首页 > 过刊浏览>2024年第45卷第9期 >大语言模型在医疗领域的前沿研究与创新应用
PDF HTML阅读 XML下载 导出引用 引用提醒
大语言模型在医疗领域的前沿研究与创新应用
作者:
作者单位:

(1.浙江大学医学院附属妇产科医院 杭州 310006;2.浙江大学软件学院 杭州 310015;3.人民卫生出版社有限公司 北京 100021;4.浙江省妇科重大疾病精准诊治研究重点实验室 杭州 310006;5.国家卫生健康委卫生发展研究中心 北京 100032)

作者简介:

何剑虎,高级工程师,发表论文30余篇；通信作者:游茂,汪辉。

中图分类号:

R-058

基金项目:

浙江省“尖兵”“领雁”研发攻关计划项目(项目编号:2023C03101)。


The Frontier Research and Innovative Applications of Large Language Models in the Medical Field
Author:
Affiliation:

(1.Women〖DK〗’s Hospital, School of Medicine, Zhejiang University，Hangzhou 310006, China; 2.School of Software Technology, Zhejiang University，Hangzhou 310015, China; 3.People〖DK〗’s Medical Publishing House，Beijing 100021, China; 4 .Zhejiang Provincial Key Laboratory for Precision Diagnosis and Treatment of Major Gynecological Diseases，Hangzhou 310006, China;5. China National Health Development Research Center，Beijing 100032, China)

  • 摘要
  • 访问统计
  • 参考文献 [1]
  • 相似文献 [20]
  • 文章评论
    摘要:

    目的/意义 系统梳理大语言模型在医疗领域的应用与研究进展,分析关键挑战与机遇,为相关研究提供参考。方法/过程 采用系统性文献回顾方法,全面梳理近年来发表的相关文献,聚焦医疗大语言模型最新进展；分析大语言模型在医疗自然语言处理任务中的应用成效、研究现状以及面临的挑战。结果/结论 大语言模型在医疗领域应用前景广阔,未来研究重点应集中在技术进步与伦理规范完善等方面。一方面加速技术创新步伐,另一方面确保严格遵守伦理标准,共同促进医疗领域大语言模型技术可持续发展。

    Abstract:

    Purpose/Significance The paper systematically reviews the application and research progress of large language models (LLMs) in the medical field, analyzes the key challenges and opportunities, and provides references for related research. Method/Process The systematic literature review method is adopted to comprehensively review the relevant literature published in recent years, focusing on the latest progress of medical LLMs. The application results, research status and challenges of LLMs in medical natural language processing (NLP) tasks are analyzed. Result/Conclusion The application of LLMs in the medical field has a broad prospect, and the future research should focus on the technical progress and the improvement of ethical norms. On the one hand, the pace of technological innovation should be accelerated, and on the other hand, strict compliance with ethical standards should be ensured to jointly promote the sustainable development of LLMs technology in the medical field.

