Huilin Jiang1, Haifeng Mao2, Huimin Lu3, Peiyi Lin4, Wei Garry5, Huijing Lu6, Guangqian Yang7, Timothy H Rainer8, Xiaohui Chen9. 1. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: lifisher@126.com. 2. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: maomao2010x@163.com. 3. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: 416905920@qq.com. 4. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: linpeiyi@163.com. 5. Goodwill Hessian Health Technology Co., Ltd, Beijing, China. Electronic address: ganwei@hessianhealth.com. 6. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: 3025515@qq.com. 7. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: 413116384@qq.com. 8. Accident and Emergency Medicine Academic Unit, Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong, China. Electronic address: thrainer@cuhk.edu.hk. 9. Emergency Department, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Electronic address: cxhgz168paper@163.com.
Abstract
BACKGROUND: Accurate differentiation and prioritization in emergency department (ED) triage is important to identify high-risk patients and to efficiently allocate of finite resources. Using data available from patients with suspected cardiovascular disease presenting at ED triage, this study aimed to train and compare the performance of four common machine learning models to assist in decision making of triage levels. METHODS: This cross-sectional study in the second Affiliated Hospital of Guangzhou Medical University was conducted from August 2015 to December 2018 inclusive. Demographic information, vital signs, blood glucose, and other available triage scores were collected. Four machine learning models - multinomial logistic regression (multinomial LR), eXtreme gradient boosting (XGBoost), random forest (RF) and gradient-boosted decision tree (GBDT) - were compared. For each model, 80 % of the data set was used for training and 20 % was used to test the models. The area under the receiver operating characteristic curve (AUC), accuracy and macro- F1 were calculated for each model. RESULTS: In 17,661 patients presenting with suspected cardiovascular disease, the distribution of triage of level 1, level 2, level 3 and level 4 were 1.3 %, 18.6 %, 76.5 %, and 3.6 % respectively. The AUCs were: XGBoost (0.937), GBDT (0.921), RF (0.919) and multinomial LR (0.908). Based on feature importance generated by XGBoost, blood pressure, pulse rate, oxygen saturation, and age were the most significant variables for making decisions at triage. CONCLUSION: Four machine learning models had good discriminative ability of triage. XGBoost demonstrated a slight advantage over other models. These models could be used for differential triage of low-risk patients and high-risk patients as a strategy to improve efficiency and allocation of finite resources.
BACKGROUND: Accurate differentiation and prioritization in emergency department (ED) triage is important to identify high-risk patients and to efficiently allocate of finite resources. Using data available from patients with suspected cardiovascular disease presenting at ED triage, this study aimed to train and compare the performance of four common machine learning models to assist in decision making of triage levels. METHODS: This cross-sectional study in the second Affiliated Hospital of Guangzhou Medical University was conducted from August 2015 to December 2018 inclusive. Demographic information, vital signs, blood glucose, and other available triage scores were collected. Four machine learning models - multinomial logistic regression (multinomial LR), eXtreme gradient boosting (XGBoost), random forest (RF) and gradient-boosted decision tree (GBDT) - were compared. For each model, 80 % of the data set was used for training and 20 % was used to test the models. The area under the receiver operating characteristic curve (AUC), accuracy and macro- F1 were calculated for each model. RESULTS: In 17,661 patients presenting with suspected cardiovascular disease, the distribution of triage of level 1, level 2, level 3 and level 4 were 1.3 %, 18.6 %, 76.5 %, and 3.6 % respectively. The AUCs were: XGBoost (0.937), GBDT (0.921), RF (0.919) and multinomial LR (0.908). Based on feature importance generated by XGBoost, blood pressure, pulse rate, oxygen saturation, and age were the most significant variables for making decisions at triage. CONCLUSION: Four machine learning models had good discriminative ability of triage. XGBoost demonstrated a slight advantage over other models. These models could be used for differential triage of low-risk patients and high-risk patients as a strategy to improve efficiency and allocation of finite resources.
Authors: Sergio Sanchez-Martinez; Oscar Camara; Gemma Piella; Maja Cikes; Miguel Ángel González-Ballester; Marius Miron; Alfredo Vellido; Emilia Gómez; Alan G Fraser; Bart Bijnens Journal: Front Cardiovasc Med Date: 2022-01-04