MétaCan
Menu
Back to cohort
Record W4408725130 · doi:10.1093/jamia/ocaf037

Robust privacy amidst innovation with large language models through a critical assessment of the risks

2025· article· en· W4408725130 on OpenAlexafffund
Yao-Shun Chuang, Atiquer Rahman Sarkar, Noman Mohammed, Xiaoqian Jiang

Bibliographic record

VenueJournal of the American Medical Informatics Association · 2025
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning in Healthcare
Canadian institutionsUniversity of Manitoba
FundersNational Center for Advancing Translational SciencesNational Human Genome Research InstituteU.S. National Library of MedicineNational Institute on AgingNatural Sciences and Engineering Research Council of CanadaUniversity of Texas Health Science Center at HoustonNational Cancer InstituteNational Science FoundationNational Institutes of HealthCancer Prevention and Research Institute of Texas
KeywordsHealth Insurance Portability and Accountability ActComputer scienceSoftware portabilityCosine similarityUsabilityHealth careInformation retrievalF1 scoreNatural language processingArtificial intelligenceData extractionHealth recordsData qualitySimilarity (geometry)Machine learningConfidentialityData miningMetric (unit)Computer securityMEDLINEPattern recognition (psychology)Human–computer interaction

Abstract

fetched live from OpenAlex

OBJECTIVE: This study evaluates the integration of electronic health records (EHRs) and natural language processing (NLP) with large language models (LLMs) to enhance healthcare data management and patient care, focusing on using advanced language models to create secure, Health Insurance Portability and Accountability Act-compliant synthetic patient notes for global biomedical research. MATERIALS AND METHODS: The study used de-identified and re-identified versions of the MIMIC III dataset with GPT-3.5, GPT-4, and Mistral 7B to generate synthetic clinical notes. Text generation employed templates and keyword extraction for contextually relevant notes, with One-shot generation for comparison. Privacy was assessed by analyzing protected health information (PHI) occurrence and co-occurrence, while utility was evaluated by training an ICD-9 coder using synthetic notes. Text quality was measured using ROUGE (Recall-Oriented Understudy for Gisting Evaluation) and cosine similarity metrics to compare synthetic notes with source notes for semantic similarity. RESULTS: The analysis of PHI occurrence and text utility via the ICD-9 coding task showed that the keyword-based method had low risk and good performance. One-shot generation exhibited the highest PHI exposure and PHI co-occurrence, particularly in geographic location and date categories. The Normalized One-shot method achieved the highest classification accuracy. Re-identified data consistently outperformed de-identified data. DISCUSSION: Privacy analysis revealed a critical balance between data utility and privacy protection, influencing future data use and sharing. CONCLUSION: This study shows that keyword-based methods can create synthetic clinical notes that protect privacy while retaining data usability, potentially improving clinical data sharing. The use of dummy PHIs to counter privacy attacks may offer better utility and privacy than traditional de-identification.

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)0.003
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation 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 score0.827
Threshold uncertainty score0.542

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.005
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
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 head0.031
GPT teacher head0.385
Teacher spread0.354 · 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.

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

Citations5
Published2025
Admission routes2
Has abstractyes

Explore more

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