    参考文献
    1 VASWANI A, SHAZEER N, PARMAR N,et al.Attention is all you need[C].Long Beach:Advances in Neural Information Processing Systems 30,2017.2 RADFORD A, NARASIMHAN K, SALIMANS T, et al.Improving language understanding by generative pre-training[EB/OL].[2024-05-05].https://openai.com/index/language-unsupervised.3 DEVLIN J, CHANG M W, LEE K, et al.Bert:pre-training of deep bidirectional transformers for language understanding[EB/OL].[2024-05-05].https://arxiv.org/pdf/1810.04805.4 RAFFEL C, SHAZEER N, ROBERTS A, et al.Exploring the limits of transfer learning with a unified text-to-text transformer[J].Journal of machine learning research, 2020,21(140):1-67.5 SINGHAL K, AZIZI S, TU T,et al.Large language models encode clinical knowledge[J].Nature, 2023,620(7972):172-180.6 SINGHAL K, TU T, GOTTWEIS J, et al.Towards expert-level medical question answering with large language models[EB/OL].[2024-05-06].https://arxiv.org/pdf/2305.09617.7 DANNER M, HADZIC B, GERHARDT S, et al.Advancing mental health diagnostics:GPT-based method for depression detection[C].Tsu:2023 62nd Annual Conference of the Society of Instrument and Control Engineers (SICE),IEEE, 2023.8 LIU H, AZAM M, BIN NAEEM S, et al.An overview of the capabilities of ChatGPT for medical writing and its implications for academic integrity[J].Health information & libraries journal, 2023,40(4):440-446.9 VAN VEEN D, VAN UDEN C, BLANKEMEIER L, et al.Clinical text summarization:adapting large language models can outperform human experts[J].Research square, 2023,30(4):1134-1142.10 ABD-ALRAZAQ A, ALSAAD R, ALHUWAIL D, et al.Large language models in medical education:opportunities, challenges, and future directions[J].JMIR medical education, 2023,9(1):e48291.11 UMAPATHI L K, PAL A, SANKARASUBBU M.Med-halt:medical domain hallucination test for large language models[EB/OL].[2024-05-07].https://arxiv.org/pdf/2307.15343.12 LIU F, ZHU T, WU X, et al.A medical multimodal large language model for future pandemics[J].NPJ digital medicine, 2023,6(1):226.13 PERNI S, LEHMANN L S, BITTERMAN D S.Patients should be informed when AI systems are used in clinical trials[J].Nature medicine, 2023,29(8):1890-1891.14 AGRAWAL M, HEGSELMANN S, LANG H, et al.Large language models are few-shot clinical information extractors[EB/OL].[2024-05-10].https://arxiv.org/pdf/2205.12689.15 GERO Z, SINGH C, CHENG H, et al.Self-verification improves few-shot clinical information extraction [EB/OL].[2024-05-10].https://arxiv.org/pdf/2306.00024.16 GOEL A, GUETA A, GILON O, et al.Llms accelerate annotation for medical information extraction[C].New Orleans:Machine Learning for Health (ML4H),PMLR, 2023.17 HU D, LIU B, ZHU X, et al.Zero-shot information extraction from radiological reports using ChatGPT[EB/OL].[2024-05-09].https://doi.org/10.1016/j.ijmedinf.2023.105321.18 CHEN J, CHEN P, WU X.Generating Chinese event extraction method based on ChatGPT and prompt learning[J].Applied sciences, 2023,13(17):9500.19 WANG L, MA Y, BI W, et al.An entity extraction pipeline for medical text records using large language models:analytical study[EB/OL].[2024-05-10].https://www.jmir.org/2024/1/e54580.20 JETHANI N, JONES S, GENES N, et al.Evaluating ChatGPT in information extraction:a case study of extracting cognitive exam dates and scores[EB/OL].[2024-05-10].http://dx.doi.org/10.2139/ssrn.4520434.21 RAMACHANDRAN G K, FU Y, HAN B, et al.Prompt-based extraction of social determinants of health using few-shot learning[EB/OL].[2024-05-11].https://arxiv.org/pdf/2306.07170.22 BHATE N J, MITTAL A, HE Z, et al.Zero-shot learning with minimum instruction to extract social determinants and family history from clinical notes using GPT Model[C].Sorrento:2023 IEEE International Conference on Big Data (BigData), 2023.23 LI M, ZHANG R.How far is language model from 100% few-shot named entity recognition in medical domain[EB/OL].[2024-05-11].https://arxiv.org/pdf/2307.00186.24 LI M, ZHENG X.Identification of ancient Chinese medical prescriptions and case data analysis under artificial intelligence GPT algorithm:a case study of song dynasty medical literature[EB/OL].