• Large Language Model-Based Cri...

*Result*: Large Language Model-Based Critical Care Big Data Deployment and Extraction: Descriptive Analysis.

Title:
Large Language Model-Based Critical Care Big Data Deployment and Extraction: Descriptive Analysis.
Authors:
Yang Z; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China., Xu SS; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China., Liu X; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China., Xu N; School of Information Science and Technology, Beijing University of Technology, Beijing, China., Chen Y; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717., Wang S; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717., Miao MY; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China., Hou M; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717., Liu S; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717., Zhou YM; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717., Zhou JX; Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China., Zhang L; Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717.
Source:
JMIR medical informatics [JMIR Med Inform] 2025 Mar 12; Vol. 13, pp. e63216. Date of Electronic Publication: 2025 Mar 12.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101645109 Publication Model: Electronic Cited Medium: Internet ISSN: 2291-9694 (Electronic) Linking ISSN: 22919694 NLM ISO Abbreviation: JMIR Med Inform Subsets: MEDLINE
Imprint Name(s):
Original Publication: Toronto : JMIR Publications, [2013]-
MeSH Terms:
Critical Care* , Big Data* , Programming Languages*, Humans ; Intensive Care Units ; Databases, Factual ; Large Language Models
References:
Crit Care Med. 2021 Jun 1;49(6):e563-e577. (PMID: 33625129)
Nat Med. 2018 Nov;24(11):1716-1720. (PMID: 30349085)
Crit Care Med. 2020 Dec;48(12):1737-1743. (PMID: 33044284)
Sci Data. 2018 Sep 11;5:180178. (PMID: 30204154)
Crit Care Med. 2019 Nov;47(11):1485-1492. (PMID: 31389839)
JMIR Med Inform. 2020 Jul 15;8(7):e15182. (PMID: 32673244)
Lancet Digit Health. 2021 Jun;3(6):e340-e348. (PMID: 33893070)
Sci Rep. 2023 Jul 17;13(1):11527. (PMID: 37460837)
J Am Med Inform Assoc. 2023 Dec 22;31(1):24-34. (PMID: 37748456)
Artif Intell Med. 2021 Jul;117:102083. (PMID: 34127232)
Hum Genomics. 2020 May 12;14(1):17. (PMID: 32398162)
JMIR Med Inform. 2016 Sep 30;4(3):e28. (PMID: 27694098)
Crit Care Med. 2007 May;35(5):1284-9. (PMID: 17414725)
Sci Data. 2016 May 24;3:160035. (PMID: 27219127)
Intensive Care Med. 2020 Mar;46(3):383-400. (PMID: 31965266)
Sci Data. 2023 Jan 16;10(1):31. (PMID: 36646711)
Crit Care. 2021 Nov 14;25(1):388. (PMID: 34775971)
Crit Care. 2020 Jul 14;24(1):433. (PMID: 32665010)
Front Big Data. 2024 Jun 26;7:1371680. (PMID: 38988646)
Contributed Indexing:
Keywords: AI; GPT; ICU; LLM; artificial intelligence; big data; critical care–related databases; database deployment; database extraction; intensive care unit; large language model
Entry Date(s):
Date Created: 20250313 Date Completed: 20250513 Latest Revision: 20250513
Update Code:
20260130
PubMed Central ID:
PMC11922493
DOI:
10.2196/63216
PMID:
40079079
Database:
MEDLINE

*Further Information*

*Background: Publicly accessible critical care-related databases contain enormous clinical data, but their utilization often requires advanced programming skills. The growing complexity of large databases and unstructured data presents challenges for clinicians who need programming or data analysis expertise to utilize these systems directly.
Objective: This study aims to simplify critical care-related database deployment and extraction via large language models.
Methods: The development of this platform was a 2-step process. First, we enabled automated database deployment using Docker container technology, with incorporated web-based analytics interfaces Metabase and Superset. Second, we developed the intensive care unit-generative pretrained transformer (ICU-GPT), a large language model fine-tuned on intensive care unit (ICU) data that integrated LangChain and Microsoft AutoGen.
Results: The automated deployment platform was designed with user-friendliness in mind, enabling clinicians to deploy 1 or multiple databases in local, cloud, or remote environments without the need for manual setup. After successfully overcoming GPT's token limit and supporting multischema data, ICU-GPT could generate Structured Query Language (SQL) queries and extract insights from ICU datasets based on request input. A front-end user interface was developed for clinicians to achieve code-free SQL generation on the web-based client.
Conclusions: By harnessing the power of our automated deployment platform and ICU-GPT model, clinicians are empowered to easily visualize, extract, and arrange critical care-related databases more efficiently and flexibly than manual methods. Our research could decrease the time and effort spent on complex bioinformatics methods and advance clinical research.
(© Zhongbao Yang, Shan-Shan Xu, Xiaozhu Liu, Ningyuan Xu, Yuqing Chen, Shuya Wang, Ming-Yue Miao, Mengxue Hou, Shuai Liu, Yi-Min Zhou, Jian-Xin Zhou, Linlin Zhang. Originally published in JMIR Medical Informatics (https://medinform.jmir.org).)*