Downloads
Download
ChatGPT赋能患者教育: 现状评估、热点洞察和未来展望. (2025). 环球医学研究, 2(2), 25-31. https://doi.org/10.62836/
Copyright (c) 2025 曾健文，朱徐乐，曹世华，周诗颖，张鑫瑜，贾宇阳
This work is licensed under a Creative Commons Attribution 4.0 International License.
ChatGPT赋能患者教育: 现状评估、热点洞察和未来展望
曾健文#，朱徐乐#，曹世华*，周诗颖，张鑫瑜，贾宇阳
杭州师范大学公共卫生与护理学院，浙江杭州
摘要：目的：分析ChatGPT应用于患者教育研究的发展现状，当前热点以及未来研究趋势。方法：通过VOSviewer和Citespace软件对该领域文章的年度分布、期刊、国家、作者及关键词进行可视化分析。结果：共纳入343篇文献，发表于223种期刊，涉及51个国家，共2027位作者。该领域发文量呈上升趋势， 近2年发文量迅速增加。使用ChatGPT生成患者教育材料、提高教育材料可读性以及回答患者常见问题为研究热点。结论：在患者教育中使用ChatGPT得到广泛关注，研究热度将继续保持。ChatGPT可以作为医疗专业人员用于患者教育的辅助工具，在未来，还需进一步研究以提升聊天机器人的安全可靠性。
参考文献
[1] Liu JL, Wang CY, Liu SR. Utility of ChatGPT in Clinical Practice. Journal of Medical Internet Research. 2023;25. doi: 10.2196/48568.
[2] Abdel-Messih MS, Boulos MNK. ChatGPT in Clinical Toxicology. Jmir Medical Education. 2023;9. doi: 10.2196/46876.
[3] Meng XB, Yan XY, Zhang K, Liu D, Cui XJ, Yang YD, et al. The application of large language models in medicine: A scoping review. Iscience. 2024;27(5). doi: 10.1016/j. isci.2024.109713.
[4] Seth I, Lim B, Xie Y, Cevik J, Rozen WM, Ross RJ, et al. Comparing the Efficacy of Large Language Models ChatGPT, BARD, and Bing AI in Providing Information on Rhinoplasty: An Observational Study. Aesthetic Surgery Journal Open Forum. 2023;5. doi: 10.1093/asjof/ojad084.
[5] Yang AL, Reid M, Nguyen AM, Nallasamy S, Velez FG, Campomanes AGD, et al. Quality and Readability of Patient Educational Materials Generated by ChatGPT-4o for Pediatric Ophthalmologic Surgeries. Journal of Pediatric Ophthalmology & Strabismus. 2025. doi: 10.3928/01913913- 20250404-01.
[6] Will J, Gupta M, Zaretsky J, Dowlath A, Testa P, Feldman J. Enhancing the Readability of Online Patient Education Materials Using Large Language Models: Cross-Sectional Study. Journal of Medical Internet Research. 2025;27. doi: 10.2196/69955.
[7] Özbek EA, Ertan MB, Kindan P, Karaca MO, Gürsoy S, Chahla J. ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy. Arthroscopy-the Journal of Arthroscopic and Related Surgery. 2025;41(6):1806-27. doi: 10.1016/j.arthro.2024.08.036.
[8] Tan S, Xin X, Wu D. ChatGPT in medicine: prospects and challenges: a review article. International Journal of Surgery. 2024;110(6):3701-6. doi: 10.1097/js9.0000000000001312.
[9] Shukla IY, Sun MZ. Online and ChatGPT-generated patient education materials regarding brain tumor prognosis fail to meet readability standards. Journal of Clinical Neuroscience. 2025;138. doi: 10.1016/j.jocn.2025.111410.
[10] Gao YW, Xu Q, Zhang O, Wang HL, Wang YL, Wang JL, et al. Large language models: unlocking new potential in patient education for thyroid eye disease. Endocrine. 2025. doi: 10.1007/s12020-025-04339-z.
[11] Nian PP, Williams CJ, Senthilnathan IS, Marsh IG, Jones RH, Palandjian PL, et al. Currently Available Large Language Models Are Moderately Effective in Improving Readability of English and Spanish Patient Education Materials in Pediatric Orthopaedics. Journal of the American Academy of Orthopaedic Surgeons. 2025;33(15):e888-e97. doi: 10.5435/ jaaos-d-25-00267.
