人工智能在烧伤谵妄预警与管理中应用的研究进展

王贵; 钱红燕; 岳晓敏

doi:10.3760/cma.j.cn501225-20250911-00392

人工智能在烧伤谵妄预警与管理中应用的研究进展

doi: 10.3760/cma.j.cn501225-20250911-00392

1.
嘉兴市中医医院重症医学科,嘉兴　314000
2.
嘉兴市中医医院神经外科,嘉兴　314000

基金项目:

浙江省中医药科技计划 2024ZL1070

详细信息

通讯作者:
王贵,Email：wg1050@163.com

计量
- 文章访问数: 12
- HTML全文浏览量: 3
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2025-09-11
- 网络出版日期: 2026-10-26

Research advances on the application of artificial intelligence in the warning and management of burn-related delirium

1.
Department of Intensive Care Medicine, Jiaxing Hospital of Traditional Chinese Medicine, Jiaxing 314000, China
2.
Department of Neurosurgery, Jiaxing Hospital of Traditional Chinese Medicine, Jiaxing 314000, China

Funds:

Zhejiang Provincial Traditional Chinese Medicine Science and Technology Plan 2024ZL1070

More Information

Corresponding author: Wang Gui, Email: wg1050@163.com

摘要

摘要: 烧伤患者谵妄发生率高、识别困难且干预窗口狭窄,是重症监护中的突出难题。人工智能技术凭借其善于处理复杂高维数据、挖掘隐匿模式与实时连续监测的独特优势,为烧伤谵妄的预警与管理提供了新方向。该文基于烧伤谵妄的主要驱动机制与临床异质性,系统综述人工智能在烧伤谵妄预测模型建立、多模态数据融合与可解释输出、多源数据采集、智能处理与决策支持、临床应用与闭环反馈等方面的研究进展,分析当前面临的数据治理与算法公平性、临床场景的整合与协同、责任认定与伦理监管等挑战,并对未来研究方向进行展望,以期为人工智能在烧伤领域的应用提供借鉴与参考。
- 人工智能 /
- 烧伤 /
- 谵妄 /
- 机器学习 /
- 决策支持系统,临床
Abstract: Delirium in burn patients presented a prominent challenge in intensive care, characterized by high incidence, difficult identification, and a narrow intervention window. Artificial intelligence (AI) technology, with its unique advantages of being adept at processing complex high-dimensional data, mining hidden patterns, and real-time continuous monitoring, provided new directions for the warning and management of burn-related delirium. Based on the main driving mechanisms and clinical heterogeneity of burn-related delirium, this article systematically reviewed the research advances of AI in establishment of predictive models for burn-related delirium, multimodal data fusion and interpretable outputs, multi-source data acquisition, intelligent processing and decision support, as well as clinical applications and closed-loop feedback. It analyzed current challenges such as data governance and algorithmic fairness, integration and collaboration in clinical scenarios, and liability attribution and ethical supervision, and prospected future research directions, aiming to provide references and insights for the application of AI in the field of burns.
- Artificial intelligence /
- Burns /
- Delirious speech /
- Machine learning /
- Decision support systems, clinical
所有作者声明不存在利益冲突

HTML全文

参考文献(47)

