人工智能技术在脓毒症患者诊断与治疗中应用的研究进展

张玉雯; 白颖璐; 张学敏; 文越; 杨卓雅; 路明烨; 徐霄龙; 刘清泉

doi:10.3760/cma.j.cn501225-20250708-00292

人工智能技术在脓毒症患者诊断与治疗中应用的研究进展

doi: 10.3760/cma.j.cn501225-20250708-00292

1.
首都医科大学附属北京中医医院急诊与危重症救治中心,北京　　100010
2.
天津中医药大学中西医结合学院,天津　　301617
3.
辽宁中医药大学第二临床学院,沈阳　　116600

基金项目:

国家自然科学基金面上项目 82474428

国家中医药管理局高水平中医药重点学科建设项目 zyyzdxk-2023001

详细信息

通讯作者:
刘清泉,Email：liuqingquan2003@126.com

计量
- 文章访问数: 96
- HTML全文浏览量: 18
- PDF下载量: 9
- 被引次数: 0
出版历程
- 收稿日期: 2025-07-08
- 网络出版日期: 2025-10-22

Research advances on the application of artificial intelligence technology in the diagnosis and treatment of sepsis patients

1.
Emergency and Critical Care Center, Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing 100010, China
2.
College of Integrated Traditional Chinese and Western Medicine, Tianjin University of Traditional Chinese Medicine, Tianjin 301617, China
3.
Second Clinical College, Liaoning University of Traditional Chinese Medicine, Shenyang 116600, China

Funds:

General Program of National Natural Science Foundation of China 82474428

The Key Discipline Construction Project of High-level Traditional Chinese Medicine of the National Administration of Traditional Chinese Medicine zyyzdxk-2023001

More Information

Corresponding author: Liu Qingquan, Email: liuqingquan2003@126.com

摘要

摘要: 近年来,随着人工智能技术的蓬勃发展,该技术已被广泛应用于急危重症领域,在临床决策支持中具有巨大潜力,为脓毒症的辅助诊断与治疗提供了新的工具。基于人工智能技术开发的脓毒症预测模型能够高效捕捉和整合不同模态数据中的信息,提高脓毒症早期预测的精准度,建立预后评价体系,从而指导临床精准治疗,提高脓毒症患者生存率。该文综述了人工智能技术在脓毒症早期预测与亚型识别、预后评估及相关器官功能障碍预测方面应用的研究进展,以期为该技术在急危重症领域的进一步应用提供参考与启示。
- 人工智能 /
- 脓毒症 /
- 重症监护病房 /
- 机器学习 /
- 诊断 /
- 预测 /
- 危重症监护结局
Abstract: In recent years, with the rapid advancement of artificial intelligence technology, this technology has been extensively applied in the field of emergency and critical care. Artificial intelligence demonstrates significant potential in clinical decision support, offering novel tools for the auxiliary diagnosis and treatment of sepsis. The sepsis prediction model developed based on artificial intelligence technology can efficiently capture and integrate information from diverse modalities, enhance the accuracy of early sepsis prediction, and establish a prognostic evaluation system, thereby guiding clinical precision treatment and ultimately improving the survival rates of sepsis patients. This paper reviews the research advances on the application of artificial intelligence technology in the early prediction and subtype identification of sepsis, prognosis assessment, and prediction of related organ dysfunction. It aims to provide a reference and inspiration for the further application of this technology in the field of emergency and critical care.
- Artificial intelligence /
- Sepsis /
- Intensive care units /
- Machine learning /
- Diagnosis /
- Forecasting /
- Critical care outcomes
所有作者声明不存在利益冲突

HTML全文

参考文献(52)