[12] Delsoz M, Hassan A, Nabavi A, Rahdar A, Fowler B, Kerr NC, et al. Large Language Models: Pioneering New Educational Frontiers in Childhood Myopia. Ophthalmology and Therapy. 2025;14(6):1281-95. doi: 10.1007/s40123-025-01142-x.
[13] Chavda H, Sontam TR, Skinner WC, Ingall EM, Zide JR. Comparison of Responses from ChatGPT-4, Google Gemini, and Google Search to Common Patient Questions About Ankle Sprains: A Readability Analysis. Journal of the American Academy of Orthopaedic Surgeons. 2025;33(16):924-30. doi: 10.5435/jaaos-d-25-00260.
[14] Taskum I, Sinaci S, Aslan F, Taskum GM, Sucu S. Assessment of readability, reliability, and quality of large language models in addressing frequently asked questions regarding prenatal screening for fetal chromosomal anomalies. International Journal of Gynecology & Obstetrics. 2025. doi: 10.1002/ ijgo.70348.
[15] Özcivelek T, Özcan B. Comparative evaluation of responses from DeepSeek-R1, ChatGPT-o1, ChatGPT-4, and dental GPT chatbots to patient inquiries about dental and maxillofacial prostheses. Bmc Oral Health. 2025;25(1). doi: 10.1186/s12903-025-06267-w.
[16] Eravsar NB, Aydin M, Eryilmaz A, Turemis C, Surucu S, Jimenez AE. Is ChatGPT a more academic source than google searches for patient questions about hip arthroscopy? An analysis of the most frequently asked questions. Journal of Isakos Joint Disorders & Orthopaedic Sports Medicine. 2025;12. doi: 10.1016/j.jisako.2025.100892.
[17] Akçay O, Özturk Ö, Acar T, Gürsoy S. Accuracy and Reliability of ChatGPT in Answering Patient Questions About Lung Cancer and Its Surgery: An Expert Panel Evaluation by Thoracic Surgeons. Journal of Cancer Education. 2025 Jul. doi: 10.1007/s13187-025-02682-3.
[18] Michalska AA, Stefaniak MM, Gotlib-Malkowska J. Can ChatGPT Provide Patient-Friendly and Reliable Information on Cervical Cancer Screening? A Study of ChatGPT-Generated Information in Polish. Medical Science Monitor. 2025;31:e947992. doi: 10.12659/msm.947992.
[19] Garcia LG, Emile SH, Linkeshwaran L, Wignakumar A, Wexner SD. A literature review on the role of artificial intelligence- based chatbots in patient education in colorectal surgery. Surgery. 2025;183. doi: 10.1016/j.surg.2025.109393.
[2] Abdel-Messih MS, Boulos MNK. ChatGPT in Clinical Toxicology. Jmir Medical Education. 2023;9. doi: 10.2196/46876.
[3] Meng XB, Yan XY, Zhang K, Liu D, Cui XJ, Yang YD, et al. The application of large language models in medicine: A scoping review. Iscience. 2024;27(5). doi: 10.1016/j. isci.2024.109713.
[4] Seth I, Lim B, Xie Y, Cevik J, Rozen WM, Ross RJ, et al. Comparing the Efficacy of Large Language Models ChatGPT, BARD, and Bing AI in Providing Information on Rhinoplasty: An Observational Study. Aesthetic Surgery Journal Open Forum. 2023;5. doi: 10.1093/asjof/ojad084.
[5] Yang AL, Reid M, Nguyen AM, Nallasamy S, Velez FG, Campomanes AGD, et al. Quality and Readability of Patient Educational Materials Generated by ChatGPT-4o for Pediatric Ophthalmologic Surgeries. Journal of Pediatric Ophthalmology & Strabismus. 2025. doi: 10.3928/01913913- 20250404-01.
[6] Will J, Gupta M, Zaretsky J, Dowlath A, Testa P, Feldman J. Enhancing the Readability of Online Patient Education Materials Using Large Language Models: Cross-Sectional Study. Journal of Medical Internet Research. 2025;27. doi: 10.2196/69955.
