MétaCan
Menu
Back to cohort
Record W4317910576 · doi:10.1101/2023.01.22.23284882

Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of its Successes and Shortcomings

2023· preprint· en· W4317910576 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.

Bibliographic record

VenuemedRxiv · 2023
Typepreprint
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsCentre intégré universitaire de santé et de services sociaux de l'Est-de-l'Île-de-MontréalCentre Hospitalier de l’Université de MontréalUniversité de MontréalCentre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-MontréalHôpital Maisonneuve-Rosemont
Fundersnot available
KeywordsRecallInterpretation (philosophy)Ophthalmic pathologySpace (punctuation)MedicineComputer scienceOptometryOphthalmologyMedical physicsPsychologyNeuro-ophthalmologyGlaucomaCognitive psychology

Abstract

fetched live from OpenAlex

ABSTRACT We tested the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space using two popular multiple choice question banks used for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) exam. The testing sets were of easy-to-moderate difficulty and were diversified, including recall, interpretation, practical and clinical decision-making problems. ChatGPT achieved 55.8% and 42.7% accuracy in the two 260-question simulated exams. Its performance varied across subspecialties, with the best results in general medicine and the worst in neuro-ophthalmology and ophthalmic pathology and intraocular tumors. These results are encouraging but suggest that specialising LLMs through domain-specific pre-training may be necessary to improve their performance in ophthalmic subspecialties.

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.

Direct model labels (unvalidated)

Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.

Model armCategoriesStudy designConfidence
gptno category
Domain: not available · Genre: Empirical
About the Canadian research system: no · About a Canadian topic: no
Bench or experimentalhigh
grokno category
Domain: not available · Genre: Empirical
About the Canadian research system: no · About a Canadian topic: no
Observationalhigh
opusno category
Domain: not available · Genre: Empirical
About the Canadian research system: no · About a Canadian topic: no
Bench or experimentalmedium
models splitAgreement compares identical category sets and study designs across arms.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.129
Threshold uncertainty score0.370

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
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 science0.0000.000
Research integrity0.0000.000
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 head0.336
GPT teacher head0.518
Teacher spread0.182 · 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