A Knowledge-Enhanced Platform (MetaSepsisKnowHub) for Retrieval Augmented Generation–Based Sepsis Heterogeneity and Personalized Management: Development Study
Journal of Medical Internet Research · 06.06.2025 · 27 · e67201
DOI: 10.2196/67201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 06.06.2025. Verfasst von Chi Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Joint Laboratory of Artificial Intelligence for Critical Care Medicine, Department of Critical Care Medicine and Institutes for Systems Genetics, Fro…. Hauptthemen laut MEDLINE: Sepsis, Precision Medicine. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 107 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Sepsis
Abstract (Originalsprache)
Background
Sepsis is a severe syndrome of organ dysfunction caused by infection; it has high heterogeneity and high in-hospital mortality, representing a grim clinical challenge for precision medicine in critical care.
Objective
We aimed to extract reported sepsis biomarkers to provide users with comprehensive biomedical information and integrate retrieval augmented generation (RAG) and prompt engineering to enhance the accuracy, stability, and interpretability of clinical decisions recommended by large language models (LLMs).
Methods
To address the challenge, we established and updated the first knowledge-enhanced platform, MetaSepsisKnowHub, comprising 427 sepsis biomarkers and 423 studies, aiming to systematically collect and annotate sepsis biomarkers to guide personalized clinical decision-making in the diagnosis and treatment of human sepsis. We curated a tailored LLM framework incorporating RAG and prompt engineering and incorporated 2 performance evaluation scales: the System Usability Scale and the Net Promoter Score.
Results
The overall quantitative ratings of expert-reviewed clinical recommendations based on RAG surpassed baseline responses generated by 4 LLMs and showed a statistically significant improvement in textual questions (GPT-4: mean 75.79, SD 7.11 vs mean 81.59, SD 9.87; P=.02; GPT-4o: mean 70.36, SD 7.63 vs mean 77.98, SD 13.26; P=.02; Qwen2.5-instruct: mean 77.08 SD 3.75 vs mean 85.46, SD 7.27; P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Joint Laboratory of Artificial Intelligence for Critical Care Medicine, Department of Critical Care Medicine and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West Chin…
- Information Center and Department of Critical Care Medicine and Institutes for Systems Genetics, West China Hospital, Sichuan University, Chengdu, China.
- Department of Computer Science and Information Technologies, University of A Coruña, Research Center for Information and Communications Technologies, Biomedical Research Institute of A Coruña, Iberian Society of Telehea…
- Department of Urology, West China Hospital, Sichuan University, Chengdu, China.
ORCID-Profile: Chi Zhang, Hao Yang, Xingyun Liu, Rongrong Wu, Hui Zong, Erman Wu, Yi Zhou, Jiakun Li, Bairong Shen
Zitieren
APA
Zhang, C., Yang, H., Liu, X., Wu, R., Zong, H., Wu, E., Zhou, Y., Li, J., & Shen, B. (2025). A Knowledge-Enhanced Platform (MetaSepsisKnowHub) for Retrieval Augmented Generation–Based Sepsis Heterogeneity and Personalized Management: Development Study. Journal of Medical Internet Research, 27, e67201. https://doi.org/10.2196/67201
Vancouver
Zhang C, Yang H, Liu X, Wu R, Zong H, Wu E, et al. A Knowledge-Enhanced Platform (MetaSepsisKnowHub) for Retrieval Augmented Generation–Based Sepsis Heterogeneity and Personalized Management: Development Study. Journal of Medical Internet Research. 2025;27:e67201. doi:10.2196/67201
BibTeX
@article{Zhang2025,
author = {Zhang, Chi and Yang, Hao and Liu, Xingyun and Wu, Rongrong and Zong, Hui and Wu, Erman and Zhou, Yi and Li, Jiakun and Shen, Bairong},
title = {A Knowledge-Enhanced Platform (MetaSepsisKnowHub) for Retrieval Augmented Generation–Based Sepsis Heterogeneity and Personalized Management: Development Study},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {27},
pages = {e67201},
doi = {10.2196/67201}
}
EUVIMED