[1]	SingerM,DeutschmanCS,SeymourCW,et al.The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)[J].JAMA,2016,315(8):801-810.DOI: 10.1001/jama.2016.0287.
[2]	SakrY,JaschinskiU,WitteboleX,et al.Sepsis in intensive care unit patients: worldwide data from the Intensive Care over Nations audit[J].Open Forum Infect Dis,2018,5(12):ofy313.DOI: 10.1093/ofid/ofy313.
[3]	FleischmannC,ScheragA,AdhikariNK,et al.Assessment of global incidence and mortality of hospital-treated sepsis. Current estimates and limitations[J].Am J Respir Crit Care Med,2016,193(3):259-272.DOI: 10.1164/rccm.201504-0781OC.
[4]	RuddKE,JohnsonSC,AgesaKM,et al.Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study[J].Lancet,2020,395(10219):200-211.DOI: 10.1016/S0140-6736(19)32989-7.
[5]	UsmanAI, 刘思奇,乔云峰,等.人工智能和机器学习在内分泌疾病研究中的前沿进展[J].吉林医学,2025,46(4):946-949.DOI: 10.3969/j.issn.1004-0412.2025.04.055.
[6]	王晓宁,杨琦,姚娓. 人工智能在辅助中医消化系统疾病诊治中应用研究进展[J]. 中华中医药学刊, 2025, 43(7): 17-21.DOI: 10.13193/j.issn.1673-7717.2025.07.004.
[7]	张煊,谢瑀,冯亚宁,等.人工智能在预测肾脏疾病预后中的应用与进展[J/OL].中华中医药学刊,(2025-03-19)[2025-07-08]. https://link.cnki.net/urlid/21.1546.R.20250319.0954.002.[网络预发表]. https://link.cnki.net/urlid/21.1546.R.20250319.0954.002
[8]	刘青光,李涵琪,孙联康. 人工智能技术助力胆道疾病的精准诊疗[J].中华消化外科杂志,2025,24(7):826-831. DOI: 10.3760/cma.j.cn115610-20250514-00196.
[9]	陈宇曦,罗亮,蒋诗情,等.外泌体多组学分析技术在烧伤脓毒症预警与诊断中应用的研究进展[J].中华烧伤与创面修复杂志,2025,41(7):698-703.DOI: 10.3760/cma.j.cn501225-20250512-00222.
[10]	KnausWA,DraperEA,WagnerDP,et al.APACHE II: a severity of disease classification system[J].Crit Care Med,1985,13(10):818-829.
[11]	ChuaWL, RusliKDB, AitkenLM. Early warning scores for sepsis identification and prediction of in-hospital mortality in adults with sepsis: a systematic review and meta-analysis[J]. J Clin Nurs, 2024, 33(6): 2005-2018. DOI: 10.1111/jocn.17061.
[12]	吴孟春,叶舜华. 脓毒症早期诊断标志物研究进展[J]. 岭南急诊医学杂志, 2025,30(4): 503-505. DOI: 10.3969/j.issn.1671-301X.2025.04.048.
[13]	申喜凤,李美婷,南嘉乐,等. 医学人工智能发展态势分析及问题浅析[J]. 科技管理研究, 2023(7): 193-198.DOI: 10.3969/j.issn.1000-7695.2023.7.021.
[14]	山其君,王绍博,周翔. 大语言模型在脓毒症诊疗中的应用研究综述[J]. 中国卫生信息管理杂志, 2025, 22(2): 187-194. DOI: 10.3969/j.issn.1672-5166.2025.02.04.
[15]	谢天基于强化学习的脓毒症治疗策略和死亡风险预测算法研究与应用兰州兰州大学2024 谢天. 基于强化学习的脓毒症治疗策略和死亡风险预测算法研究与应用[D]. 兰州:兰州大学, 2024.
[16]	RhodesA,EvansLE,AlhazzaniW,et al.Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock: 2016[J].Intensive Care Med,2017,43(3):304-377.DOI: 10.1007/s00134-017-4683-6.
[17]	LiuVX,Fielding-SinghV,GreeneJD,et al.The timing of early antibiotics and hospital mortality in sepsis[J].Am J Respir Crit Care Med,2017,196(7):856-863.DOI: 10.1164/rccm.201609-1848OC.
[18]	FleurenLM, KlauschTLT, ZwagerCL, et al.Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy[J].Intensive Care Med,2020,46(3):383-400.DOI: 10.1007/s00134-019-05872-y.
[19]	NematiS,HolderA,RazmiF,et al.An interpretable machine learning model for accurate prediction of sepsis in the ICU[J].Crit Care Med,2018,46(4):547-553.DOI: 10.1097/CCM.0000000000002936.
[20]	BurdickH,PinoE,Gabel-ComeauD,et al.Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals[J].BMJ Health Care Inform,2020,27(1):e100109.DOI: 10.1136/bmjhci-2019-100109.
