MétaCan
Menu
Back to cohort
Record W4378976945 · doi:10.1101/2023.05.30.23290758

Evaluating ChatGPT-4 in Otolaryngology–Head and Neck Surgery Board Examination using the CVSA Model

2023· preprint· en· W4378976945 on OpenAlexaffabout
Cai Long, K. Lowe, André dos Santos, Jessica Zhang, Alaa Alanazi, Daniel C. O’Brien, Erin D. Wright, David W. J. Côté

Bibliographic record

VenuemedRxiv · 2023
Typepreprint
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsOtorhinolaryngologyConcordanceHead and neck surgeryMedicineHead and neckSAFERSample (material)Consistency (knowledge bases)Medical physicsMultiple choiceMedical educationSurgeryArtificial intelligenceComputer scienceInternal medicine

Abstract

fetched live from OpenAlex

Abstract Background ChatGPT is among the most popular Large Language Models (LLM), exhibiting proficiency in various standardized tests, including multiple-choice medical board examinations. However, its performance on Otolaryngology–Head and Neck Surgery (OHNS) board exams and open-ended medical board examinations has not been reported. We present the first evaluation of LLM (ChatGPT-4) on such examinations and propose a novel method to assess an artificial intelligence (AI) model’s performance on open-ended medical board examination questions. Methods Twenty-one open end questions were adopted from the Royal College of Physicians and Surgeons of Canada’s sample exam to query ChatGPT-4 on April 11th, 2023, with and without prompts. A new CVSA (concordance, validity, safety, and accuracy) model was developed to evaluate its performance. Results In an open-ended question assessment, ChatGPT-4 achieved a passing mark (an average of 75% across three trials) in the attempts. The model demonstrated high concordance (92.06%) and satisfactory validity. While demonstrating considerable consistency in regenerating answers, it often provided only partially correct responses. Notably, concerning features such as hallucinations and self-conflicting answers were observed. Conclusion ChatGPT-4 achieved a passing score in the sample exam, and demonstrated the potential to pass the Canadian Otolaryngology–Head and Neck Surgery Royal College board examination. Some concerns remain due to its hallucinations that could pose risks to patient safety. Further adjustments are necessary to yield safer and more accurate answers for clinical implementation.

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)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.531
Threshold uncertainty score0.645

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.449
GPT teacher head0.489
Teacher spread0.040 · 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 designObservational
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

Citations16
Published2023
Admission routes2
Has abstractyes

Explore more

Same venuemedRxivSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207