[1]赵子涵,畅智慧.大语言模型对介入科及介入治疗的推荐作用[J].介入放射学杂志,2025,34(11):1204-1209.[doi:10.3969/j.issn.1008-794X.2025.11.007]
 ZHAO Zihan,CHANG Zhihui..The role of large language models in recommending intervention disciplines and interventional therapies[J].J Intervent Med,2025,34(11):1204-1209.[doi:10.3969/j.issn.1008-794X.2025.11.007]
点击复制

大语言模型对介入科及介入治疗的推荐作用()

PDF下载中关闭

《介入放射学杂志》[ISSN:1008-794X/CN:31-1796/R]

卷:
34
期数:
2025年11
页码:
1204-1209
栏目:
数字介入
出版日期:
2025-11-25

文章信息/Info

Title:
The role of large language models in recommending intervention disciplines and interventional therapies
文章编号:
1008-794X(2025)-011-1204-06
作者:
赵子涵 畅智慧
110004 辽宁沈阳 沈阳中国医科大学附属盛京医院放射科
Author(s):
ZHAO ZihanCHANG Zhihui.
Department of Radiology,Affiliated Shengjing Hospital,China Medical University,Shenyang,Liaoning Province 110004,China
关键词:
大语言模型 人工智能 介入治疗 介入放射学
分类号:
R-058
DOI:
10.3969/j.issn.1008-794X.2025.11.007
文献标志码:
A
摘要:
目的 探讨大语言模型对介入科及介入治疗的推荐情况。方法 选取Kimi k1.5、豆包、DeepSeek-R1、ChatGPT-4o 4种主流模型,针对18种介入科常见疾病设计标准化提问(“推荐科室”和“治疗方法”),通过3次重复测试收集推荐数据,采用SPSS 25.0进行统计学分析。结果 各大语言模型在一定程度上推荐介入科医生及其治疗方法,其中循环系统疾病中的下肢动脉闭塞和 Stanford B 型主动脉夹层分别在介入科及介入治疗中推荐率最高(100%),为前3位推荐,而前列腺增生推荐率最低,在介入科及介入治疗输出中均未被推荐。结论 大语言模型对介入科治疗循环系统疾病推荐度最高,泌尿与生殖系统疾病最低。模型训练数据需进一步强化介入科及其治疗方法的场景数据覆盖,逐步提升介入科的社会认知度。

参考文献/References:

[1] Thirunavakarasu AJ,Ting D SJ,Elangovan K,et al.Large language models in medicine[J].Nat Med,2023,29:1930-1940.
[2]Cascella M,Montomoli J,Bellini V,et al.Evaluating the feasibility of ChatGPT in healthcare:an analysis of multiple clinical and research scenarios[J].J Med Syst,2023,47:33.
[3]Choudhury A,Chaudhry B M Z.Large language models and user trust:consequence of self-referential learning loop and the deskilling of health care professionals[J].J Med Internet Res,2024,24:e56764.
[4]Choudhury A,Shamszare H.Investigating the impact of user trust on the adoption and use of ChatGPT:survey analysis[J].J Med Internet Res,2023,25:e47184.
[5]吴志远,程永德.数字介入——当介入放射学遇上数字医学[J].介入放射学杂志,2024,33:1-6.
Wu ZY,Cheng YD.Digital intervention:when interventional radiology meets digital medicine[J].J Intervent Radiol,2024,33:1-6.
[6]刘一廷,程 凌,吴志远.元宇宙在介入诊疗中的应用展望[J].介入放射学杂志,2025,34:123-128.
Liu YT,Cheng L,Wu ZY.Application prospect of the metaverse in interventional diagnosis and treatment[J].J Intervent Radiol,2025,34:123-128.
[7]Cross CG,Hofmann H L,Cangut B,et al.When does chat-GPT refer someone to an interventional radiologist?[J].J Vasc Interv Radiol,2025,36:355-357.
[8]国家卫生健康委员会.原发性肝癌诊疗指南(2024年版)[J].临床肝胆病杂志,2024,40:893-918.
NATIONAL HEALTH COMMISSION OF THE PEOPLE'S REPUBLIC OF CHINA.Clinical guidelines for diagnosis and treatment of primary liver cancer(2024 edition)[J].J Clin Hepatol,2024,40:893-918.
[9]Sangro B,Sarobe P,Kennedy A,et al.EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma[J].J Hepatol,2025,82:315-374.
[10]National Comprehensive Cancer Network.NCCN Clinical Practice Guidelines in Oncology(NCCN Guidelines):Hepatocellular Carcinoma(Version 1.2024)[EB/OL].https://www.nccn.org/guidelines/guidelines-detail?catego-ry=1&id=1514,2024-10-02.
[11]Singhal K,Azizi S,Tu T,et al.Large language models encode clinical knowledge[J].Nature,2023,620:172-180.
(收稿日期:2025-03-26)
(本文编辑:新 宇)