[21]	ShimabukuroDW,BartonCW,FeldmanMD,et al.Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial[J].BMJ Open Respir Res,2017,4(1):e000234.DOI: 10.1136/bmjresp-2017-000234.
[22]	WangX,GuoZ,WangX,et al.Construction of diagnostic model for regulatory T cell-related genes in sepsis based on machine learning[J].Biomedicines,2025,13(5):1060.DOI: 10.3390/biomedicines13051060.
[23]	刘辉,童森,姚咏明.脓毒症亚型研究的现状与展望[J].中华急诊医学杂志,2025,34(2):129-132.DOI: 10.3760/cma.j.issn.1671-0282.2025.02.001.
[24]	LuisChiscano-camón,AdolfRuiz-sanmartin,IvanBajaña, et al. Current perspectives in the management of sepsis and septic shock[J].Front Med (Lausanne), 2024,15:11:1431791.DOI: 10.3389/fmed.2024.1431791.
[25]	姚咏明,张卉,董宁.脓毒症分型:精准治疗之基石[J].中华烧伤与创面修复杂志,2024,40(10):915-919.DOI: 10.3760/cma.j.cn501225-20240529-00203.
[26]	SweeneyTE,AzadTD,DonatoM,et al.Unsupervised analysis of transcriptomics in bacterial sepsis across multiple datasets reveals three robust clusters[J].Crit Care Med,2018,46(6):915-925.DOI: 10.1097/CCM.0000000000003084.
[27]	FjellCD,ThairS,HsuJL,et al.Cytokines and signaling molecules predict clinical outcomes in sepsis[J].PLoS One,2013,8(11):e79207.DOI: 10.1371/journal.pone.0079207.
[28]	JekarlDW,KimJY,HaJH,et al.Diagnosis and prognosis of sepsis based on use of cytokines, chemokines, and growth factors[J].Dis Markers,2019,2019:1089107.DOI: 10.1155/2019/1089107.
[29]	DavenportEE,BurnhamKL,RadhakrishnanJ,et al.Genomic landscape of the individual host response and outcomes in sepsis: a prospective cohort study[J].Lancet Respir Med,2016,4(4):259-271.DOI: 10.1016/S2213-2600(16)00046-1.
[30]	冯春晓,金瑛,林丽君,等. 老年脓毒症病人预后风险预测模型的研究进展[J]. 全科护理, 2025, 23(19): 3655-3659. DOI: 10.12104/j.issn.1674-4748.2025.19.010.
[31]	HouN,LiM,HeL,et al.Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost[J].J Transl Med,2020,18(1):462.DOI: 10.1186/s12967-020-02620-5.
[32]	WernlyB,MamandipoorB,BaldiaP,et al.Machine learning predicts mortality in septic patients using only routinely available ABG variables: a multi-centre evaluation[J].Int J Med Inform,2021,145:104312.DOI: 10.1016/j.ijmedinf.2020.104312.
[33]	GuoF,ZhuX,WuZ,et al.Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter[J].J Transl Med,2022,20(1):265.DOI: 10.1186/s12967-022-03469-6.
[34]	B H,DK M,TM R,et al.Advances in diagnosis and prognosis of bacteraemia, bloodstream infection, and sepsis using machine learning: a comprehensive living literature review[J].Artif Intell Med,2025,160:103008.DOI: 10.1016/j.artmed.2024.103008.
[35]	LyuW,DongX,WongR,et al.A multimodal transformer: fusing clinical notes with structured EHR data for interpretable in-hospital mortality prediction[J].AMIA Annu Symp Proc,2022,2022:719-728.
[36]	PeerapornratanaS,Manrique-CaballeroCL,GómezH,et al.Acute kidney injury from sepsis: current concepts, epidemiology, pathophysiology, prevention and treatment[J].Kidney Int,2019,96(5):1083-1099.DOI: 10.1016/j.kint.2019.05.026.
[37]	SunJ,ZhangJ,TianJ,et al.Mitochondria in sepsis-induced AKI[J].J Am Soc Nephrol,2019,30(7):1151-1161.DOI: 10.1681/ASN.2018111126.
