Comparing orthodontic pre-treatment information provided by large language models

Abstract This study collected and screened the 50 most common pre-treatment consultation questions from adult orthodontic patients through clinical practice. Responses to these questions were generated using three large language models: Ernie Bot, ChatGPT, and Gemini. The responses were evaluated ac...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingcheng Chen, Xiangyu Ge, Chenyang Yuan, Yanan Chen, Xiangyu Li, Xi Zhang, Shixiang Chen, WeiYing Zheng, Chunqin Miao
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Oral Health
Subjects:
Online Access:https://doi.org/10.1186/s12903-025-06246-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231135090507776
author Jingcheng Chen
Xiangyu Ge
Chenyang Yuan
Yanan Chen
Xiangyu Li
Xi Zhang
Shixiang Chen
WeiYing Zheng
Chunqin Miao
author_facet Jingcheng Chen
Xiangyu Ge
Chenyang Yuan
Yanan Chen
Xiangyu Li
Xi Zhang
Shixiang Chen
WeiYing Zheng
Chunqin Miao
author_sort Jingcheng Chen
collection DOAJ
description Abstract This study collected and screened the 50 most common pre-treatment consultation questions from adult orthodontic patients through clinical practice. Responses to these questions were generated using three large language models: Ernie Bot, ChatGPT, and Gemini. The responses were evaluated across six dimensions: Professional Accuracy (PA), Accuracy of Content(AC), Clarity and Comprehensibility (CC), Personalization and Relevance (PR), Information Completeness (IC), and Empathy and Patient-Centeredness (EHC). Results indicated that scores for each group in various dimensions primarily fell within the range of 3–4 points, with relatively few high-quality scores (5 points). While large language models demonstrate some capability in addressing open-ended questions, their use in medical consultation, particularly in orthodontic medicine, requires caution and further integration with professional guidance and verification. Future research and technological improvements should focus on enhancing AI(Artificial Intelligence) performance in accuracy, information completeness, and humanistic care to better meet the needs of diverse clinical scenarios.
format Article
id doaj-art-12ecdda893b547c5886e2f8df0239a4a
institution OA Journals
issn 1472-6831
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Oral Health
spelling doaj-art-12ecdda893b547c5886e2f8df0239a4a2025-08-20T02:03:39ZengBMCBMC Oral Health1472-68312025-05-012511810.1186/s12903-025-06246-1Comparing orthodontic pre-treatment information provided by large language modelsJingcheng Chen0Xiangyu Ge1Chenyang Yuan2Yanan Chen3Xiangyu Li4Xi Zhang5Shixiang Chen6WeiYing Zheng7Chunqin Miao8Jiaxing Nanhu District People’s HospitalThe Second Hospital of JiaxingThe Second Hospital of JiaxingThe Second Hospital of JiaxingThe Second Hospital of JiaxingThe Second Hospital of JiaxingTongxiang Hospital of Traditional Chinese MedicineThe Second Hospital of JiaxingThe Second Hospital of JiaxingAbstract This study collected and screened the 50 most common pre-treatment consultation questions from adult orthodontic patients through clinical practice. Responses to these questions were generated using three large language models: Ernie Bot, ChatGPT, and Gemini. The responses were evaluated across six dimensions: Professional Accuracy (PA), Accuracy of Content(AC), Clarity and Comprehensibility (CC), Personalization and Relevance (PR), Information Completeness (IC), and Empathy and Patient-Centeredness (EHC). Results indicated that scores for each group in various dimensions primarily fell within the range of 3–4 points, with relatively few high-quality scores (5 points). While large language models demonstrate some capability in addressing open-ended questions, their use in medical consultation, particularly in orthodontic medicine, requires caution and further integration with professional guidance and verification. Future research and technological improvements should focus on enhancing AI(Artificial Intelligence) performance in accuracy, information completeness, and humanistic care to better meet the needs of diverse clinical scenarios.https://doi.org/10.1186/s12903-025-06246-1Large language modelsPre-treatment informationOrthodonticErnie botChatgptGemini
spellingShingle Jingcheng Chen
Xiangyu Ge
Chenyang Yuan
Yanan Chen
Xiangyu Li
Xi Zhang
Shixiang Chen
WeiYing Zheng
Chunqin Miao
Comparing orthodontic pre-treatment information provided by large language models
BMC Oral Health
Large language models
Pre-treatment information
Orthodontic
Ernie bot
Chatgpt
Gemini
title Comparing orthodontic pre-treatment information provided by large language models
title_full Comparing orthodontic pre-treatment information provided by large language models
title_fullStr Comparing orthodontic pre-treatment information provided by large language models
title_full_unstemmed Comparing orthodontic pre-treatment information provided by large language models
title_short Comparing orthodontic pre-treatment information provided by large language models
title_sort comparing orthodontic pre treatment information provided by large language models
topic Large language models
Pre-treatment information
Orthodontic
Ernie bot
Chatgpt
Gemini
url https://doi.org/10.1186/s12903-025-06246-1
work_keys_str_mv AT jingchengchen comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT xiangyuge comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT chenyangyuan comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT yananchen comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT xiangyuli comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT xizhang comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT shixiangchen comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT weiyingzheng comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels
AT chunqinmiao comparingorthodonticpretreatmentinformationprovidedbylargelanguagemodels