大语言模型在临床护理实践的潜在应用及障碍分析

doi:10.16460/j.issn1008-9969.2024.21.044

摘要/Abstract

摘要： 目的探讨大语言模型在临床护理实践的潜在应用,并分析其面临的障碍,为人工智能与护理实践的深度融合提供指引。方法检索国内外相关文献,分析大语言模型的基本特征,阐述其在临床护理中的潜在应用场景,并分析其应用过程中可能存在的风险与挑战。结果大语言模型在临床护理领域具有广阔的应用前景,主要包括：信息采集与文本书写;临床护理决策支持;智能问答与患者教育;虚拟临床护理助手;精准评估与护理等。然而,其应用也面临诸多障碍,包括数据安全风险、法律和伦理问题,以及数据偏见、模型“幻觉”、可解释性差及与临床护理需求匹配度欠佳等技术挑战。结论大语言模型技术有望重塑传统护理服务模式,推动临床护理向更加精准化、个性化和高效化的方向发展。未来需加强该技术在医疗健康领域应用的伦理治理、法律监管和垂直领域优化,以确保其在临床护理中的安全、合规、可控运用,最终造福人类健康福祉。

关键词: 大语言模型, 智能护理, 潜在应用, 障碍, 综述

中图分类号:

R47-05

李源, 罗碧如, Fu Mei R, 胡艳玲. 大语言模型在临床护理实践的潜在应用及障碍分析[J]. 护理学报, 2024, 31(21): 44-48.