相似文献/References:

[1]刘凌晓,董 怡.人工智能技术在甲状腺结节诊断及预测淋巴结转移中的应用 [J].介入放射学杂志,2021,30(04):323.
 LIU Lingxiao,DONG Yi..Application of artificial intelligence technology in diagnosing thyroid nodules and predicting lymph node metastasis[J].J Intervent Med,2021,30(11):323.
[2]吴志远,程永德.数字介入——当介入放射学遇上数字医学[J].介入放射学杂志,2024,33(01):1.
 WU Zhiyuan,CHENG Yongde.Digital intervention: current status of the integration of digital medicine with interventional radiology[J].J Intervent Med,2024,33(11):1.
[3]杨子雨,朱锡雨,虞隽扬,等.人工智能在介入医学中的应用及前景[J].介入放射学杂志,2025,34(04):441.[doi:10.3969/j.issn.1008-794X.2025.04.019]
 YANG Ziyu,ZHU Xiyu,YU Juanyang,et al.Application and prospect of artificial intelligence in interventional medicine[J].J Intervent Med,2025,34(11):441.[doi:10.3969/j.issn.1008-794X.2025.04.019]
[4]王小泽,李 肖.从评分到人工智能——经颈静脉肝内门体分流术后肝性脑病预测的演变与挑战[J].介入放射学杂志,2025,34(05):449.[doi:10.3969/j.issn.1008-794X.2025.05.001]
 WANG Xiaoze,LI Xiao.Department of Gastroenterology,West China Hospital,et al.From scoring to artificial intelligence:the evolution and challenges in predicting hepatic encephalopathy after TIPS[J].J Intervent Med,2025,34(11):449.[doi:10.3969/j.issn.1008-794X.2025.05.001]
[5]闵一斐,秦永林.人工智能在主动脉夹层腔内修复术预后评估中的应用[J].介入放射学杂志,2025,34(10):1039.[doi:10.3969/j.issn.1008-794X.2025.10.001]
 MIN Yifei,QIN Yonglin..Application of artificial intelligence in assessing the prognosis of patients with aortic dissection after receiving endovascular repair[J].J Intervent Med,2025,34(11):1039.[doi:10.3969/j.issn.1008-794X.2025.10.001]
[6]祝 琳,马婧嶔,瞿旭东,等.人工智能时代下的介入放射学重塑:从辅助工具到范式变革的跨学科跃迁[J].介入放射学杂志,2026,(02):228.[doi:10.3969/j.issn.1008-794X.2026.02.019 ]
 ZHU Lin,MA Jingqin,QU Xudong,et al.Reshaping interventional radiology in the AI era:from auxiliary tools to paradigm changer via interdisciplinary integration[J].J Intervent Med,2026,(11):228.[doi:10.3969/j.issn.1008-794X.2026.02.019 ]

备注/Memo

备注/Memo:
通信作者: 畅智慧 E-mail:changzh@sj-hospital.org
更新日期/Last Update: 2025-11-25