Assessment of ChatGPT in the Prehospital Management of Ophthalmological Emergencies – An Analysis of 10 Fictional Case Vignettes
Klinische Monatsblätter für Augenheilkunde · 01.05.2024 · 241 (05) · 675-681
DOI: 10.1055/a-2149-0447 ↗Kurz gefasst
Fachartikel in der Zeitschrift Klinische Monatsblätter für Augenheilkunde, erschienen am 01.05.2024. Verfasst von Dominik Knebel und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, University Hospital, Ludwigs-Maximilians-Universität München, München, Germany. Hauptthemen laut MEDLINE: Emergency Medical Services, Triage, Eye Diseases. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 10 Literaturangaben.
Abstract (Originalsprache)
Background
The artificial intelligence (AI)-based platform ChatGPT (Chat Generative Pre-Trained Transformer, OpenAI LP, San Francisco, CA, USA) has gained impressive popularity in recent months. Its performance on case vignettes of general medical (non-ophthalmological) emergencies has been assessed – with very encouraging results. The purpose of this study was to assess the performance of ChatGPT on ophthalmological emergency case vignettes in terms of the main outcome measures triage accuracy, appropriateness of recommended prehospital measures, and overall potential to inflict harm to the user/patient.
Methods
We wrote ten short, fictional case vignettes describing different acute ophthalmological symptoms. Each vignette was entered into ChatGPT five times with the same wording and following a standardized interaction pathway. The answers were analyzed following a systematic approach.
Results
We observed a triage accuracy of 93.6%. Most answers contained only appropriate recommendations for prehospital measures. However, an overall potential to inflict harm to users/patients was present in 32% of answers.
Conclusion
ChatGPT should presently not be used as a stand-alone primary source of information about acute ophthalmological symptoms. As AI continues to evolve, its safety and efficacy in the prehospital management of ophthalmological emergencies has to be reassessed regularly.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Ophthalmology, University Hospital, Ludwigs-Maximilians-Universität München, München, Germany.
ORCID-Profile: Jakob Siedlecki
Zitieren
APA
Knebel, D., Priglinger, S., Scherer, N., Klaas, J., Siedlecki, J., & Schworm, B. (2024). Assessment of ChatGPT in the Prehospital Management of Ophthalmological Emergencies – An Analysis of 10 Fictional Case Vignettes. Klinische Monatsblätter für Augenheilkunde, 241(05), 675-681. https://doi.org/10.1055/a-2149-0447
Vancouver
Knebel D, Priglinger S, Scherer N, Klaas J, Siedlecki J, Schworm B. Assessment of ChatGPT in the Prehospital Management of Ophthalmological Emergencies – An Analysis of 10 Fictional Case Vignettes. Klinische Monatsblätter für Augenheilkunde. 2024;241(05):675-681. doi:10.1055/a-2149-0447
BibTeX
@article{Knebel2024,
author = {Knebel, Dominik and Priglinger, Siegfried and Scherer, Nicolas and Klaas, Julian and Siedlecki, Jakob and Schworm, Benedikt},
title = {Assessment of ChatGPT in the Prehospital Management of Ophthalmological Emergencies – An Analysis of 10 Fictional Case Vignettes},
journal = {Klinische Monatsblätter für Augenheilkunde},
year = {2024},
volume = {241},
number = {05},
pages = {675--681},
doi = {10.1055/a-2149-0447}
}
EUVIMED