Hui Liu, Jialun Peng, Lu Li, Ao Deng, XiangXin Huang, Guobing Yin, Haojun Luo
{"title":"大型语言模型作为中国乳腺癌患者和专家咨询热线:横断面问卷研究。","authors":"Hui Liu, Jialun Peng, Lu Li, Ao Deng, XiangXin Huang, Guobing Yin, Haojun Luo","doi":"10.2196/66429","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The disease burden of breast cancer is increasing in China. Guiding people to obtain accurate information on breast cancer and improving the public's health literacy are crucial for the early detection and timely treatment of breast cancer. Large language model (LLM) is a currently popular source of health information. However, the accuracy and practicality of the breast cancer-related information provided by LLMs have not yet been evaluated.</p><p><strong>Objective: </strong>This study aims to evaluate and compare the accuracy, practicality, and generalization-specificity of responses to breast cancer-related questions from two LLMs, ChatGPT and ERNIE Bot (EB).</p><p><strong>Methods: </strong>The questions asked to the LLMs consisted of a patient questionnaire and an expert questionnaire, each containing 15 questions. ChatGPT was queried in both Chinese and English, recorded as ChatGPT-Chinese (ChatGPT-C) and ChatGPT-English (ChatGPT-E) respectively, while EB was queried in Chinese. The accuracy, practicality, and generalization-specificity of each inquiry's responses were rated by a breast cancer multidisciplinary treatment team using Likert scales.</p><p><strong>Results: </strong>Overall, for both the patient and expert questionnaire, the accuracy and practicality of responses from ChatGPT-E were significantly higher than those from ChatGPT-C and EB (all Ps<.001). However, the responses from all LLMs are relatively generalized, leading to lower accuracy and practicality for the expert questionnaire compared to the patient questionnaire. Additionally, there were issues such as the lack of supporting evidence and potential ethical risks in the responses of LLMs.</p><p><strong>Conclusions: </strong>Currently, compared to other LLMs, ChatGPT-E has demonstrated greater potential for application in educating Chinese patients with breast cancer, and may serve as an effective tool for them to obtain health information. However, for breast cancer specialists, these LLMs are not yet suitable for assisting in clinical diagnosis or treatment activities. Additionally, data security, ethical, and legal risks associated with using LLMs in clinical practice cannot be ignored. In the future, further research is needed to determine the true efficacy of LLMs in clinical scenarios related to breast cancer in China.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e66429"},"PeriodicalIF":3.1000,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Large Language Models as a Consulting Hotline for Patients With Breast Cancer and Specialists in China: Cross-Sectional Questionnaire Study.\",\"authors\":\"Hui Liu, Jialun Peng, Lu Li, Ao Deng, XiangXin Huang, Guobing Yin, Haojun Luo\",\"doi\":\"10.2196/66429\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The disease burden of breast cancer is increasing in China. Guiding people to obtain accurate information on breast cancer and improving the public's health literacy are crucial for the early detection and timely treatment of breast cancer. Large language model (LLM) is a currently popular source of health information. However, the accuracy and practicality of the breast cancer-related information provided by LLMs have not yet been evaluated.</p><p><strong>Objective: </strong>This study aims to evaluate and compare the accuracy, practicality, and generalization-specificity of responses to breast cancer-related questions from two LLMs, ChatGPT and ERNIE Bot (EB).</p><p><strong>Methods: </strong>The questions asked to the LLMs consisted of a patient questionnaire and an expert questionnaire, each containing 15 questions. ChatGPT was queried in both Chinese and English, recorded as ChatGPT-Chinese (ChatGPT-C) and ChatGPT-English (ChatGPT-E) respectively, while EB was queried in Chinese. The accuracy, practicality, and generalization-specificity of each inquiry's responses were rated by a breast cancer multidisciplinary treatment team using Likert scales.</p><p><strong>Results: </strong>Overall, for both the patient and expert questionnaire, the accuracy and practicality of responses from ChatGPT-E were significantly higher than those from ChatGPT-C and EB (all Ps<.001). However, the responses from all LLMs are relatively generalized, leading to lower accuracy and practicality for the expert questionnaire compared to the patient questionnaire. Additionally, there were issues such as the lack of supporting evidence and potential ethical risks in the responses of LLMs.