Can ChatGPT be used as a scientific source of information on tooth extraction?

IF 0.4 Q4 DENTISTRY, ORAL SURGERY & MEDICINE

Journal of Oral and Maxillofacial Surgery Medicine and Pathology Pub Date : 2025-02-21 DOI:10.1016/j.ajoms.2025.02.009

Shiori Yamamoto , Masakazu Hamada , Kyoko Nishiyama , Ayako Motoki , Yusei Fujita , Narikazu Uzawa

{"title":"Can ChatGPT be used as a scientific source of information on tooth extraction?","authors":"Shiori Yamamoto , Masakazu Hamada , Kyoko Nishiyama , Ayako Motoki , Yusei Fujita , Narikazu Uzawa","doi":"10.1016/j.ajoms.2025.02.009","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>Tooth extraction is one of the most commonly performed dental procedures. ChatGPT uses artificial intelligence and machine learning techniques to generate human-like answers to questions. However, the amount of information that ChatGPT retrieves from the literature and media varies by language, so its response may differ depending on the language used. In this study, we investigated the quality and reliability of English and Japanese responses regarding tooth extractions provided through ChatGPT.</div></div><div><h3>Materials and methods</h3><div>The 10 most frequently asked questions by patients about tooth extraction in English and Japanese were created and posed to the artificial intelligence-based chatbot ChatGPT. Ten Japanese dentists with at least 10 years’ experience of oral and maxillofacial surgery evaluated ChatGPT responses using GQS and LS.</div></div><div><h3>Results</h3><div>Questions input in English to ChatGPT achieved a significantly higher mean GQS score and significantly lower mean LS score than questions in Japanese (both P < 0.05). The results showed significant differences between English and Japanese in the quality and reliability of chatbot performance.</div></div><div><h3>Conclusion</h3><div>ChatGPT’s answers, in both English and Japanese, were sufficiently accurate and appropriate. However, questions input in English to ChatGPT received better answers than those in Japanese. For non-native English speakers, such as Japanese, the information provided by ChatGPT may be limited or inappropriate due to the language barrier. In addition, because conditions vary from case to case, patients should consult their dentist or oral surgeon for personalized advice.</div></div>","PeriodicalId":45034,"journal":{"name":"Journal of Oral and Maxillofacial Surgery Medicine and Pathology","volume":"37 5","pages":"Pages 877-882"},"PeriodicalIF":0.4000,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Oral and Maxillofacial Surgery Medicine and Pathology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212555825000250","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

Tooth extraction is one of the most commonly performed dental procedures. ChatGPT uses artificial intelligence and machine learning techniques to generate human-like answers to questions. However, the amount of information that ChatGPT retrieves from the literature and media varies by language, so its response may differ depending on the language used. In this study, we investigated the quality and reliability of English and Japanese responses regarding tooth extractions provided through ChatGPT.

Materials and methods

The 10 most frequently asked questions by patients about tooth extraction in English and Japanese were created and posed to the artificial intelligence-based chatbot ChatGPT. Ten Japanese dentists with at least 10 years’ experience of oral and maxillofacial surgery evaluated ChatGPT responses using GQS and LS.

Results

Questions input in English to ChatGPT achieved a significantly higher mean GQS score and significantly lower mean LS score than questions in Japanese (both P < 0.05). The results showed significant differences between English and Japanese in the quality and reliability of chatbot performance.

Conclusion

ChatGPT’s answers, in both English and Japanese, were sufficiently accurate and appropriate. However, questions input in English to ChatGPT received better answers than those in Japanese. For non-native English speakers, such as Japanese, the information provided by ChatGPT may be limited or inappropriate due to the language barrier. In addition, because conditions vary from case to case, patients should consult their dentist or oral surgeon for personalized advice.

查看原文本刊更多论文

ChatGPT可以作为拔牙的科学信息来源吗？

目的拔牙是最常见的牙科手术之一。ChatGPT使用人工智能和机器学习技术来生成类似人类的问题答案。然而，ChatGPT从文献和媒体中检索的信息量因语言而异，因此其响应可能因所使用的语言而异。在这项研究中，我们调查了通过ChatGPT提供的关于拔牙的英语和日语应答的质量和可靠性。材料和方法用英语和日语制作患者拔牙最常见的10个问题，并向基于人工智能的聊天机器人ChatGPT提问。10位具有至少10年口腔颌面外科经验的日本牙医使用GQS和LS评估ChatGPT的反应。结果输入英语的ChatGPT题型的GQS平均分显著高于日语题型，LS平均分显著低于日语题型（P均为 <； 0.05）。结果表明，英语和日语在聊天机器人性能的质量和可靠性方面存在显著差异。结论chatgpt的英语和日语答案都足够准确和恰当。然而，用英语输入ChatGPT的问题得到的答案比用日语输入的问题更好。对于非英语母语者，如日本人，由于语言障碍，ChatGPT提供的信息可能有限或不合适。此外，由于情况因情况而异，患者应咨询牙医或口腔外科医生以获得个性化建议。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