Evaluating ChatGPT-4 in Otolaryngology–Head and Neck Surgery Board Examination using the CVSA Model
Bibliographic record
Abstract
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".