ChatGPT在全科临床实践中的新机遇与挑战

李佳汶; 易珊烨; 马婧馨; 冯嘉; 周伊恒; 赵茜; 雷弋; 袁波; 贾禹; 廖晓阳

doi:10.16766/j.cnki.issn.1674-4152.004476

ChatGPT在全科临床实践中的新机遇与挑战

doi: 10.16766/j.cnki.issn.1674-4152.004476

李佳汶¹,
易珊烨¹,
马婧馨¹,
冯嘉¹,
周伊恒¹,
赵茜¹,
雷弋¹,
袁波¹,
贾禹¹,
廖晓阳^{1, 2, ,}

1.
四川大学华西医院全科医学中心全科医学研究室，四川成都 610041
2.
四川大学华西医院全科医学中心全科特需病房

基金项目:

四川省科技计划项目 2023YFS0027

四川省科技计划项目 2023NSFSC1652

四川大学华西临床医学院、华西医院“启明星”青年人才科研启动基金 HXQMX0139

详细信息

通讯作者:
廖晓阳，E-mail：625880796@qq.com

中图分类号: R499
计量
- 文章访问数: 25
- HTML全文浏览量: 13
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2025-06-04
- 网络出版日期: 2026-10-23

New opportunities and challenges of ChatGPT in general clinical practice

1.
Department of General Practice Center, West China Hospital of Sichuan University, Chengdu, Sichuan 610041, China

摘要

摘要: ChatGPT是OpenAI于2022年11月30日推出的一款基于GPT-3的大型预训练语言模型。凭借丰富的数据训练经验和强大的语言处理能力，ChatGPT在语言理解的准确性、全面性和灵活性方面表现出色，尤其在医学领域的医患沟通和预防保健方面展现出巨大潜力。全科医学具有基层医疗、预防保健、以患者为中心的照顾、综合保健、持续照顾和社区保健的3P3C特点，而ChatGPT在这些方面均展现出强大的应用潜力，例如提供健康信息和诊断建议、制定个性化治疗方案、支持慢病管理等。然而，ChatGPT的应用也面临诸多挑战，例如数据偏见与准确性问题、知识更新滞后性问题、伦理和隐私问题等。因此，未来在全科医学中应用ChatGPT时，需优化伦理法律框架，加快本地化部署，提升技术与数据质量，确保其安全有效应用。鉴于ChatGPT有助于在社区环境下改进医患沟通、促进健康教育普及、辅助医疗诊断等，作者结合自身应用体验和医学领域相关文献，系统性地探讨了ChatGPT在全科医学临床实践中的应用潜力和研究进展，展望了其未来发展趋势，并分析了可能面临的问题和挑战。希望以ChatGPT为代表的大语言模型的未来应用和推进能促进全科医学学科发展。
- ChatGPT /
- 全科医学 /
- 临床实践
Abstract: ChatGPT is a large-scale pretrained language model based on GPT-3 launched by OpenAI on November 30, 2022. Owing to its extensive training data and powerful language processing capabilities, ChatGPT demonstrates high accuracy, comprehensiveness, and flexibility in language understanding, showing considerable potential in medical applications, particularly in doctor-patient communication and preventive healthcare. General practice medicine is characterized by the "3P3C" framework, encompassing primary healthcare, preventive healthcare, patient-centered care, comprehensive healthcare, continuous care, and community healthcare. ChatGPT has shown significant potential in these areas, such as providing health information and diagnostic advice, assisting in the development of personalized treatment plans, and supporting chronic disease management. However, the application of ChatGPT also faces many challenges, such as data bias, accuracy limitations, delays in knowledge updates, and ethical and privacy issues, etc. Therefore, future integration of ChatGPT into general practice requires improvements in ethical and legal framework, acceleration of localized deployment, and enhancement of data quality and technological reliability to ensure safe and effective application. Given its potential to improve doctor-patient communication, promote health education, and assist in medical diagnosis in community settings, this study systematically explores the applications and research progress of ChatGPT in the clinical practice, drawing on practical experience and relevant literature in the medical field. It also examines future development trends and provides a preliminary analysis of potential challenges. The broader adoption and implementation of large language models, represented by ChatGPT, may further advance the development of general medicine.
- ChatGPT /
- General practice /
- Clinical practice

HTML全文

图 1 ChatGPT在全科医学医教研中的应用与挑战概览

Figure 1. Overview of the applications and challenges of ChatGPT in general practice medicine, education, research

下载: 全尺寸图片幻灯片

参考文献(50)