[38]	van SlobbeR,HerrmannovaD,BoekeDJ,et al.Multimodal convolutional neural networks for the prediction of acute kidney injury in the intensive care[J].Int J Med Inform,2025,196:105815.DOI: 10.1016/j.ijmedinf.2025.105815.
[39]	LiJ,ZhuM,YanL.Predictive models of sepsis-associated acute kidney injury based on machine learning: a scoping review[J].Ren Fail,2024,46(2):2380748.DOI: 10.1080/0886022X.2024.2380748.
[40]	GhanbariG,LamJY,ShashikumarSP,et al.Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients[J].JAMIA Open,2024,7(3):ooae097.DOI: 10.1093/jamiaopen/ooae097.
[41]	LvX,LiuD,ChenX,et al.Machine learning for the prediction of mortality in patients with sepsis-associated acute kidney injury: a systematic review and meta-analysis[J].BMC Infect Dis,2024,24(1):1454.DOI: 10.1186/s12879-024-10380-6.
[42]	WuCC,PolyTN,WengYC,et al.Machine learning models for predicting mortality in critically ill patients with sepsis-associated acute kidney injury: a systematic review[J].Diagnostics (Basel),2024,14(15):1594.DOI: 10.3390/diagnostics14151594.
[43]	ZhaoH,CaiX,LiuN,et al.Thromboelastography as a tool for monitoring blood coagulation dysfunction after adequate fluid resuscitation can predict poor outcomes in patients with septic shock[J].J Chin Med Assoc,2020,83(7):674-677.DOI: 10.1097/JCMA.0000000000000345.
[44]	CuiR,HuaW,QuK,et al.An interpretable early dynamic sequential predictor for sepsis-induced coagulopathy progression in the real-world using machine learning[J].Front Med (Lausanne),2021,8:775047.DOI: 10.3389/fmed.2021.775047.
[45]	ZhaoQY,LiuLP,LuoJC,et al.A machine-learning approach for dynamic prediction of sepsis-induced coagulopathy in critically ill patients with sepsis[J].Front Med (Lausanne),2021,7:637434.DOI: 10.3389/fmed.2020.637434.
[46]	Shankar-HariM,PhillipsGS,LevyML,et al.Developing a new definition and assessing new clinical criteria for septic shock: for the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)[J].JAMA,2016,315(8):775-787.DOI: 10.1001/jama.2016.0289.
[47]	GianniniHM,GinestraJC,ChiversC,et al.A machine learning algorithm to predict severe sepsis and septic shock: development, implementation, and impact on clinical practice[J].Crit Care Med,2019,47(11):1485-1492.DOI: 10.1097/CCM.0000000000003891.
[48]	MisraD,AvulaV,WolkDM,et al.Early detection of septic shock onset using interpretable machine learners[J].J Clin Med,2021,10(2):301.DOI: 10.3390/jcm10020301.
[49]	ZengQB,PengEL,ZhouY,et al.Explainable machine learning model for predicting septic shock in critically sepsis patients based on coagulation indexes: a multicenter cohort study[J].Chin J Traumatol,2025:S1008-1275(25)00032-X.DOI: 10.1016/j.cjtee.2024.08.012.
[50]	宋大庆,李亚,孙树印.人工智能技术在脓毒症/脓毒性休克中的应用[J].实用休克杂志(中英文),2024,8(6):323-327.
[51]	KomorowskiM,CeliLA,BadawiO,et al.The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care[J].Nat Med,2018,24(11):1716-1720.DOI: 10.1038/s41591-018-0213-5.
[52]	KalimouttouA,KennedyJN,FengJ,et al.Optimal vasopressin initiation in septic shock: the OVISS reinforcement learning study[J].JAMA,2025,333(19):1688-1698.DOI: 10.1001/jama.2025.3046.