[1]	YiL,XieZ,WangZ,et al.Time trends in thermal burns incidence among Brazil, Russia, India, China, and South Africa (BRICS), an age-period-cohort analysis from the GBD 2019[J].Sci Rep,2025,15(1):6877.DOI: 10.1038/s41598-025-90935-y.
[2]	SilvaMP,ValaJ,SousaJ,et al.Incidence and delirium risk factors in burn patients: a prospective cohort study[J].Burns,2025,51(6):107556.DOI: 10.1016/j.burns.2025.107556.
[3]	SalhotraR,BoseA,SrivastavaS,et al.Reliability and validity of Hindi version of the confusion assessment method for intensive care unit (CAM-ICU) for diagnosis of delirium: a cohort study[J].Indian J Crit Care Med,2024,28(10):958-962.DOI: 10.5005/jp-journals-10071-24809.
[4]	EsumiR,FunaoH,KawamotoE,et al.Machine learning-based prediction of delirium and risk factor identification in intensive care unit patients with burns: retrospective observational study[J].JMIR Form Res,2025,9:e65190.DOI: 10.2196/65190.
[5]	SchölerLM,GrafL,AirolaA,et al.Determining the ground truth for the prediction of delirium in adult patients in acute care: a scoping review[J].JAMIA Open,2025,8(3):ooaf037.DOI: 10.1093/jamiaopen/ooaf037.
[6]	RenY,ZhangY,ZhanJ,et al.Machine learning for prediction of delirium in patients with extensive burns after surgery[J].CNS Neurosci Ther,2023,29(10):2986-2997.DOI: 10.1111/cns.14237.
[7]	GongKD,LuR,BergamaschiTS,et al.Predicting intensive care delirium with machine learning: model development and external validation[J].Anesthesiology,2023,138(3):299-311.DOI: 10.1097/ALN.0000000000004478.
[8]	曹烨君,张明珠,潘国俊,等.基于E-PRE-DELIRIC风险分层模型的谵妄管理模式在重症监护病房应用的有效性及预测性能研究[J].解放军医学院学报,2023,44(5):501-507,524.DOI: 10.3969/j.issn.2095-5227.2023.05.011.
[9]	MertinV,MostP,BuschM,et al.Current understanding of thermo(dys)regulation in severe burn injury and the pathophysiological influence of hypermetabolism, adrenergic stress and hypothalamic regulation-a systematic review[J/OL].Burns Trauma,2022,10:tkac031[2025-09-11]. https://pubmed.ncbi.nlm.nih.gov/36168403/.DOI: 10.1093/burnst/tkac031.
[10]	PruskowskiKA,FethM,HongL,et al.Pharmacologic management of pain, agitation, and delirium in burn patients[J].Surg Clin North Am,2023,103(3):495-504.DOI: 10.1016/j.suc.2023.02.003.
[11]	RenY,ZhangY,LuoJ,et al.Research progress on risk factors of delirium in burn patients: a narrative review[J].Front Psychiatry,2022,13:989218.DOI: 10.3389/fpsyt.2022.989218.
[12]	ZhangR,XuB,ZhangN,et al.Spinal microglia-derived TNF promotes the astrocytic JNK/CXCL1 pathway activation in a mouse model of burn pain[J].Brain Behav Immun,2022,102:23-39.DOI: 10.1016/j.bbi.2022.02.006.
[13]	ZhangP,ZouB,LiouYC,et al.The pathogenesis and diagnosis of sepsis post burn injury[J/OL].Burns Trauma,2021,9:tkaa047[2025-09-11]. https://pubmed.ncbi.nlm.nih.gov/33654698/.DOI: 10.1093/burnst/tkaa047.
[14]	Moins-TeisserencH,CordeiroDJ,AudigierV,et al.Severe altered immune status after burn injury is associated with bacterial infection and septic shock[J]. Front Immunol,2021,12:586195.DOI: 10.3389/fimmu.2021.586195.
[15]	中华医学会神经病学分会神经心理与行为神经病学学组.综合医院谵妄诊治中国专家共识(2021)[J].中华老年医学杂志,2021,40(10):1226-1233.DOI: 10.3760/cma.j.issn.0254-9026.2021.10.002.
[16]	StanleyGHM,BarberARJ,O'BrienAM,et al.Delirium in hospitalised adults with acute burns - a systematic review[J].Burns,2022,48(5):1040-1054.DOI: 10.1016/j.burns.2022.05.023.
[17]	罗月,梁光萍.烧伤后认知障碍及其机制的研究进展[J].中华烧伤与创面修复杂志,2023,39(8):790-794.DOI: 10.3760/cma.j.cn501225-20221117-00492.
[18]	DupreyMS,Dijkstra-KerstenSMA,ZaalIJ,et al.Opioid use increases the risk of delirium in critically ill adults independently of pain[J].Am J Respir Crit Care Med,2021,204(5):566-572.DOI: 10.1164/rccm.202010-3794OC.
[19]	TangBHY,ManaloJ,ChowdhurySR,et al.Melatonin use in the ICU: a systematic review and meta-analysis[J].Crit Care Med,2025,53(9):e1714-e1724.DOI: 10.1097/CCM.0000000000006767.
[20]	WuZ,JiangY,LiS,et al.Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: a retrospective study based on MIMIC-IV[J].PLoS One,2025,20(3):e0319297.DOI: 10.1371/journal.pone.0319297.
[21]	TangD,MaC,XuY.Interpretable machine learning model for early prediction of delirium in elderly patients following intensive care unit admission: a derivation and validation study[J].Front Med (Lausanne),2024,11:1399848.DOI: 10.3389/fmed.2024.1399848.
[22]	SchmidtS,DryschM,LehnhardtM. Burn surgery[J].Dtsch Med Wochenschr,2023,148(17):1075-1080.DOI: 10.1055/a-1957-4457.
[23]	PerkinsM,WoodF,GriffinB,et al.Variation in burn wound management approaches for paediatric burn patients in Australia and New Zealand[J].ANZ J Surg,2022,92(4):753-758.DOI: 10.1111/ans.17435.