[1]	于晓松. 新中国成立70年以来中国全科医学发展与展望[J]. 中华全科医学, 2019, 17(11): 1797-1799. doi: 10.16766/j.cnki.issn.1674-4152.001058 YU X S. The development and prospect of Chinese general practice since the founding of new China 70 years ago[J]. Chinese Journal of General Practice, 2019, 17(11): 1797-1799. doi: 10.16766/j.cnki.issn.1674-4152.001058
[2]	GUPTA R, SRIVASTAVA D, SAHU M, et al. Artificial intelligence to deep learning: machine intelligence approach for drug discovery[J]. Mol Divers, 2021, 25(3): 1315-1360. doi: 10.1007/s11030-021-10217-3
[3]	GAUTIER T, ZIEGLER L B, GERBER M S, et al. Artificial intelligence and diabetes technology: a review[J]. Metabolism, 2021, 124: 154872. DOI: 10.1016/j.metabol.2021.154872.
[4]	LEE D, YOON S N. Application of artificial intelligence-based technologies in the healthcare industry: opportunities and challenges[J]. Int J Environ Res Public Health, 2021, 18(1): 271. doi: 10.3390/ijerph18010271
[5]	WANG X, HE X, WEI J, et al. Application of artificial intelligence to the public health education[J]. Front Public Health, 2023, 10: 1087174. DOI: 10.3389/fpubh.2022.1087174.
[6]	ZHANG K Z. ChatGPT: optimizing language models for dialogue[EB/OL]. (2022-12-22)[2025-10-28]. https://kpzhang.github.io/report/ChatGPT-KZ-Feb2023.pdf.
[7]	MOONS P, VAN BULCK L. ChatGPT: can artificial intelligence language models be of value for cardiovascular nurses and allied health professionals[J]. Eur J Cardiovasc Nurs, 2023, 22(7): e55-e59. doi: 10.1093/eurjcn/zvad022
[8]	GIRAY L. Prompt engineering with ChatGPT: a guide for academic writers[J]. Ann Biomed Eng, 2023, 51(12): 2629-2633. doi: 10.1007/s10439-023-03272-4
[9]	ABD-ALRAZAQ A, ALSAAD R, ALHUWAIL D, et al. Large language models in medical education: opportunities, challenges, and future directions[J]. JMIR Med Educ, 2023, 9(1): e48291. DOI: 10.2196/48291.
[10]	WU J, MA Y, WANG J, et al. The application of ChatGPT in medicine: a scoping review and bibliometric analysis[J]. J Multidiscip Healthc, 2024, 17: 1681-1692. doi: 10.2147/JMDH.S463128
[11]	BASHSHUR R L, HOWELL J D, KRUPINSKI E A, et al. The empirical foundations of telemedicine interventions in primary care[J]. Telemed J E Health, 2016, 22(5): 342-375. doi: 10.1089/tmj.2016.0045
[12]	JOHNSON D, GOODMAN R, PATRINELY J, et al. Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model[J]. Res Sq, 2023. DOI: 10.21203/rs.3.rs-2566942/v1.
[13]	DAVIS R, EPPLER M, AYO-AJIBOLA O, et al. Evaluating the effectiveness of artificial intelligence-powered large language models application in disseminating appropriate and readable health information in urology[J]. J Urol, 2023, 210(4): 688-694. doi: 10.1097/JU.0000000000003615
[14]	ZHENG Y, SUN X, FENG B, et al. Rare and complex diseases in focus: ChatGPT's role in improving diagnosis and treatment[J]. Front Artif Intell, 2024, 7: 1338433. DOI: 10.3389/frai.2024.1338433.
[15]	SHIKINO K, SHIMIZU T, OTSUKA Y, et al. Evaluation of ChatGPT-generated differential diagnosis for common diseases with atypical presentation: descriptive research[J]. JMIR Med Educ, 2024, 10: e58758. DOI: 10.2196/58758.
[16]	VAIRA L A, LECHIEN J R, ABBATE V, et al. Accuracy of ChatGPT-generated information on head and neck and oromaxillofacial surgery: a multicenter collaborative analysis[J]. Otolaryngol Head Neck Surg, 2024, 170(6): 1492-1503. doi: 10.1002/ohn.489
[17]	AYO-AJIBOLA O, JULIEN C, LIN M E, et al. Association of primary care access with health-related ChatGPT use: a national cross-sectional survey[J]. J Gen Intern Med, 2025. DOI: 10.1007/s11606-025-09406-9.
