This study introduced the development history and current research status of large language model (LLM), data query robot (DQR). Meanwhile, through empirical analyses, the practical application effect of LLM-based DQR and its role in dealing with the complex tasks of medical data querying and analysis in the field of digital medicine was explored, and it was confirmed that LLM-based DQR could provide non-technical people with an intuitive and convenient tool to significantly improve the querying efficiency and analysis capability of medical data. In addition, this paper discusses the limitations and potential of future development of LLM and DQR techniques in current applications, providing reference for further research and applications.

1.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: e48291, DOI: 10.2196/48291.

2.Atallah SB, Banda NR, Banda A, et al. How large language models including generative pre-trained transformer (GPT) 3 and 4 will impact medicine and surgery[J]. Tech Coloproctol, 2023, 27(8): 609-614. DOI: 10.1007/s10151-023-02837-8.

3.周志浩,宋佳琳,刘嘉成,等. 基于人工智能LLM技术的虚拟患者系统构建与临床教学应用 [J]. 医学新知, 2024, 34 (7): 833-842. [Zhou ZH, Song JL, Liu JC, et al. Construction and clinical teaching application of virtual patient system: based on artificial intelligence LLM technology[J]. Yixue Xinzhi Zazhi, 2024, 34(7): 833-842.] DOI: 10.12173/j.issn.1004-5511.202403091.

4.Yang X, Chen A, PourNejatian N, et al. A large language model for electronic health records[J]. NPJ Digit Med, 2022, 5(1): 194. DOI: 10.1038/s41746-022-00742-2.

5.Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Comput, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.

6.DeLong KA, Trott S, Kutas M. Offline dominance and zeugmatic similarity normings of variably ambiguous words assessed against a neural language model (BERT)[J]. Behav Res Methods, 55(4): 1537–1557. https:/doi.org/10.3758/s13428-022-01869-6.

7.Lee J, Yoon W, Kim S, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining[J]. Bioinformatics, 2020, 36(4): 1234-1240. DOI: 10.1093/bioinformatics/btz682.

8.Nielsen JPS, von Buchwald C, Grønhøj C. Validity of the large language model ChatGPT (GPT4) as a patient information source in otolaryngology by a variety of doctors in a tertiary otorhinolaryngology department[J]. Acta Otolaryngol, 2023, 143(9): 779-782. DOI: 10.1080/00016489.2023.2254809.

9.Sutherland R, Trembath D, Hodge A, et al. Telehealth language assessments using consumer grade equipment in rural and urban settings: feasible, reliable and well tolerated[J]. J Telemed Telecare, 2017, 23(1): 106-115. DOI: 10.1177/1357633X15623921.

10.Hristidis V, Ruggiano N, Brown EL, et al. ChatGPT vs Google for queries related to dementia and other cognitive decline: comparison of results[J]. J Med Internet Res, 2023, 25: e48966. DOI: 10.2196/48966.

11.Gorenstein L, Konen E, Green M, et al. Bidirectional encoder representations from transformers in radiology: a systematic review of natural language processing applications[J]. J Am Coll Radiol, 2024, 21(6): 914-941. DOI: 10.1016/j.jacr.2024.01.012.

12.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(1): 33. DOI: 10.1007/s10916-023-01925-4.

13.Arora A, Arora A. The promise of large language models in health care[J]. Lancet, 2023, 401(10377): 641. DOI: 10.1016/S0140-6736(23)00216-7.

14.Bagal V, Aggarwal R, Vinod PK, et al. Molgpt: molecular generation using a transformer-decoder model[J]. J Chem Inf Model, 2022, 62(9): 2064-2076. DOI: 10.1021/acs.jcim.1c00600.

15.Jagannatha A, Yu H. Calibrating structured output predictors for natural language processing[J]. Proc Conf Assoc Comput Linguist Meet, 2020, 2020: 2078-2092. DOI: 10.18653/v1/2020.acl-main.188.

16.Haider L, Baumgartner M, Hayn D, et al. Integration of python modules in a matlab-based predictive analytics toolset for healthcare[J]. Stud Health Technol Inform, 2022, 293: 197-204. DOI: 10.3233/SHTI220369.

17.Hu Y, Wen G, Ma J, et al. Label-indicator morpheme growth on LSTM for Chinese healthcare question department classification[J]. J Biomed Inform, 2018, 82: 154-168. DOI: 10.1016/j.jbi.2018.04.011.

18.Becerra-Culqui TA, Lonky NM, Chen Q, et al. Patterns and correlates of cervical cancer screening initiation in a large integrated health care system[J]. Am J Obstet Gynecol, 2018, 218(4): 429.e1-429.e9. DOI: 10.1016/j.ajog.2017.12.209.

19.Koranteng E, Rao A, Flores E, et al. Empathy and equity: key considerations for large language model adoption in health care[J]. JMIR Med Educ, 2023, 9: e51199. DOI: 10.2196/51199.

20.Patsakis C, Lykousas N. Man vs the machine in the struggle for effective text anonymisation in the age of large language models[J]. Sci Rep, 2023, 13(1): 16026. DOI: 10.1038/s41598-023-42977-3.

21.Peng C, Yang X, Chen A, et al. A study of generative large language model for medical research and healthcare[J]. NPJ Digit Med, 2023, 6(1): 210. DOI: 10.1038/s41746-023-00958-w.

22.Klerings I, Weinhandl AS, Thaler KJ. Information overload in healthcare: too much of a good thing?[J]. Z Evid Fortbild Qual Gesundhwes, 2015, 109(4-5): 285-290. DOI: 10.1016/j.zefq.2015.06.005.

23.Sivarajkumar S, Mohammad HA, Oniani D, et al. Clinical information retrieval: a literature review[J]. J Healthc Inform Res, 2024, 8(2): 313-352. DOI: 10.1007/s41666-024-00159-4.

24.Chow JCL, Wong V, Li K. Generative pre-trained transformer-empowered healthcare conversations: current trends, challenges, and future directions in large language model-enabled medical chatbots[J]. BioMedInformatics, 2024, 4(1): 837-852. DOI: 10.3390/biomedinformatics4010047.

25.诸宇佳, 韩慧, 卫建华, 等. 人工智能医学影像研究报告规范: CLAIM检查清单解读[J]. 中国循证医学杂志, 2023, 23(12): 1478-1484. [Zhu YJ, Han H, Wei JH, et al. Interpretation of checklist for artificial intelligence in medical imaging(CLAIM)[J]. Chinese Journal of Evidence-Based Medicine, 2023, 23(12): 1478-1484.] DOI: 10.7507/1672-2531.202303152.

26.袁为标, 陆大军, 李海峰, 等. 基于磁共振表观扩散系数图像的影像组学模型对鉴别前列腺癌和前列腺增生的价值[J]. 中华腔镜泌尿外科杂志(电子版), 2022, 16(1): 14-18. [Yuan WB, Lu DJ, Li HF, et al. Apparent diffusion coefficient map based radiomics model in differentiation of prostate cancer and benign prostate hyperplasia[J]. Chinese Journal of Endourology (Electronic Edition), 2022, 16(1): 14-18.] DOI: 10.3877/cma.j.issn.1674-3253.2022.01.003.