[7] Özbek EA, Ertan MB, Kindan P, Karaca MO, Gürsoy S, Chahla J. ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy. Arthroscopy-the Journal of Arthroscopic and Related Surgery. 2025;41(6):1806-27. doi: 10.1016/j.arthro.2024.08.036.
[8] Tan S, Xin X, Wu D. ChatGPT in medicine: prospects and challenges: a review article. International Journal of Surgery. 2024;110(6):3701-6. doi: 10.1097/js9.0000000000001312.
[9] Shukla IY, Sun MZ. Online and ChatGPT-generated patient education materials regarding brain tumor prognosis fail to meet readability standards. Journal of Clinical Neuroscience. 2025;138. doi: 10.1016/j.jocn.2025.111410.
[10] Gao YW, Xu Q, Zhang O, Wang HL, Wang YL, Wang JL, et al. Large language models: unlocking new potential in patient education for thyroid eye disease. Endocrine. 2025. doi: 10.1007/s12020-025-04339-z.
[11] Nian PP, Williams CJ, Senthilnathan IS, Marsh IG, Jones RH, Palandjian PL, et al. Currently Available Large Language Models Are Moderately Effective in Improving Readability of English and Spanish Patient Education Materials in Pediatric Orthopaedics. Journal of the American Academy of Orthopaedic Surgeons. 2025;33(15):e888-e97. doi: 10.5435/ jaaos-d-25-00267.
[12] Delsoz M, Hassan A, Nabavi A, Rahdar A, Fowler B, Kerr NC, et al. Large Language Models: Pioneering New Educational Frontiers in Childhood Myopia. Ophthalmology and Therapy. 2025;14(6):1281-95. doi: 10.1007/s40123-025-01142-x.
[13] Chavda H, Sontam TR, Skinner WC, Ingall EM, Zide JR. Comparison of Responses from ChatGPT-4, Google Gemini, and Google Search to Common Patient Questions About Ankle Sprains: A Readability Analysis. Journal of the American Academy of Orthopaedic Surgeons. 2025;33(16):924-30. doi: 10.5435/jaaos-d-25-00260.
[14] Taskum I, Sinaci S, Aslan F, Taskum GM, Sucu S. Assessment of readability, reliability, and quality of large language models in addressing frequently asked questions regarding prenatal screening for fetal chromosomal anomalies. International Journal of Gynecology & Obstetrics. 2025. doi: 10.1002/ ijgo.70348.
[15] Özcivelek T, Özcan B. Comparative evaluation of responses from DeepSeek-R1, ChatGPT-o1, ChatGPT-4, and dental GPT chatbots to patient inquiries about dental and maxillofacial prostheses. Bmc Oral Health. 2025;25(1). doi: 10.1186/s12903-025-06267-w.
[16] Eravsar NB, Aydin M, Eryilmaz A, Turemis C, Surucu S, Jimenez AE. Is ChatGPT a more academic source than google searches for patient questions about hip arthroscopy? An analysis of the most frequently asked questions. Journal of Isakos Joint Disorders & Orthopaedic Sports Medicine. 2025;12. doi: 10.1016/j.jisako.2025.100892.
[17] Akçay O, Özturk Ö, Acar T, Gürsoy S. Accuracy and Reliability of ChatGPT in Answering Patient Questions About Lung Cancer and Its Surgery: An Expert Panel Evaluation by Thoracic Surgeons. Journal of Cancer Education. 2025 Jul. doi: 10.1007/s13187-025-02682-3.
[18] Michalska AA, Stefaniak MM, Gotlib-Malkowska J. Can ChatGPT Provide Patient-Friendly and Reliable Information on Cervical Cancer Screening? A Study of ChatGPT-Generated Information in Polish. Medical Science Monitor. 2025;31:e947992. doi: 10.12659/msm.947992.
[19] Garcia LG, Emile SH, Linkeshwaran L, Wignakumar A, Wexner SD. A literature review on the role of artificial intelligence- based chatbots in patient education in colorectal surgery. Surgery. 2025;183. doi: 10.1016/j.surg.2025.109393.