[18]	GUNESLI I, AKSUN S, FATHELBAB J, et al. Comparative evaluation of ChatGPT-4, ChatGPT-3.5 and Google Gemini on PCOS assessment and management based on recommendations from the 2023 guideline[J]. Endocrine, 2025, 88(1): 315-322.
[19]	BALAS M, MANDELCORN E D, YAN P, et al. ChatGPT and retinal disease: a cross-sectional study on AI comprehension of clinical guidelines[J]. Can J Ophthalmol, 2025, 60(1): e117-e123. doi: 10.1016/j.jcjo.2024.06.001
[20]	STEPHENS T N, JOERIN A, RAUWS M, et al. Feasibility of pediatric obesity and prediabetes treatment support through tess, the AI behavioral coaching chatbot[J]. Transl Behav Med, 2019, 9(3): 440-447. doi: 10.1093/tbm/ibz043
[21]	BILAL M, JAMIL Y, RANA D, et al. Enhancing awareness and self-diagnosis of obstructive sleep apnea using AI-powered Chatbots: the role of ChatGPT in revolutionizing healthcare[J]. Ann Biomed Eng, 2024, 52(2): 136-138. doi: 10.1007/s10439-023-03298-8
[22]	DEIANA G, DETTORI M, ARGHITTU A, et al. Artificial intelligence and public health: evaluating ChatGPT responses to vaccination myths and misconceptions[J]. Vaccines, 2023, 11(7): 1217. DOI: 10.3390/vaccines11071217.
[23]	GHANEM D, SHU H, BERGSTEIN V, et al. Educating patients on osteoporosis and bone health: can "ChatGPT" provide high-quality content?[J]. Eur J Orthop Surg Traumatol, 2024, 34(5): 2757-2765. doi: 10.1007/s00590-024-03990-y
[24]	KATTIH M, BRESSLER M, SMITH L R, et al. Artificial intelligence-prompted explanations of common primary care diagnoses[J]. PRiMER, 2024, 8: 51. DOI: 10.22454/PRiMER.2024.916089.
[25]	CHANDRA K, GHILZAI U, LAWAND J, et al. Improving Readability of shoulder and elbow surgery online patient education material with Chat Generative Pretrained Transformer (ChatGPT) 4[J]. J Shoulder Elbow Surg, 2025, 34(11): e1119-e1124. doi: 10.1016/j.jse.2025.02.025
[26]	CONSTAND M K, MACDERMID J C, DAL BELLO-HAAS V, et al. Scoping review of patient-centered care approaches in healthcare[J]. BMC Health Serv Res, 2014, 14(1): 271. doi: 10.1186/1472-6963-14-271
[27]	AYERS J W, POLIAK A, DREDZE M, et al. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum[J]. JAMA Intern Med, 2023, 183(6): 589-596. doi: 10.1001/jamainternmed.2023.1838
[28]	STENZL A, ARMSTRONG A J, ROGERS E, et al. Evaluation of ChatGPT as a reliable source of medical information on prostate cancer for patients: global comparative survey of medical oncologists and urologists[J]. Urol Pract, 2025, 12(2): 229-240. doi: 10.1097/UPJ.0000000000000740
[29]	OANDASAN I F, ARCHIBALD D, AUTHIER L, et al. Future practice of comprehensive care: practice intentions of exiting family medicine residents in Canada[J]. Can Fam Physician, 2018, 64(7): 520-528.
[30]	ALLAHQOLI L, GHIASVAND M M, MAZIDIMORADI A, et al. Diagnostic and management performance of ChatGPT in obstetrics and gynecology[J]. Gynecol Obstet Invest, 2023, 88(5): 310-313. doi: 10.1159/000533177
[31]	RAHSEPAR A A, TAVAKOLI N, KIM G H J, et al. How AI responds to common lung cancer questions: ChatGPT versus Google Bard[J]. Radiology, 2023, 307(5): e230922. DOI: 10.1148/radiol.230922.
[32]	AL-ANEZI F M. Exploring the use of ChatGPT as a virtual health coach for chronic disease management[J]. Learn Health Syst, 2024, 8(3): e10406. DOI: 10.1002/lrh2.10406.
[33]	AKDOGAN O, UYAR G C, YESILBAS E, et al. Effect of a ChatGPT-based digital counseling intervention on anxiety and depression in patients with cancer: a prospective, randomized trial[J]. Eur J Cancer, 2025, 221: 115408. DOI: 10.1016/j.ejca.2025.115408.
