ArticleJournal of hand surgery global online2024
ChatGPT's Performance on the Hand Surgery Self-Assessment Exam: A Critical Analysis.
Article in Journal of hand surgery global online, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 10 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
10 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Examining the Role of Large Language Models in Orthopedics: Systematic Review.Journal of medical Internet research · 2024Pooled it
- Impact of prompting on large language model performance: ChatGPT-4 performance on the 2023 hand surgery self-assessment examination.Journal of hand and microsurgery · 2025Article
- Comparison of hand surgery certification exams in Europe and the United States using ChatGPT 4.0.Journal of hand and microsurgery · 2025Article
- Review
- Article
- Evaluation of Chat Generative Pre-trained Transformer and Microsoft Copilot Performance on the American Society of Surgery of the Hand Self-Assessment Examinations.Journal of hand surgery global online · 2025Article
- ChatGPT-4 Surpasses Residents: A Study of Artificial Intelligence Competency in Plastic Surgery In-service Examinations and Its Advancements from ChatGPT-3.5.Plastic and reconstructive surgery. Global open · 2024Article
- Article
- ChatGPT-4 Can Help Hand Surgeons Communicate Better With Patients.Journal of hand surgery global online · 2024Article
- The Performance of ChatGPT on the American Society for Surgery of the Hand Self-Assessment Examination.Cureus · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Purpose: To assess the performance of Chat Generative Pre-Trained Transformer (ChatGPT) when answering self-assessment exam questions in hand surgery and to compare correct results for text-only questions to those for questions that included images. Methods: This study used 10 self-assessment exams from 2004 to 2013 provided by the American Society for Surgery of the Hand (ASSH). ChatGPT's performance on text-only questions and image-based questions was compared. The primary outcomes were ChatGPT's total score, score on text-only questions, and score on image-based questions. The secondary outcomes were the proportion of questions for which ChatGPT provided additional explanations, the length of those elaborations, and the number of questions for which ChatGPT provided answers with certainty. Results: Out of 1,583 questions, ChatGPT answered 573 (36.2%) correct. ChatGPT performed better on text-only questions than image-based questions. Out of 1,127 text-only questions, ChatGPT answered 442 (39.2%) correctly. Out of the 456 image-based questions, it answered 131 (28.7%) correctly. There was no difference between the proportion of elaborations among text-only and image-based questions. Although there was no difference between the length of elaborations for questions ChatGPT got correct and incorrect, the length of elaborations provided for image-based questions were longer than those provided for text-only questions. Out of 1,441 confident answers, 548 (38.0%) were correct; out of 142 unconfident answers, 25 (17.6%) were correct. Conclusions: ChatGPT performed poorly on the ASSH self-assessment exams from 2004 to 2013. It performed better on text-only questions. Even with its highest score of 42% for the year 2012, the AI platform would not have received continuing medical education credit from ASSH or the American Board of Surgery. Even when only considering questions without images, ChatGPT's high score of 44% correct would not have "passed" the examination. Clinical relevance: At this time, medical professionals, trainees, and patients should use ChatGPT with caution as the program has not yet developed proficiency with hand subspecialty knowledge.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.