</p><p><strong>Conclusions: </strong>Currently, compared to other LLMs, ChatGPT-E has demonstrated greater potential for application in educating Chinese patients with breast cancer, and may serve as an effective tool for them to obtain health information. However, for breast cancer specialists, these LLMs are not yet suitable for assisting in clinical diagnosis or treatment activities. Additionally, data security, ethical, and legal risks associated with using LLMs in clinical practice cannot be ignored. In the future, further research is needed to determine the true efficacy of LLMs in clinical scenarios related to breast cancer in China.</p>\",\"PeriodicalId\":56334,\"journal\":{\"name\":\"JMIR Medical Informatics\",\"volume\":\"13 \",\"pages\":\"e66429\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2025-05-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JMIR Medical Informatics\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.2196/66429\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MEDICAL INFORMATICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JMIR Medical Informatics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2196/66429","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICAL INFORMATICS","Score":null,"Total":0}
Large Language Models as a Consulting Hotline for Patients With Breast Cancer and Specialists in China: Cross-Sectional Questionnaire Study.
Background: The disease burden of breast cancer is increasing in China. Guiding people to obtain accurate information on breast cancer and improving the public's health literacy are crucial for the early detection and timely treatment of breast cancer. Large language model (LLM) is a currently popular source of health information. However, the accuracy and practicality of the breast cancer-related information provided by LLMs have not yet been evaluated.
Objective: This study aims to evaluate and compare the accuracy, practicality, and generalization-specificity of responses to breast cancer-related questions from two LLMs, ChatGPT and ERNIE Bot (EB).
Methods: The questions asked to the LLMs consisted of a patient questionnaire and an expert questionnaire, each containing 15 questions. ChatGPT was queried in both Chinese and English, recorded as ChatGPT-Chinese (ChatGPT-C) and ChatGPT-English (ChatGPT-E) respectively, while EB was queried in Chinese. The accuracy, practicality, and generalization-specificity of each inquiry's responses were rated by a breast cancer multidisciplinary treatment team using Likert scales.
Results: Overall, for both the patient and expert questionnaire, the accuracy and practicality of responses from ChatGPT-E were significantly higher than those from ChatGPT-C and EB (all Ps<.001). However, the responses from all LLMs are relatively generalized, leading to lower accuracy and practicality for the expert questionnaire compared to the patient questionnaire. Additionally, there were issues such as the lack of supporting evidence and potential ethical risks in the responses of LLMs.
Conclusions: Currently, compared to other LLMs, ChatGPT-E has demonstrated greater potential for application in educating Chinese patients with breast cancer, and may serve as an effective tool for them to obtain health information. However, for breast cancer specialists, these LLMs are not yet suitable for assisting in clinical diagnosis or treatment activities. Additionally, data security, ethical, and legal risks associated with using LLMs in clinical practice cannot be ignored. In the future, further research is needed to determine the true efficacy of LLMs in clinical scenarios related to breast cancer in China.
期刊介绍:
JMIR Medical Informatics (JMI, ISSN 2291-9694) is a top-rated, tier A journal which focuses on clinical informatics, big data in health and health care, decision support for health professionals, electronic health records, ehealth infrastructures and implementation. It has a focus on applied, translational research, with a broad readership including clinicians, CIOs, engineers, industry and health informatics professionals.
Published by JMIR Publications, publisher of the Journal of Medical Internet Research (JMIR), the leading eHealth/mHealth journal (Impact Factor 2016: 5.175), JMIR Med Inform has a slightly different scope (emphasizing more on applications for clinicians and health professionals rather than consumers/citizens, which is the focus of JMIR), publishes even faster, and also allows papers which are more technical or more formative than what would be published in the Journal of Medical Internet Research.