Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations
Radiology · 01.06.2023 · 307 (5)
DOI: 10.1148/radiol.230582 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology, erschienen am 01.06.2023. Verfasst von Rajesh Bhayana und 2 weiteren Autor:innen. Beteiligte Einrichtung: From the University Medical Imaging Toronto, Joint Department of Medical Imaging, University Health Network, Mount Sinai Hospital and Women's College…. Hauptthemen laut MEDLINE: Artificial Intelligence, Radiology. Die Arbeit wurde bisher 466-mal zitiert (Crossref) und nennt 13 Literaturangaben.
Abstract (Originalsprache)
Background
ChatGPT is a powerful artificial intelligence large language model with great potential as a tool in medical practice and education, but its performance in radiology remains unclear.
Purpose
To assess the performance of ChatGPT on radiology board-style examination questions without images and to explore its strengths and limitations. Materials and Methods In this exploratory prospective study performed from February 25 to March 3, 2023, 150 multiple-choice questions designed to match the style, content, and difficulty of the Canadian Royal College and American Board of Radiology examinations were grouped by question type (lower-order [recall, understanding] and higher-order [apply, analyze, synthesize] thinking) and topic (physics, clinical). The higher-order thinking questions were further subclassified by type (description of imaging findings, clinical management, application of concepts, calculation and classification, disease associations). ChatGPT performance was evaluated overall, by question type, and by topic. Confidence of language in responses was assessed. Univariable analysis was performed.
Results
ChatGPT answered 69% of questions correctly (104 of 150). The model performed better on questions requiring lower-order thinking (84%, 51 of 61) than on those requiring higher-order thinking (60%, 53 of 89) (P = .002). When compared with lower-order questions, the model performed worse on questions involving description of imaging findings (61%, 28 of 46; P = .04), calculation and classification (25%, two of eight; P = .01), and application of concepts (30%, three of 10; P = .01). ChatGPT performed as well on higher-order clinical management questions (89%, 16 of 18) as on lower-order questions (P = .88). It performed worse on physics questions (40%, six of 15) than on clinical questions (73%, 98 of 135) (P = .02). ChatGPT used confident language consistently, even when incorrect (100%, 46 of 46).
Conclusion
Despite no radiology-specific pretraining, ChatGPT nearly passed a radiology board-style examination without images; it performed well on lower-order thinking questions and clinical management questions but struggled with higher-order thinking questions involving description of imaging findings, calculation and classification, and application of concepts. © RSNA, 2023 See also the editorial by Lourenco et al and the article by Bhayana et al in this issue.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- From the University Medical Imaging Toronto, Joint Department of Medical Imaging, University Health Network, Mount Sinai Hospital and Women's College Hospital, University of Toronto, Toronto General Hospital, 200 Elizab…
ORCID-Profile: Rajesh Bhayana, Satheesh Krishna, Robert R Bleakney
Zitieren
APA
Bhayana, R., Krishna, S., & Bleakney, R. R. (2023). Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations. Radiology, 307(5). https://doi.org/10.1148/radiol.230582
Vancouver
Bhayana R, Krishna S, Bleakney RR. Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations. Radiology. 2023;307(5). doi:10.1148/radiol.230582
BibTeX
@article{Bhayana2023,
author = {Bhayana, Rajesh and Krishna, Satheesh and Bleakney, Robert R},
title = {Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations},
journal = {Radiology},
year = {2023},
volume = {307},
number = {5},
doi = {10.1148/radiol.230582}
}
EUVIMED