EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images

Shila Kahalian iD, Marieh Rajabzadeh iD, Melisa Öçbe iD, Mahmut Sabri Medisoglu iD

Folia Medica · 31.12.2024 · 66 (6) · 863-868

DOI: 10.3897/folmed.66.e135584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Folia Medica, online erschienen am 31.12.2024. Verfasst von Shila Kahalian und 3 weiteren Autor:innen. Beteiligte Einrichtung: Kocaeli Health and Technology University, Kocaeli, Turkiye. Hauptthemen laut MEDLINE: Natural Language Processing. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

ChatGPT has the ability to generate human-like text, analyze and understand medical images using natural Language processing (NLP) algorithms. It can generate real-time diagnosis and recognize patterns and learn from previous cases to improve accuracy by combining patient history, symptoms, and image characteristics. It has been used recently for learning about maxillofacial diseases, writing and translating radiology reports, and identifying anatomical landmarks, among other things. Materials and methods : In this study, 52 radiographic images were queried on the OpenAI application ChatGPT-4.0. The responses were evaluated with and without using clues for specific radiographs to see if adding clues during prompting improved diagnostic accuracy.

Results

The true prediagnosis rate without any clue was 30.7%. By adding one clue this rate significantly increased to 56.9%. There was not a significant difference in accurate diagnosis of anatomical landmarks, cysts, and tumors ( p >0.05). However, including internal structure information improved the diagnostic accuracy ( p <0.05)

Conclusion

GPT-4.0 showed a tendency to misdiagnose closely located anatomical structures and by adding additional clues its performance showed improvement, while its ability to recognize diverse differential diagnoses remains limited.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingHumansAlgorithms

Stichwörter der Autor:innen

anatomical landmarks artificial intelligence ChatGPT oral radiology

Autor:innen und Institutionen

  • Kocaeli Health and Technology University, Kocaeli, Turkiye.

ORCID-Profile: Shila Kahalian, Marieh Rajabzadeh, Melisa Öçbe, Mahmut Sabri Medisoglu

Zitieren

APA

Kahalian, S., Rajabzadeh, M., Öçbe, M., & Medisoglu, M. S. (2024). ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images. Folia Medica, 66(6), 863-868. https://doi.org/10.3897/folmed.66.e135584

Vancouver

Kahalian S, Rajabzadeh M, Öçbe M, Medisoglu MS. ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images. Folia Medica. 2024;66(6):863-868. doi:10.3897/folmed.66.e135584

BibTeX
@article{Kahalian2024,
  author = {Kahalian, Shila and Rajabzadeh, Marieh and Öçbe, Melisa and Medisoglu, Mahmut Sabri},
  title = {ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images},
  journal = {Folia Medica},
  year = {2024},
  volume = {66},
  number = {6},
  pages = {863--868},
  doi = {10.3897/folmed.66.e135584}
}
Kostenlos starten →