基于机器学习的重症患者脓毒症实时风险预测模型

doi:10.3969/j.issn.0258-8021.2024.01.001

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (4471 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Sepsis is a syndrome of organ dysfunction caused by the body's dysfunctional response to infection, with high morbidity and mortality. The traditional scoring system has low specificity. Based on the LightGBM machine learning framework, this study proposed a model for early prediction and risk assessment of sepsis to provide timely intervention for patients with potential risk of sepsis. In order to realize the model, a time series feature construction method based on LASSO feature selection and sliding window path reintegration and a time series clustering sampling method based on dynamic time regularization algorithm were proposed. We selected clinical information from 29 239 patients in the MIMIC-III dataset and 40 336 patients in the PhysioNet/CinC 2019 challenge dataset to train and validate the model. The sensitivity, specificity, and area under the receiver operation characteristic curve (AUC) of the proposed model on the MIMIC-III and PhysioNet/CinC 2019 independent test sets were 0.737 7, 0.730 4, 0.814 7 and 0.802 6, 0.789 1, 0.873 0, respectively. Compared with the state-of-the-art method EASP, the improvement of AUC was 3.62% and 2.83% respectively. In conclusion, the established model could predict the risk of sepsis in real time, reveal the important factors affecting the occurrence of sepsis, and provide a basis for timely intervention of people at risk of sepsis.

Key words： sepsis prediction machine learning feature construction time series sampling

Received: 19 June 2023

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Li Runfa
	Yang Meicheng
	Li Jianqing
	Liu Chengyu

Cite this article:

Li Runfa,Yang Meicheng,Li Jianqing, et al. Sepsis Real-Time Risk Prediction Model for Intensive Care Unit Patients Based on Machine Learning[J]. Chinese Journal of Biomedical Engineering, 2024, 43(1): 1-9.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2024.01.001 OR http://cjbme.csbme.org/EN/Y2024/V43/I1/1

[1] Fleischmann C, Scherag A, Adhikari NKJ, et al.Assessment of global incidence and mortality of hospital-treated sepsis. Current estimates and limitations[J]. American Journal of Respiratory and Critical Care Medicine, 2016, 193(3): 259-272.
[2] Rhee C, Dantes R, Epstein L, et al.Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009-2014[J]. Journal of the American Medical Association, 2017, 318(13): 1241-1249.
[3] Kumar A, Roberts D, Wood KE, et al.Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock[J]. Critical Care Medicine, 2006, 34(6): 1589-1596.
[4] Vincent J, Moreno R, Takala J, et al.The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure[J]. Intensive Care Medicine, 1996, 22(7): 707-710.
[5] Singer M, Deutschman C, Seymour C, et al.The third international consensus definitions for sepsis and septic shock (Sepsis-3)[J]. Journal of the American Medical Association, 2016, 315(8): 775-787.
[6] Smith GB, Prytherch DR, Paul M, et al.The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death[J]. Resuscitation, 2013, 84(4): 465-470.
[7] Delahanty RJ, Alvarez JA, Flynn LM, et al.Development and evaluation of a machine learning model for the early identification of patients at risk for sepsis[J]. Annals of Emergency Medicine, 2019, 73(4): 334-344.
[8] Yang Meicheng, Wang Xingyao, Gao Hongxiang, et al.An explainable artificial intelligence predictor for early detection of sepsis[J]. Critical Care Medicine, 2020, 48(11): e1091-e1096.
[9] Zhang Tianyi, Zhong Ming, Cheng Yunzhang, et al.An interpretable machine learning model for real-time sepsis prediction based on basic physiological indicators[J]. European Review for Medical and Pharmacological Sciences, 2023, 27: 4348-4356.
[10] Futoma J, Hariharan S, Heller K.Learning to detect sepsis with a multitask Gaussian process RNN classifier[C]//International Conference on Machine Learning. Sydney: PMLR, 2017: 1174-1182.
[11] Wang Zekai, Yao Bing.Multi-branching temporal convolutional network for sepsis prediction[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 26(2): 876-887.
[12] Reyna MA, Josef C, Seyedi S, et al.Early prediction of sepsis from clinical data: the PhysioNet/Computing in Cardiology Challenge 2019[C]//2019 Computing in Cardiology. Singapore: IEEE, 2019: 1-4.
[13] Wang S, McDermott MBA, Chauhan G, et al. Mimic-extract: a data extraction, preprocessing, and representation pipeline for mimic-iii[C]//Proceedings of the ACM Conference on Health, Inference, and Learning. Toronto: ACM, 2020: 222-235.
[14] 梁怀新, 宋佳霖, 郑存芳, 等. 肿瘤参数属性偏序结构可视化实现乳腺癌诊断[J]. 中国生物医学工程学报, 2018, 37(4): 404-413.
[15] Pfeffer M, Seigal A, Sturmfels B.Learning paths from signature tensors[J]. SIAM Journal on Matrix Analysis and Applications, 2019, 40(2): 394-416.
[16] Morrill JH, Kormilitzin A, Nevado-Holgado AJ, et al.Utilization of the signature method to identify the early onset of sepsis from multivariate physiological time series in critical care monitoring[J]. Critical Care Medicine, 2020, 48(10): e976-e981.
[17] Hambly B, Lyons T.Uniqueness for the signature of a path of bounded variation and the reduced path group[J]. Annals of Mathematics, 2010, 171(1): 109-167.
[18] Liu Shuhui, Fu Bo, Wang Wen, et al.Dynamic sepsis prediction for intensive care unit patients using XGBoost-based model with novel time-dependent features[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(8): 4258-4269.
[19] 张钦, 郭圣文, 梁馨苓, 等. 住院患者急性肾损伤的风险预测与关键影响因素分析[J]. 中国生物医学工程学报, 2019, 38(6): 702-710.
[20] Wickramaratne SD, Mahmud MDS.Bi-directional gated recurrent unit based ensemble model for the early detection of sepsis[C]//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal: IEEE, 2020: 70-73.
[21] Catling FJR, Wolff AH.Temporal convolutional networks allow early prediction of events in critical care[J]. Journal of the American Medical Informatics Association, 2020, 27(3): 355-365.