EUVIMEDEUVIMED entdecken
Crossref

Assessing the accuracy of ChatGPT references in head and neck and ENT disciplines

Andrea Frosolini, Leonardo Franz, Simone Benedetti, Luigi Angelo Vaira, Cosimo de Filippis, Paolo Gennaro, Gino Marioni, Guido Gabriele

European Archives of Oto-Rhino-Laryngology · 2023-11 · 280 (11) · 5129-5133

DOI: 10.1007/s00405-023-08205-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Archives of Oto-Rhino-Laryngology, online erschienen am 08.09.2023. Verfasst von Andrea Frosolini und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Maxillo-Facial Surgery, Policlinico Le Scotte, University of Siena, Siena, Italy. andreafrosolini@gmail.com. Hauptthemen laut MEDLINE: Artificial Intelligence, Head. Die Arbeit wurde bisher 64-mal zitiert (Crossref) und nennt 14 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: ChatGPT has gained popularity as a web application since its release in 2022. While artificial intelligence (AI) systems' potential in scientific writing is widely discussed, their reliability in reviewing literature and providing accurate references remains unexplored. This study examines the reliability of references generated by ChatGPT language models in the Head and Neck field. METHODS: Twenty clinical questions were generated across different Head and Neck disciplines, to prompt ChatGPT versions 3.5 and 4.0 to produce texts on the assigned topics. The generated references were categorized as "true," "erroneous," or "inexistent" based on congruence with existing records in scientific databases. RESULTS: ChatGPT 4.0 outperformed version 3.5 in terms of reference reliability. However, both versions displayed a tendency to provide erroneous/non-existent references. CONCLUSIONS: It is crucial to address this challenge to maintain the reliability of scientific literature. Journals and institutions should establish strategies and good-practice principles in the evolving landscape of AI-assisted scientific writing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceHeadHumansReproducibility of ResultsNeckDatabases, Factual

Stichwörter der Autor:innen

AIArtificial intelligenceChat-GPTHead and neck surgeryMaxillofacial

Autor:innen und Institutionen

  • Department of Maxillo-Facial Surgery, Policlinico Le Scotte, University of Siena, Siena, Italy. andreafrosolini@gmail.com.
  • Phoniatris and Audiology Unit, Department of Neuroscience DNS, University of Padova, Treviso, Italy.
  • Artificial Intelligence in Medicine and Innovation in Clinical Research and Methodology (PhD Program), Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy.
  • Department of Maxillo-Facial Surgery, Policlinico Le Scotte, University of Siena, Siena, Italy.
  • Maxillofacial Surgery Operative Unit, Department of Medicine, Surgery and Pharmacy, University of Sassari, Sassari, Italy.
  • PhD School of Biomedical Sciences, Department of Biomedical Sciences, University of Sassari, Sassari, Italy.

Zitieren

APA

Frosolini, A., Franz, L., Benedetti, S., Vaira, L. A., de Filippis, C., Gennaro, P., Marioni, G., & Gabriele, G. (2023). Assessing the accuracy of ChatGPT references in head and neck and ENT disciplines. European Archives of Oto-Rhino-Laryngology, 280(11), 5129-5133. https://doi.org/10.1007/s00405-023-08205-4

Vancouver

Frosolini A, Franz L, Benedetti S, Vaira LA, de Filippis C, Gennaro P, et al. Assessing the accuracy of ChatGPT references in head and neck and ENT disciplines. European Archives of Oto-Rhino-Laryngology. 2023;280(11):5129-5133. doi:10.1007/s00405-023-08205-4

BibTeX
@article{Frosolini2023,
  author = {Frosolini, Andrea and Franz, Leonardo and Benedetti, Simone and Vaira, Luigi Angelo and de Filippis, Cosimo and Gennaro, Paolo and Marioni, Gino and Gabriele, Guido},
  title = {Assessing the accuracy of ChatGPT references in head and neck and ENT disciplines},
  journal = {European Archives of Oto-Rhino-Laryngology},
  year = {2023},
  volume = {280},
  number = {11},
  pages = {5129--5133},
  doi = {10.1007/s00405-023-08205-4}
}
Kostenlos starten →