参考文献

[1] 国家卫生健康委. 国家卫生健康委关于印发《全国护理事业发展规划(2021-2025年)》的通知[EB/OL]. [2024-10-17].https://www.gov.cn/zhengce/zhengceku/2022-05/09/content_5689354.htm.
[2] Webster P.Six ways large language models are changing healthcare[J]. Nat Med, 2023, 29(12):2969-2971. DOI:10.1038/s41591-023-02700-1.
[3] Woo B, Huynh T, Tang A, et al.Transforming nursing with large language models: from concept to practice[J]. Eur J Cardiovasc Nurs, 2024, 23(5):549-552. DOI:10.1093/eurjcn/zvad120.
[4] 胡杏娟, 梁业基, 高钰琳, 等. 生成式人工智能辅助混合式教学在实习护生皮内针技术感染预防教学中的应用[J]. 护理学报, 2024, 31(18):21-25. DOI:10.16460/j.issn1008-9969.2024.18.021.
[5] Singhal K, Azizi S, Tu T, et al.Large language models encode clinical knowledge[J]. Nature, 2023, 620(7972):172-180. DOI:10.1038/s41586-023-06455-0.
[6] 胡振生, 杨瑞, 朱嘉豪, 等. 大语言模型在医学领域的研究与应用发展[J]. 人工智能, 2023(4):10-19. DOI:10.16453/j.2096-5036.2023.04.002.
[7] Naveed H, Khan AU, Qiu S, et al.A comprehensive overview of large language models[EB/OL]. [2024-02-02].https://doi.org/10.48550/arXiv.2307.06435.
[8] Carlini N, Tramèr F, Brown T, et al.Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21)[C].USENIX Association, 2021.
[9] Kaplan J, McCandlish S, Henighan T, et al. Scaling laws for neural language models[EB/OL].[2024-02-02].https://doi.org/10.48550/arXiv.2001.08361.
[10] Mann B, Ryder N, Subbiah M, et al.Language models are few-shot learners[EB/OL].[2024-02-02].https://doi.org/10.48550/arXiv.2005.14165.
[11] Ding N, Qin Y, Yang G, et al.Parameter-efficient fine-tuning of large-scale pre-trained language models[J]. Nat Mach Intell,2023, 5(3):220-235.DOI:10.1038/s42256-023-00626-4.
[12] SEO.AI.GPT store statistics & facts: contains 159.000 of the 3 million created GPTs[EB/OL].[2024-02-03]. https://seo.ai/blog/gpt-store-statistics-facts.
[13] Wei J, Tay Y, Bommasani R, et al.Emergent abilities of large language models[EB/OL].[2024-02-04].https://doi.org/10.48550/arXiv.2206.07682.
[14] Webb T, Holyoak KJ, Lu H.Emergent analogical reasoning in large language models[J]. Nat Hum Behav, 2023, 7(9):1526-1541. DOI:10.1038/s41562-023-01659-w.
[15] Thirunavukarasu AJ, Ting DSJ, Elangovan K, et al.Large language models in medicine[J]. Nat Med, 2023, 29(8): 1930-1940. DOI:10.1038/s41591-023-02448-8.
[16] Patel SB, Lam K.ChatGPT: the future of discharge summaries?[J]. Lancet Digit Health, 2023, 5(3):e107-e108. DOI:10.1016/S2589-7500(23)00021-3.
[17] Okaisu EM, Kalikwani F, Wanyana G, et al.Improving the quality of nursing documentation: an action research project[J]. Curationis, 2014, 37(2):E1-11. DOI:10.4102/curationis.v37i2.1251.
[18] Nayak A, Alkaitis MS, Nayak K, et al.Comparison of history of present illness summaries generated by a chatbot and senior internal medicine residents[J]. JAMA Intern Med, 2023,183(9):1026-1027.DOI:10.1001/jamainternmed.
[19] Liu S, Wright AP, Patterson BL, et al. Assessing the value of ChatGPT for clinical decision support optimization[DB/OL].[2024-02-05].https://doi.org/10.1101/2023.02.21.23286254.
[20] 马武仁, 弓孟春, 戴辉, 等. 以ChatGPT为代表的大语言模型在临床医学中的应用综述[J].医学信息学杂志, 2023, 44(7):9-17. DOI:10.3969/j.issn.1673-6036.2023.07.002.
[21] Nashwan AJ, Abujaber AA.Harnessing large language models in nursing care planning: opportunities, challenges, and ethical considerations[J]. Cureus, 2023, 15(6): e40542. DOI:10.7759/cureus.40542.
[22] Dağcı M, Çam F, Dost A.Reliability and quality of the nursing care planning texts generated by ChatGPT[J]. Nurse Educ, 2024, 49(3):E109-E114. DOI:10.1097/NNE.0000000000001566.
[23] Jiang LY, Liu XC, Nejatian NP, et al.Health system-scale language models are all-purpose prediction engines[J]. Nature, 2023, 619(7969):357-362. DOI:10.1038/s41586-023-06160-y.
[24] Ayers JW, 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.
[25] Moons P, Van Bulck L.Using ChatGPT and Google Bard to improve the readability of written patient information: A proof-of-concept[J]. Eur J Cardiovasc Nurs, 2024, 23(2):122-126. DOI:10.1093/eurjcn/zvad087.
[26] 陈洁, 孟庆童, 刘惊今, 等. 基于指南的慢性心力衰竭患者运动康复科普手册研制[J]. 护理学报, 2024, 31(9):36-41. DOI:10.16460/j.issn1008-9969.2024.09.036
[27] HealthGPT Inc. The first safety focused LLM for healthcare[EB/OL].[2024-02-05]. https://www.hippocraticai.com/.
[28] 徐雪芬, 王红燕, 郭萍萍, 等. 人工智能在慢性病患者健康管理中的应用进展[J]. 中华护理杂志, 2023, 58(9):1063-1067. DOI:10.3761/j.issn.0254-1769.2023.09.006.
[29] 夏浩然, 陈小艳, 赵慧明, 等. 搭载ChatGPT的人工机械瓣膜置换术后患者自我监测随访大数据平台的建设与实践[J]. 中国实用护理杂志, 2023, 39(29):2276-2284. DOI:10.3760/cma.j.cn211501-20230328-00746.
[30] Kataoka Y, Takemura T, Sasajima M, et al.Development and early feasibility of chatbots for educating patients with lung cancer and their caregivers in Japan: mixed methods study[J]. JMIR Cancer, 2021, 7(1):e26911. DOI:10.2196/26911.
[31] Liu J, Wang C, Liu S.Utility of ChatGPT in clinical practice[J]. J Med Internet Res, 2023, 25:e48568. DOI:10.2196/48568.
[32] Qiu J, Han W, Zhu J, et al.Transfer knowledge from natural language to electrocardiography: can we detect cardiovascular disease through language models? [DB/OL]. [2024-02-06].https://doi.org/10.48550/arXiv.2301.09017.
[33] Nashwan AJ,Bani Hani S.Enhancing oncology nursing care planning for patients with cancer through harnessing large language models[J]. Asia Pac J Oncol Nurs, 2023, 10(9):100277. DOI:10.1016/j.apjon.2023.100277.
[34] Fu MR, 田亚丽, 冯先琼, 等. 精准护理的应用领域及发展方向[J]. 中华护理杂志, 2017, 52(10):1273-1275. DOI:10.3761/j.issn.0254-1769.2017.10.025.
[35] 李源, 周宗蓉, 罗碧如. 精准医学视域下护理专业实践的革新与展望[J]. 护理学杂志, 2020, 35(18):107-110. DOI:10.3870/j.issn.1001-4152.2020.18.107.
[36] Poon H, Naumann T, Zhang S, et al.Precision health in the age of large language models: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining[C]. New York: Association for Computing Machinery, 2023. DOI:10.1145/3580305.3599568.
[37] 颜见智, 何雨鑫, 骆子烨, 等. 生成式大语言模型在医疗领域的潜在典型应用与面临的挑战[J].医学信息学杂志, 2023, 44(9):23-31. DOI:10.3969/j.issn.1673-6036.2023.09.003.
[38] World Health Organization.Ethics and governance of artificial intelligence for health[EB/OL]. [2024-10-18].https://www.who.int/publications/i/item/9789240029200.
[39] 郭彩霞, 郭彩旭, 史晓宁, 等. ChatGPT赋能护理实践:前景、风险及对策[J]. 协和医学杂志, 2023, 14(6):1170-1174. DOI:10.12290/xhyxzz.2023-0326.
[40] Huang L, Yu W, Ma W, et al.A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions[DB/OL]. [2024-02-06].https://doi.org/10.48550/arXiv.2311.05232.
[41] Zhang R, Du H, Liu Y, et al.Interactive AI with retrieval-augmented generation for next generation networking[DB/OL]. [2024-02-06].https://arxiv.org/html/2401.11391v1.

Metrics

Viewed

Full text

Abstract

Cited

Shared