[2024-05-11].10.1109/ACCESS.2023.3330212.25 ISCOE M, SOCRATES V, GILSON A, et al.Identifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models[J].Academic emergency medicine, 2023,31(6):599-610.26 LOSSIO-VENTURA J A, WEGER R, LEE A Y, et al.A comparison of ChatGPT and fine-tuned open pre-trained transformers (opt) against widely used sentiment analysis tools:sentiment analysis of COVID-19 survey data[EB/OL].[2024-05-12].https://mental.jmir.org/2024/1/e50150.27 DE S, VATS S.Decoding concerns:multi-label classification of vaccine sentiments in social media[EB/OL].[2024-05-12].https://arxiv.org/pdf/2312.10626.28 CLARKE P, LEININGER C, PRINCIPATO C,et al.From a large language model to three-dimensional sentiment[EB/OL].[2024-05-12].https://doi.org/10.31234/osf.io/kaeqy.29 GMEZ-ZARAGOZ L, MINISSI M E, LLANES-JURADO J, et al.Linguistic indicators of depressive symptoms in conversations with virtual humans[C].Valencia:Working Conference on Virtual Enterprises, 2023.30 MITTAL S, DE CHOUDHURY M.Moral framing of mental health discourse and its relationship to stigma:a comparison of social media and news[C].Hamburg:The 2023 CHI Conference on Human Factors in Computing Systems, 2023.31 WANG S, ZHAO Z, OUYANG X, et al.Chatcad:interactive computer-aided diagnosis on medical image using large language models[EB/OL].[2024-05-15].https://arxiv.org/pdf/2302.07257.32 MAZUMDAR H, CHAKRABORTY C, SATHVIK M, et al.GPTFX:a novel GPT-3 based framework for mental health detection and explanations[EB/OL].[2024-05-15].10.1109/JBHI.2023.3328350.33 JO E, EPSTEIN D A, JUNG H, et al.Understanding the benefits and challenges of deploying conversational AI leveraging large language models for public health intervention[C].Hamburg:The 2023 CHI Conference on Human Factors in Computing Systems, 2023.34 AKILESH S, ABINAYA R, DHANUSHKODI S, et al.A novel AI-based chatbot application for personalized medical diagnosis and review using large language models[C].Chennai:2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) IEEE, 2023.35 CHEN S, KANN B H, FOOTE M B, et al.Use of artificial intelligence chatbots for cancer treatment information[J].JAMA oncology, 2023,9(10):1459-1462.36 CHEN S, GUEVARA M, MONINGI S, et al.The impact of responding to patient messages with large language model assistance[EB/OL].[2024-05-17].https://arxiv.org/abs/2310.17703.37 LAKER B, CURRELL E.ChatGPT:a novel AI assistant for healthcare messaging—a commentary on its potential in addressing patient queries and reducing clinician burnout[EB/OL].[2024-05-18].https://doi.org/10.1136/leader-2023-000844.38 PATEL S B, LAM K.ChatGPT:the future of discharge summaries[J].The lancet digital health, 2023,5(3):e107-e108.39 LIU F, YANG B, YOU C, et al.Retrieve, reason, and refine:generating accurate and faithful patient instructions[C].New Orleans:Advances in Neural Information Processing Systems 35,2022.40 ALI S R, DOBBS T D, HUTCHINGS H A, et al.Using ChatGPT to write patient clinic letters[J].The lancet digital health, 2023,5(4):e179-e181.41 WAISBERG E, ONG J, MASALKHI M, et al.Chat generative pretrained transformer to optimize accessibility for cataract surgery postoperative management[J].The Pan-American journal of ophthalmology, 2023,5(1):46.42 LIM S, SCHMLZLE R.Artificial intelligence for health message generation:an empirical study using a large language model (LLM) and prompt engineering[EB/OL].[2024-05-20].https://doi.org/10.3389/fcomm.2023.1129082.43 XIE Y, SETH I, HUNTER-SMITH D J, et al.Aesthetic surgery advice and counseling from artificial intelligence:a rhinoplasty consultation with ChatGPT[J].Aesthetic plastic surgery, 2023,47(5):1985-1993.44 World Health Organization.International classification of diseases[EB/OL].[2024-05-21].https://icd.who.int/en.45 THIRUNAVUKARASU A J, TING D S J, ELANGOVAN K, et al.Large language models in medicine[J].Nature medicine, 2023,29(8):1930-1940.46 HUANG C W, TSAI S C, CHEN Y N.PLM-ICD:automatic ICD coding with pretrained language models[EB/OL].[2024-05-21].https://arxiv.org/abs/2207.05289.47 ONG J, KEDIA N, HARIHAR S,et al.Applying large language model artificial intelligence for retina international classification of diseases (ICD) coding[EB/OL].