Article (Scientific journals)
Accuracy of ChatGPT-3.5 and -4 in providing scientific references in otolaryngology-head and neck surgery.
Lechien, Jerome R; Briganti, Giovanni; Vaira, Luigi A
2024In European Archives of Oto-Rhino-Laryngology, 281 (4), p. 2159 - 2165
Peer Reviewed verified by ORBi
 

Files


Full Text
s00405-023-08441-8.pdf
Publisher postprint (616.25 kB)
Request a copy

All documents in ORBi UMONS are protected by a user license.

Send to



Details



Keywords :
Artificial intelligence; ChatGPT; Chatbot; Head neck surgery; Otolaryngology; Reference; Humans; Software; Otolaryngologists; Language; Artificial Intelligence; Otorhinolaryngology
Abstract :
[en] [en] INTRODUCTION: Chatbot generative pre-trained transformer (ChatGPT) is a new artificial intelligence-powered language model of chatbot able to help otolaryngologists in practice and research. We investigated the accuracy of ChatGPT-3.5 and -4 in the referencing of manuscripts published in otolaryngology. METHODS: ChatGPT-3.5 and ChatGPT-4 were interrogated for providing references of the top-30 most cited papers in otolaryngology in the past 40 years including clinical guidelines and key studies that changed the practice. The responses were regenerated three times to assess the accuracy and stability of ChatGPT. ChatGPT-3.5 and ChatGPT-4 were compared for accuracy of reference and potential mistakes. RESULTS: The accuracy of ChatGPT-3.5 and ChatGPT-4.0 ranged from 47% to 60%, and 73% to 87%, respectively (p < 0.005). ChatGPT-3.5 provided 19 inaccurate references and invented 2 references throughout the regenerated questions. ChatGPT-4.0 provided 13 inaccurate references, while it proposed only one invented reference. The stability of responses throughout regenerated answers was mild (k = 0.238) and moderate (k = 0.408) for ChatGPT-3.5 and 4.0, respectively. CONCLUSIONS: ChatGPT-4.0 reported higher accuracy than the free-access version (3.5). False references were detected in both 3.5 and 4.0 versions. Practitioners need to be careful regarding the use of ChatGPT in the reach of some key reference when writing a report.
Disciplines :
Otolaryngology
Author, co-author :
Lechien, Jerome R  ;  Division of Laryngology and Broncho-Esophagology, Department of Otolaryngology-Head Neck Surgery, EpiCURA Hospital, UMONS Research Institute for Health Sciences and Technology, University of Mons (UMons), Mons, Belgium. Jerome.Lechien@umons.ac.be ; Department of Otorhinolaryngology and Head and Neck Surgery, School of Medicine, Phonetics and Phonology Laboratory (UMR 7018, Foch Hospital, CNRS, Université Sorbonne Nouvelle/Paris 3), Paris, France. Jerome.Lechien@umons.ac.be ; Department of Otorhinolaryngology and Head and Neck Surgery, School of Medicine, CHU de Bruxelles, CHU Saint-Pierre, Université Libre de Bruxelles, Brussels, Belgium. Jerome.Lechien@umons.ac.be ; Polyclinique Elsan de Poitiers, Poitiers, France. Jerome.Lechien@umons.ac.be ; Department of Human Anatomy and Experimental Oncology, Faculty of Medicine, UMONS Research Institute for Health Sciences and Technology, Avenue du Champ de Mars, 6, 7000, Mons, Belgium. Jerome.Lechien@umons.ac.be
Briganti, Giovanni  ;  Université de Mons - UMONS > Faculté de Médecine et de Pharmacie > Service de Médecine computationnelle et Neuropsychiatrie
Vaira, Luigi A;  Maxillofacial Surgery Operative Unit, Department of Medicine, Surgery and Pharmacy, University of Sassari, Sassari, Italy ; Biomedical Sciences Department, PhD School of Biomedical Science, University of Sassari, Sassari, Italy
Language :
English
Title :
Accuracy of ChatGPT-3.5 and -4 in providing scientific references in otolaryngology-head and neck surgery.
Publication date :
April 2024
Journal title :
European Archives of Oto-Rhino-Laryngology
ISSN :
0937-4477
eISSN :
1434-4726
Publisher :
Springer Science and Business Media Deutschland GmbH, Germany
Volume :
281
Issue :
4
Pages :
2159 - 2165
Peer reviewed :
Peer Reviewed verified by ORBi
Research unit :
M121 - Service de Médecine computationnelle et Neuropsychiatrie
Research institute :
Santé
Available on ORBi UMONS :
since 03 December 2024

Statistics


Number of views
5 (3 by UMONS)
Number of downloads
0 (0 by UMONS)

Scopus citations®
 
12
Scopus citations®
without self-citations
6
OpenCitations
 
2
OpenAlex citations
 
17

Bibliography


Similar publications



Contact ORBi UMONS