MétaCan
Menu
Back to cohort
Record W4410985212 · doi:10.1200/cci-24-00331

Clinical Trial Design Approach to Auditing Language Models in Health Care Setting

2025· article· en· W4410985212 on OpenAlexaff
Lovedeep Gondara, Jonathan Simkin, Shebnum Devji

Bibliographic record

VenueJCO Clinical Cancer Informatics · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsProvincial Health Services AuthorityUniversity of British Columbia
Fundersnot available
KeywordsAuditHealth careMedicineComputer sciencePsychologyBusinessAccountingEconomics

Abstract

fetched live from OpenAlex

PURPOSE: Rapid advancements in natural language processing have led to the development of sophisticated language models. Inspired by their success, these models are now used in health care for tasks such as clinical documentation and medical record classification. However, language models are prone to errors, which can have serious consequences in critical domains such as health care, ensuring that their reliability is essential to maintain patient safety and data integrity. METHODS: To address this, we propose an innovative auditing process based on principles from clinical trial design. Our approach involves subject matter experts (SMEs) manually reviewing pathology reports without previous knowledge of the model's classification. This single-blind setup minimizes bias and allows us to apply statistical rigor to assess model performance. RESULTS: Deployed at the British Columbia Cancer Registry, our audit process effectively identified the core issues in the operational models. Early interventions addressed these issues, maintaining data integrity and patient care standards. CONCLUSION: The audit provides real-world performance metrics and underscores the importance of human-in-the-loop machine learning. Even advanced models require SME oversight to ensure accuracy and reliability. To our knowledge, we have developed the first continuous audit process for language models in health care, modeled after clinical trial principles. This methodology ensures that audits are statistically sound and operationally feasible, setting a new standard for evaluating language models in critical applications.

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)0.455
metaresearch head score (Gemma)0.557
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: Methods
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.545
Threshold uncertainty score0.672

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.4550.557
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.003
Bibliometrics0.0040.003
Science and technology studies0.0020.005
Scholarly communication0.0060.005
Open science0.0050.006
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0100.002

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 head0.472
GPT teacher head0.601
Teacher spread0.129 · 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.

Study designTheoretical or conceptual
DomainMethods
GenreMethods

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJCO Clinical Cancer InformaticsSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207