[2024-05-21].https://jmai.amegroups.org/article/view/8198/html.48 DONG H, FALIS M, WHITELEY W,et al.Automated clinical coding:what, why, and where we are [J].NPJ digital medicine, 2022,5(1):159.49 KARABACAK M, OZKARA B B, MARGETIS K, et al.The advent of generative language models in medical education[EB/OL].[2024-05-28].https://mededu.jmir.org/2023/1/e48163.50 AHN S.The impending impacts of large language models on medical education[J].Korean journal of medical education, 2023,35(1):103.51 LEE H.The rise of ChatGPT:exploring its potential in medical education[J].Anatomical sciences education, 2023,17(5):926-931.52 SALLAM M.ChatGPT utility in healthcare education, research, and practice:systematic review on the promising perspectives and valid concerns[J].Healthcare, 2023,11(6):887.53 KUNG T H, CHEATHAM M, MEDENILLA A, et al.Performance of ChatGPT on USMLE:potential for AI-assisted medical education using large language models[J].Plos digital health, 2023,2(2):e0000198.54 SCHUBERT M C, WICK W, VENKATARAMANI V.Performance of large language models on a neurology board-style examination[J].JAMA network open, 2023,6(12):e2346721-e2346721.55 RAWTE V, SHETH A, DAS A.A survey of hallucination in large foundation models[EB/OL].[2024-06-01].https://arxiv.org/abs/2309.05922.56 MANAKUL P, LIUSIE A, GALES M J F.SelfcheckGPT:zero-resource black-box hallucination detection for generative large language models[EB/OL].[2024-06-05].https://arxiv.org/abs/2303.08896.57 SHUSTER K, POFF S, CHEN M, et al.Retrieval augmentation reduces hallucination in conversation[EB/OL].[2024-06-05].https://arxiv.org/abs/2104.07567.58 ROIT P, FERRET J, SHANI L, et al.Factually consistent summarization via reinforcement learning with textual entailment feedback[EB/OL].[2024-06-05].https://arxiv.org/abs/2306.00186.59 CHERN I C, WANG Z, DAS S, et al.Improving factuality of abstractive summarization via contrastive reward learning[EB/OL].[2024-06-07].https://arxiv.org/abs/2307.04507.60 DHULIAWALA S, KOMEILI M, XU J,et al.Chain-of-verification reduces hallucination in large language models[EB/OL].[2024-06-10].https://arxiv.org/abs/2309.11495.61 XIE Q, SCHENCK E J, YANG H S, et al.Faithful AI in medicine:a systematic review with large language models and beyond[EB/OL].[2024-06-10].https://doi.org/10.1101/2023.04.18.23288752.62 JIN D, PAN E, OUFATTOLE N, et al.What disease does this patient have? A large-scale open domain question answering dataset from medical exams[J].Applied sciences, 2021,11(14):6421.63 PAL A, UMAPATHI L K, SANKARASUBBU M.Medmcqa:a large-scale multi-subject multi-choice dataset for medical domain question answering[C].online:Conference on Health, Inference, and Learning, PMLR, 2022.64 LIN S, HILTON J, EVANS O.Truthfulqa:measuring how models mimic human falsehoods[EB/OL].[2024-06-10].https://arxiv.org/abs/2109.07958.65 LI J, CHENG X, ZHAO W X, et al.Halueval:a large-scale hallucination evaluation benchmark for large language models[C].Singapore:The 2023 Conference on Empirical Methods in Natural Language Processing, 2023.66 LEWIS P, PEREZ E, PIKTUS A, et al.Retrieval-augmented generation for knowledge-intensive NLP tasks[C].online:Advances in Neural Information Processing Systems 33,2020.67 VALIA L G, MASTROLEO I.The ethical and scientific challenges of ChatGPT in health:utopianism, technophobia and pragmatism[EB/OL].[2024-06-11].https://doi.org/10.31219/osf.io/phtwz.68 HE K, MAO R, LIN Q, et al.A survey of large language models for healthcare:from data, technology, and applications to accountability and ethics[EB/OL].[2024-06-11].https://arxiv.org/abs/2310.05694.69 TIAN S, JIN Q, YEGANOVA L, et al.Opportunities and challenges for ChatGPT and large language models in biomedicine and health[J].Briefings in bioinformatics, 2024,25(1):bbad493.70 STOKEL-WALKER C.ChatGPT listed as author on research papers:many scientists disapprove[J].Nature, 2023,613(7945):620-621.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

何剑虎,王德健,赵志锐,等.大语言模型在医疗领域的前沿研究与创新应用[J].医学信息学杂志,2024,45(9):10-18

复制
分享
文章指标
  • 点击次数:2050
  • 下载次数: 4362
  • HTML阅读次数: 753
  • 引用次数: 0
历史
  • 最后修改日期:2024-09-12
  • 在线发布日期: 2024-10-17

友情链接

联系地址：北京市朝阳区雅宝路3号     邮编：100020

联系电话：（010）52328686/87     邮箱：yxxxx@imicams.ac.cn

技术支持：北京勤云科技发展有限公司 京ICP备10218182-2

京公网安备 11010502037823号

总访问量：6214223 今日访问量：2273

《医学信息学杂志》

微信公众号

扫码关注

官方微信