Abstract
The purpose of triage is to prevent the delay of treatment for patients in real emergencies due to excessive numbers of patients in the hospital. This study uses the data of patients of consistent triage to develop the triage prediction model. By integrating Principal Component Analysis (PCA) and Support Vector Machine (SVM), the anomaly detection (overestimate and underestimate) prediction accuracy rate can be 100%, which is better than the accuracy rate of SVM (about 89.2%) or Back- propagation Neural Networks (BPNN) (96.71%); afterwards, this study uses Support Vector Regression (SVR) to adopt Genetic Algorithm (GA) to determine three SVR parameters to predict triage. After using the scroll data predictive values, we calculate the Absolute Percentage Error (APE) of each scroll data. The resulting SVR's Mean Absolute Percentage Error (MAPE) is 3.78%, and BPNN's MAPE is 5.99%; therefore, the proposed triage prediction model of this study can effectively predict anomaly detection and triage.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have