[24]	HarutaA,MandellSP.Assessment and management of acute burn injuries[J].Phys Med Rehabil Clin N Am,2023,34(4):701-716.DOI: 10.1016/j.pmr.2023.06.019.
[25]	ZhangM,ZhongM,ChengY,et al.Intelligent prediction platform for sepsis risk based on real-time dynamic temporal features: design study[J].JMIR Med Inform,2025,13:e74940.DOI: 10.2196/74940.
[26]	李丽轩,梁洪,范勇,等.基于物联网和可穿戴技术的智能监护系统研发及其应用模式探索研究[J].生物医学工程学杂志,2023,40(6):1053-1061.DOI: 10.7507/1001-5515.202211047.
[27]	YangZ,MitraA,LiuW,et al.TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records[J].Nat Commun,2023,14(1):7857.DOI: 10.1038/s41467-023-43715-z.
[28]	YeJ,HaiJ,SongJ,et al.Multimodal data hybrid fusion and natural language processing for clinical prediction models[J].AMIA Jt Summits Transl Sci Proc,2024,2024:191-200.
[29]	LiuJ,CapurroD,NguyenA,et al.Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalities[J].J Biomed Inform,2023,145:104466.DOI: 10.1016/j.jbi.2023.104466.
[30]	KalyakulinaA,YusipovI,MoskalevA,et al.eXplainable Artificial Intelligence (XAI) in aging clock models[J].Ageing Res Rev,2024,93:102144.DOI: 10.1016/j.arr.2023.102144.
[31]	HanC,KimHI,SohS,et al.Machine learning with clinical and intraoperative biosignal data for predicting postoperative delirium after cardiac surgery[J].iScience,2024,27(6):109932.DOI: 10.1016/j.isci.2024.109932.
[32]	BelaynehAG,AdalO,MamoST,et al.Treatment outcome and associated factors of burn injury in Ethiopian hospitals: a systematic review and meta-analysis[J].Scars Burn Heal,2025,11:20595131251321772.DOI: 10.1177/20595131251321772.
[33]	MesseluMA,AbrhaNN,JemberieHK,et al.The national burden of mortality and its associated factors among burn patients in Ethiopia. A systematic review and meta-analysis[J].Burns,2024,50(9):107201.DOI: 10.1016/j.burns.2024.07.005.
[34]	BagleyBA,Senthil-KumarP,PavlikLE,et al.Care of the critically injured burn patient[J].Ann Am Thorac Soc,2022,19(6):880-889.DOI: 10.1513/AnnalsATS.202110-1099CME.
[35]	CaoZ,HidalgoG,SimonT,et al.OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields[J].IEEE Trans Pattern Anal Mach Intell,2021,43(1):172-186.DOI: 10.1109/TPAMI.2019.2929257.
[36]	CarterJE,ShuppJW,PhelanHA,et al.Refinement of an artificial intelligence algorithm for enhanced burn wound depth assessment using multispectral imaging: an expanded proof of concept study[J].J Burn Care Res,2025,46(6):1302-1317.DOI: 10.1093/jbcr/iraf057.
[37]	BoppanaSH,TyagiD,KomatiS,et al.AI-delirium guard: predictive modeling of postoperative delirium in elderly surgical patients[J].PLoS One,2025,20(6):e0322032.DOI: 10.1371/journal.pone.0322032.
[38]	GiesaN,SekutowiczM,RubarthK,et al.Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium[J].Commun Med (Lond),2024,4(1):251.DOI: 10.1038/s43856-024-00681-x.
[39]	EdrissS,RomagnoliC,CaprioliL,et al.Commercial vision sensors and AI-based pose estimation frameworks for markerless motion analysis in sports and exercises: a mini review[J].Front Physiol,2025,16:1649330.DOI: 10.3389/fphys.2025.1649330.
[40]	ZhangW,TangN,SongJ,et al.Development and validation of a machine learning-based risk prediction model for postoperative delirium in older patients with hip fracture[J].J Gerontol A Biol Sci Med Sci,2025,80(12): glaf200.DOI: 10.1093/gerona/glaf200.
[41]	DitzelFL,HutSCA,van den BoogaardM,et al.DeltaScan for the assessment of acute encephalopathy and delirium in ICU and non-ICU patients,a prospective cross-sectional multicenter validation study[J].Am J Geriatr Psychiatry,2024,32(9):1093-1104.DOI: 10.1016/j.jagp.2023.12.005.
[42]	姜泽伟,郁慧杰,陈子红,等.“全链智控”重症护理信息数据的设计及临床应用[J].中国中西医结合急救杂志,2023,30(6):739-742.DOI: 10.3969/j.issn.1008-9691.2023.06.020.
[43]	NagamaniGM,KumarCK.Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning[J].Heliyon,2024,10(24):e41071.DOI: 10.1016/j.heliyon.2024.e41071.
[44]	YangY,LinM,ZhaoH,et al.A survey of recent methods for addressing AI fairness and bias in biomedicine[J].J Biomed Inform,2024,154:104646.DOI: 10.1016/j.jbi.2024.104646.
[45]	BakkerT,KlopotowskaJE,DongelmansDA,et al.The effect of computerised decision support alerts tailored to intensive care on the administration of high-risk drug combinations, and their monitoring: a cluster randomised stepped-wedge trial[J].Lancet,2024,403(10425):439-449.DOI: 10.1016/S0140-6736(23)02465-0.
[46]	RozenesS,FuxA,KaganI,et al.Alert-grouping: Smart Personalization of Monitoring System Thresholds to Help Healthcare Teams Struggle with Alarm Fatigue in Intensive Care[J].J Med Syst,2023,47(1):113.DOI: 10.1007/s10916-023-02010-6.
[47]	KeutzerL,SimonssonUS.Medical device apps: an introduction to regulatory affairs for developers[J].JMIR Mhealth Uhealth,2020,8(6):e17567.DOI: 10.2196/17567.