Open Access
Open access
Ovid Technologies (Wolters Kluwer Health)
Saudi Endodontic Journal
,  том 15 ,  издание 1 ,  страницы 45-52

Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion

Rafael Wolanski Bordin 1
, 
Caio César Bartnack 1
, 
Vânia Portela Ditzel Westphalen 1
, 
Gil Guilherme Gasparello 1
, 
Mohamad Jamal Bark 1
, 
Thaís Nogueira Gava 2
, 
Orlando Motohiro Tanaka 1, 3
1
 
2
 
Private Practice, Orthodontist IOA, Missouri, US | 
3
 
Тип публикации: Journal Article
Дата публикации: 2024-12-24
Ovid Technologies (Wolters Kluwer Health)
scimago Q3
БС3
SJR: 0.215
CiteScore: 1.4
Impact factor: —
ISSN: 22789618, 23201495, 16585984
Краткое описание
Introduction:

The advancement of artificial intelligence (AI) has revolutionized digital communication, enhancing interactions between humans and computers. This study explores the application of Chat Generative Pretrained Transformer 3.5 (ChatGPT-3.5), in providing accurate information on dental trauma.

Materials and Methods:

Utilizing a dataset of 45 self-generated questions across three topics, general dental trauma, avulsion, and intrusion, ChatGPT-3.5 generated responses that were subsequently evaluated by five endodontic experts, each with over a decade of experience. The evaluators used a Likert scale to assess the quality of the AI-generated answers, synthesizing reliable scientific evidence and clinical expertise to ensure a thorough analysis. The data obtained from the evaluators’ scores were organized and analyzed using Microsoft Excel software and the Statistical Package for the Social Sciences version 25. For each question, descriptive statistics including the median and interquartile range were computed.

Results:

The study found that ChatGPT provided reliable information across the three assessed dental topics. Avulsion was rated the highest (4.40 ± 0.717), significantly outperforming general dental trauma (3.97 ± 0.885) (P = 0.005). Intrusion received a rating of 4.13 ± 0.794, showing no significant difference compared to the other topics. Most evaluator scores fell into the “Good” (44.0%) and “Very Good” (38.7%) categories. This indicates a generally positive appraisal of ChatGPT’s performance, with a fair agreement among evaluators, evidenced by a combined Fleiss’s kappa coefficient of 0.324. However, there was variability, particularly with Evaluator 4’s scores differing significantly from those of evaluators 1 and 2.

Conclusions:

ChatGPT’s responses on general dental trauma, avulsion, and intrusion were generally rated positively, with avulsion responses deemed the most reliable. The study underscores the need for continuous evaluation to maintain the accuracy, reliability, and safety of AI-generated content in endodontics, suggesting AI should serve as a supplementary tool rather than a primary information source.

Найдено 
Найдено 

Топ-30

Журналы

1
Journal of Endodontics
Journal of Endodontics, 1, 33.33%
Journal of Endodontics
1 публикация, 33.33%
Applied Sciences (Switzerland)
Applied Sciences (Switzerland), 1, 33.33%
Applied Sciences (Switzerland)
1 публикация, 33.33%
International Journal of Medical Informatics
International Journal of Medical Informatics, 1, 33.33%
International Journal of Medical Informatics
1 публикация, 33.33%
1

Издатели

1
2
Elsevier
Elsevier, 2, 66.67%
Elsevier
2 публикации, 66.67%
MDPI
MDPI, 1, 33.33%
MDPI
1 публикация, 33.33%
1
2
  • Мы не учитываем публикации, у которых нет DOI.
  • Статистика публикаций обновляется еженедельно.

Вы ученый?

Создайте профиль, чтобы получать персональные рекомендации коллег, конференций и новых статей.
Метрики
3
Поделиться
Цитировать
ГОСТ |
Цитировать
ГОСТ Скопировать
Bordin R. W. et al. Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion // Saudi Endodontic Journal. 2024. Vol. 15. No. 1. pp. 45-52.
ГОСТ со всеми авторами (до 50) Скопировать
Bordin R. W., Bartnack C. C., Westphalen V. P. D., Gasparello G. G., Bark M. J., Gava T. N., Tanaka O. M. Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion // Saudi Endodontic Journal. 2024. Vol. 15. No. 1. pp. 45-52.
RIS |
Цитировать
RIS Скопировать
TY - JOUR
DO - 10.4103/sej.sej_107_24
UR - https://journals.lww.com/10.4103/sej.sej_107_24
TI - Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion
T2 - Saudi Endodontic Journal
AU - Bordin, Rafael Wolanski
AU - Bartnack, Caio César
AU - Westphalen, Vânia Portela Ditzel
AU - Gasparello, Gil Guilherme
AU - Bark, Mohamad Jamal
AU - Gava, Thaís Nogueira
AU - Tanaka, Orlando Motohiro
PY - 2024
DA - 2024/12/24
PB - Ovid Technologies (Wolters Kluwer Health)
SP - 45-52
IS - 1
VL - 15
SN - 2278-9618
SN - 2320-1495
SN - 1658-5984
ER -
BibTex |
Цитировать
BibTex (до 50 авторов) Скопировать
@article{2024_Bordin,
author = {Rafael Wolanski Bordin and Caio César Bartnack and Vânia Portela Ditzel Westphalen and Gil Guilherme Gasparello and Mohamad Jamal Bark and Thaís Nogueira Gava and Orlando Motohiro Tanaka},
title = {Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion},
journal = {Saudi Endodontic Journal},
year = {2024},
volume = {15},
publisher = {Ovid Technologies (Wolters Kluwer Health)},
month = {dec},
url = {https://journals.lww.com/10.4103/sej.sej_107_24},
number = {1},
pages = {45--52},
doi = {10.4103/sej.sej_107_24}
}
MLA
Цитировать
MLA Скопировать
Bordin, Rafael Wolanski, et al. “Evaluating generative pretraining transformer reliability in addressing dental trauma: A cross-sectional observational study on avulsion and intrusion.” Saudi Endodontic Journal, vol. 15, no. 1, Dec. 2024, pp. 45-52. https://journals.lww.com/10.4103/sej.sej_107_24.