Four machine learning models – multinomial logistic regression (multinomial LR), eXtreme gradient boosting (XGBoost), random forest (RF) and gradient-boosted decision tree (GBDT) – were compared.
Demographic information, vital signs, blood glucose, and other available triage scores were collected.
This cross-sectional study in the second Affiliated Hospital of Guangzhou Medical University was conducted from August 2015 to December 2018 inclusive. 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. The CETS is a reliable system for ED triage and can promote rapid and effective triage in mainland China.Īccurate differentiation and prioritization in emergency department (ED) triage is important to identify high-risk patients and to efficiently allocate of finite resources. The chi-square test showed that there was a significant difference in triage time between the CETS levels (p < 0.001). The average triage time of ED nurses in all sites was 151.5 ± 26.3 s, using the computer-based triage instrument. Trauma cases were assigned to triage with greater accuracy than were nontrauma cases, both for the scenarios and for active patients. Inter-rater reliability values for triage nurses and research nurses were 0.96 (95% CI = 0.95-0.97), based on the quadratic weight κ. There was no difference in accuracy between sites or according to nurse experience. Mean pooled accuracy from all sites was 89.4% (95% CI = 86.9%-91.8%), and the proportion of over-triage slightly exceeded under-triage (6.5% vs. The ability of the CETS to predict ED mortality was assessed via the receiver-operating characteristic (ROC) area under the curve (AUC). The relationship between the CETS acuity levels triaged by the research nurse and four possible outcomes was assessed with a cross-classification table, using a chi-square test.
The criterion-related validity of the CETS was evaluated criteria included ED mortality, number of patients discharged, and admission to ICU or general ward. The triage time and clinical outcome of 1000 active patients per site also were collected. Inter-rater reliability was measured by weighted κ to compare the triage nurse's rating with the research nurse's acuity level for each patient. Accuracy was defined by concordance with the key for the scenarios and was calculated as percentages.
Standardized triage scenarios and active patients were assigned to nurses who used the CETS for evaluative purposes. The aim of this study was to assess the reliability and validity of the CETS by emergency department (ED) nurses in eight EDs in mainland China.Ī cross-sectional multi-center study was conducted.Įight EDs in the eastern, western, northern, and central areas of mainland China.Ī total of 51 ED nurses and 8000 active ED patients participated in the study between May and September 2018 in eight EDs. The Chinese Emergency Triage Scale (CETS) was developed based on vital complaints and vital parameters, according to Chinese data. Each of the tools indicate the number of turning points, useful for editing and resizing of the various objects of your projects.ĭesigned by and for professionals in architecture, packaging and industrial design seamlessly integrates Adobe Illustrator, enriching it with their measurement tools Bezier curves with linear, polar and angular coordinates, dynamic resizing an object simple numerical data collection, integration and transformation CADtracker for instant replays, creating labels and legends, scales settings and more.An effective emergency triage system is lacking in mainland China.
CADtools has been designed especially for industrial and other sensitive high measurement precision professional designers.Įasy installation and ergonomic use, CADtools distributes its tools in four different palettes, fully integrated into Adobe Illustrator, gathering the drawing tools, Dimensioning, Editing and Labeling. Increasing chances of technical drawing in IllustratorĬADtools is a plug-in Illustrator seeks to combine all the graphic and technical performance of this robust application of illustration, a collection consisting of 38 drawing tools, dimensioning and labeling It concentrates ideal for expanding the horizon of your architectural projects, industrial design and technical power.ĭraw using multiple scales at once, resizes your work with the help of mouse movements, and numerically controlled objects.