the proposed evaluation framework to a data set from the University of Michigan Medical School. Our risk assessment results are then compared with those that would be obtained using a typical contemporary micro-average evaluation of recall in order to illustrate the difference between the proposed evaluation framework and the current baseline method. RESULTS: We demonstrate how this framework compares against common measures of the re-identification risk associated with an automated text de-identification process. For the probability of re-identification using our evaluation framework we obtained a mean value for direct identifiers of 0.0074 and a mean value for quasi-identifiers of 0.0022. The 95% confidence interval for these estimates were below the relevant thresholds. The threshold for direct identifier risk was based on previously used approaches in the literature. The threshold for quasi-identifiers was determined based on the context of the data release following commonly used de-identification criteria for structured data. DISCUSSION: Our framework attempts to correct for poorly distributed evaluation corpora, accounts for the data release context, and avoids the often optimistic assumptions that are made using the more traditional evaluation approach. It therefore provides a more realistic estimate of the true probability of re-identification. CONCLUSIONS: This framework should be used as a basis for computing re-identification risk in order to more realistically evaluate future text de-identification tools.

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 imitation

Not 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.

metaresearch head score (Codex)0.116
metaresearch head score (Gemma)0.253
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.116
Threshold uncertainty score0.612

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1160.253
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0030.003
Bibliometrics0.0200.006
Science and technology studies0.0020.003
Scholarly communication0.0100.008
Open science0.0040.006
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.131
GPT teacher head0.494
Teacher spread0.363 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations28
Published2016
Admission routes2
Has abstractyes

Explore more

Same venueJournal of Biomedical InformaticsSame topicElectronic Health Records SystemsFrench-language works237,207