MétaCan
Menu
Back to cohort
Record W3021380283 · doi:10.1093/jamia/ocaa038

Using word embeddings to improve the privacy of clinical notes

2020· article· en· W3021380283 on OpenAlexafffund
Mohamed Abdalla, Moustafa Abdalla, Frank Rudzicz, Graeme Hirst

Bibliographic record

VenueJournal of the American Medical Informatics Association · 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 Canada
KeywordsComputer scienceReadabilitySecurity tokenWord embeddingRecallArtificial intelligenceWord (group theory)Natural language processingPrecision and recallMachine learningInformation retrievalEmbeddingData scienceComputer security

Abstract

fetched live from OpenAlex

OBJECTIVE: In this work, we introduce a privacy technique for anonymizing clinical notes that guarantees all private health information is secured (including sensitive data, such as family history, that are not adequately covered by current techniques). MATERIALS AND METHODS: We employ a new "random replacement" paradigm (replacing each token in clinical notes with neighboring word vectors from the embedding space) to achieve 100% recall on the removal of sensitive information, unachievable with current "search-and-secure" paradigms. We demonstrate the utility of this paradigm on multiple corpora in a diverse set of classification tasks. RESULTS: We empirically evaluate the effect of our anonymization technique both on upstream and downstream natural language processing tasks to show that our perturbations, while increasing security (ie, achieving 100% recall on any dataset), do not greatly impact the results of end-to-end machine learning approaches. DISCUSSION: As long as current approaches utilize precision and recall to evaluate deidentification algorithms, there will remain a risk of overlooking sensitive information. Inspired by differential privacy, we sought to make it statistically infeasible to recreate the original data, although at the cost of readability. We hope that the work will serve as a catalyst to further research into alternative deidentification methods that can address current weaknesses. CONCLUSION: Our proposed technique can secure clinical texts at a low cost and extremely high recall with a readability trade-off while remaining useful for natural language processing classification tasks. We hope that our work can be used by risk-averse data holders to release clinical texts to researchers.

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 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)0.005
metaresearch head score (Gemma)0.035
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
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 score0.917
Threshold uncertainty score0.973

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.035
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.001
Research integrity0.0000.001
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 head0.055
GPT teacher head0.407
Teacher spread0.352 · 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 teacher head, not a consensus.

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

Citations21
Published2020
Admission routes2
Has abstractyes

Explore more

Same venueJournal of the American Medical Informatics AssociationSame topicMachine Learning in HealthcareFrench-language works237,207