Early identification of high-risk patients admitted to emergency departments using vital signs and machine learning

被引:0
作者
Qingyuan Liu [1 ]
Yixin Zhang [2 ]
Jian Sun [3 ]
Kaipeng Wang [4 ]
Yueguo Wang [3 ]
Yulan Wang [3 ]
Cailing Ren [3 ]
Yan Wang [3 ]
Jiashan Zhu [3 ]
Shusheng Zhou [3 ]
Mengping Zhang [2 ]
Yinglei Lai [2 ]
Kui Jin [3 ]
机构
[1] School of Mathematics and Physics, Anhui Jianzhu University
[2] School of Mathematical Sciences, University of Science and Technology of China
[3] Department of Emergency Medicine, the First Affiliated Hospital of University of Science and Technology of China, Division of Life Sciences and Medicine, University of Science and Technology of China
[4] School of Mathematics and Statistics, Nanjing University of Science and
关键词
D O I
暂无
中图分类号
R459.7 [急症、急救处理];
学科分类号
100218 ;
摘要
BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments (EDs) is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment (CETAT) database,which was collected between January 1st,2020,and June 25th,2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron (MLP) classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8 (Scenario I),and a scenario requiring specificity greater than 0.8 (Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression (LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score (NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation (SpO2),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.
引用
收藏
页码:113 / 120
页数:8
相关论文
共 26 条
[1]  
Artificial intelligence promotes shared decision-making through recommending tests to febrile pediatric outpatients.[J].Wei-hua Li;Bin Dong;Han-song Wang;Jia-jun Yuan;Han Qian;Ling-ling Zheng;Xu-lin Lin;Zhao Wang;Shi-jian Liu;Bo-tao Ning;Dan Tian;Lie-bin Zhao;.World Journal of Emergency Medicine.2023, 02
[2]   基于倾向性评分匹配法急诊院前救护(EMS)与病情危重程度及相关影响因素的研究 [J].
金魁 ;
王恺鹏 ;
刘庆源 ;
汪跃国 ;
王玉兰 ;
黄崇建 ;
王焕力 ;
周树生 ;
赖颖蕾 ;
张梦萍 ;
徐军 .
中华急诊医学杂志, 2021, (12) :1514-1522
[3]  
Initial emergency department vital signs may predict PICU admission in pediatric patients presenting with asthma exacerbation..[J].Freedman Michael S;Forno Erick.The Journal of asthma : official journal of the Association for the Care of Asthma.2022, 5
[4]   The association between vital signs and clinical outcomes in emergency department patients of different age categories [J].
Candel, Bart G. J. ;
Duijzer, Renee ;
Gaakeer, Menno, I ;
ter Avest, Ewoud ;
Sir, Ozcan ;
Lameijer, Heleen ;
Hessels, Roger ;
Reijnen, Resi ;
van Zwet, Erik W. ;
de Jonge, Evert ;
de Groot, Bas .
EMERGENCY MEDICINE JOURNAL, 2022, 39 (12) :903-911
[5]   Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department [J].
Lee, Jung-Ting ;
Hsieh, Chih-Chia ;
Lin, Chih-Hao ;
Lin, Yu-Jen ;
Kao, Chung-Yao .
SCIENTIFIC REPORTS, 2021, 11 (01)
[6]   An Explainable Artificial Intelligence Predictor for Early Detection of Sepsis [J].
Yang, Meicheng ;
Liu, Chengyu ;
Wang, Xingyao ;
Li, Yuwen ;
Gao, Hongxiang ;
Liu, Xing ;
Li, Jianqing .
CRITICAL CARE MEDICINE, 2020, 48 (11) :E1091-E1096
[7]   Explainable artificial intelligence model to predict acute critical illness from electronic health records [J].
Lauritsen, Simon Meyer ;
Kristensen, Mads ;
Olsen, Mathias Vassard ;
Larsen, Morten Skaarup ;
Lauritsen, Katrine Meyer ;
Jorgensen, Marianne Johansson ;
Lange, Jeppe ;
Thiesson, Bo .
NATURE COMMUNICATIONS, 2020, 11 (01)
[8]   Comparing public and private emergency departments in China: Early evidence from a national healthcare quality survey [J].
Jin, Kui ;
Zhang, Hui ;
Seery, Sam ;
Fu, Yangyang ;
Yu, Shanshan ;
Zhang, Lili ;
Sun, Feng ;
Tian, Liyuan ;
Xu, Jun ;
Yue, Xue Zhong .
INTERNATIONAL JOURNAL OF HEALTH PLANNING AND MANAGEMENT, 2020, 35 (02) :581-591
[9]   Emergency department triage prediction of clinical outcomes using machine learning models [J].
Raita, Yoshihiko ;
Goto, Tadahiro ;
Faridi, Mohammad Kamal ;
Brown, David F. M. ;
Camargo, Carlos A., Jr. ;
Hasegawa, Kohei .
CRITICAL CARE, 2019, 23 (1)
[10]   Scalable and accurate deep learning with electronic health records [J].
Rajkomar, Alvin ;
Oren, Eyal ;
Chen, Kai ;
Dai, Andrew M. ;
Hajaj, Nissan ;
Hardt, Michaela ;
Liu, Peter J. ;
Liu, Xiaobing ;
Marcus, Jake ;
Sun, Mimi ;
Sundberg, Patrik ;
Yee, Hector ;
Zhang, Kun ;
Zhang, Yi ;
Flores, Gerardo ;
Duggan, Gavin E. ;
Irvine, Jamie ;
Quoc Le ;
Litsch, Kurt ;
Mossin, Alexander ;
Tansuwan, Justin ;
Wang, De ;
Wexler, James ;
Wilson, Jimbo ;
Ludwig, Dana ;
Volchenboum, Samuel L. ;
Chou, Katherine ;
Pearson, Michael ;
Madabushi, Srinivasan ;
Shah, Nigam H. ;
Butte, Atul J. ;
Howell, Michael D. ;
Cui, Claire ;
Corrado, Greg S. ;
Dean, Jeffrey .
NPJ DIGITAL MEDICINE, 2018, 1