[34]	FERDUSH J, BEGUM M, HOSSAIN S T. ChatGPT and clinical decision support: scope, application, and limitations[J]. Ann Biomed Eng, 2024, 52(5): 1119-1124. doi: 10.1007/s10439-023-03329-4
[35]	LIU S, WRIGHT A P, PATTERSON B L, et al. Assessing the Value of ChatGPT for clinical decision support optimization. medRxiv[Preprint]. 2023. DOI: 10.1101/2023.02.21.23286254.
[36]	FREEMAN G K, OLESEN F, HJORTDAHL P. Continuity of care: an essential element of modern general practice?[J]. Fam Pract, 2003, 20(6): 623-627. doi: 10.1093/fampra/cmg601
[37]	ROSENBERG G S, MAGNÉLI M, BARLE N, et al. ChatGPT-4 generates orthopedic discharge documents faster than humans maintaining comparable quality: a pilot study of 6 cases[J]. Acta Orthop, 2024, 95: 152-156. doi: 10.2340/17453674.2024.40182
[38]	IQBAL U, TANWEER A, RAHMANTI A R, et al. Impact of large language model (ChatGPT) in healthcare: an umbrella review and evidence synthesis[J]. J Biomed Sci, 2025, 32(1): 45. DOI: 10.1186/s12929-025-01131-z.
[39]	ALI S R, DOBBS T D, HUTCHINGS H A, et al. Using ChatGPT to write patient clinic letters[J]. Lancet Digit Health, 2023, 5(4): e179-e181. doi: 10.1016/S2589-7500(23)00048-1
[40]	RAO A, PANG M, KIM J, et al. Assessing the utility of ChatGPT throughout the entire clinical workflow: development and usability study[J]. J Med Internet Res, 2023, 25: e48659. DOI: 10.2196/48659.
[41]	KUSH J C. Integrating sensor technologies with conversational AI: enhancing context-sensitive interaction through real-time data fusion[J]. Sensors, 2025, 25(1): 249. DOI: 10.3390/s25010249.
[42]	AYDIN S, KARABACAK M, VLACHOS V, et al. Large language models in patient education: a scoping review of applications in medicine[J]. Front Med, 2024, 11: 1477898. DOI: 10.3389/fmed.2024.1477898.
[43]	GILLEARD C, HYDE M, HIGGS P. Community and communication in the third age: the impact of internet and cell phone use on attachment to place in later life in England[J]. J Gerontol B Psychol Sci Soc Sci, 2007, 62(4): S276-S283. doi: 10.1093/geronb/62.4.S276
[44]	LOVEDAY M, WALLENGREN K, BRUST J, et al. Community-based care vs. centralised hospitalisation for MDR-TB patients, KwaZulu-Natal, South Africa[J]. Int J Tuberc Lung Dis, 2015, 19(2): 163-171. doi: 10.5588/ijtld.14.0369
[45]	SINGH O P. Artificial intelligence in the era of ChatGPT-Opportunities and challenges in mental health care[J]. Indian J Psychiatry, 2023, 65(3): 297-298. doi: 10.4103/indianjpsychiatry.indianjpsychiatry_112_23
[46]	IMRAN N, HASHMI A, IMRAN A. Chat-GPT: opportunities and challenges in child mental healthcare[J]. Pak J Med Sci, 2023, 39(4): 1191-1193.
[47]	BRANT-ZAWADZKI G, KLAPTHOR B, RYBA C, et al. The performance of ChatGPT-4 and Gemini Ultra 1.0 for quality assurance review in emergency medical services chest pain calls[J]. Prehosp Emerg Care, 2025, 29(3): 210-217. doi: 10.1080/10903127.2024.2376757
[48]	WANG C, LIU S, YANG H, et al. Ethical considerations of using ChatGPT in health care[J]. J Med Internet Res, 2023, 25: e48009. DOI: 10.2196/48009.
[49]	CASALS-FARRE O, BASKARAN R, SINGH A, et al. Assessing ChatGPT 4.0's capabilities in the United Kingdom medical licensing examination (UKMLA): a robust categorical analysis[J]. Sci Rep, 2025, 15(1): 13031. DOI: 10.1038/s41598-025-97327-2.
[50]	ARIYARATNE S, IYENGAR K P, NISCHAL N, et al. A comparison of ChatGPT-generated articles with human-written articles[J]. Skeletal Radiol, 2023, 52(9): 1755-1758. doi: 10.1007/s00256-023-04340-5