MétaCan
Menu
Back to cohort
Record W3043243165 · doi:10.2196/18055

Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study

2020· article· en· W3043243165 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueJournal of Medical Internet Research · 2020
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning in Healthcare
Canadian institutionsSt. Michael's HospitalInstitute for Clinical Evaluative SciencesVector InstituteUniversity of Toronto
FundersNatural Sciences and Engineering Research Council of CanadaOntario Ministry of Health and Long-Term Care
KeywordsComputer scienceWord (group theory)Natural language processingCode (set theory)Word embeddingArtificial intelligenceRepresentation (politics)EmbeddingInformation retrievalSource codeLinguistics

Abstract

fetched live from OpenAlex

BACKGROUND: Word embeddings are dense numeric vectors used to represent language in neural networks. Until recently, there had been no publicly released embeddings trained on clinical data. Our work is the first to study the privacy implications of releasing these models. OBJECTIVE: This paper aims to demonstrate that traditional word embeddings created on clinical corpora that have been deidentified by removing personal health information (PHI) can nonetheless be exploited to reveal sensitive patient information. METHODS: We used embeddings created from 400,000 doctor-written consultation notes and experimented with 3 common word embedding methods to explore the privacy-preserving properties of each. RESULTS: We found that if publicly released embeddings are trained from a corpus anonymized by PHI removal, it is possible to reconstruct up to 68.5% (n=411/600) of the full names that remain in the deidentified corpus and associated sensitive information to specific patients in the corpus from which the embeddings were created. We also found that the distance between the word vector representation of a patient's name and a diagnostic billing code is informative and differs significantly from the distance between the name and a code not billed for that patient. CONCLUSIONS: Special care must be taken when sharing word embeddings created from clinical texts, as current approaches may compromise patient privacy. If PHI removal is used for anonymization before traditional word embeddings are trained, it is possible to attribute sensitive information to patients who have not been fully deidentified by the (necessarily imperfect) removal algorithms. A promising alternative (ie, anonymization by PHI replacement) may avoid these flaws. Our results are timely and critical, as an increasing number of researchers are pushing for publicly available health data.

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 imitation

Not 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.

metaresearch head score (Codex)0.011
metaresearch head score (Gemma)0.014
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Open science, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.927
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0110.014
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0060.003
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

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 head0.353
GPT teacher head0.440
Teacher spread0.088 · 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