BACKGROUND: Triage of patients in the emergency department is a complex task based on several uncertainties and ambiguous information. Triage must be implemented within two to five minutes to avoid potential fatality and increased waiting time.
OBJECTIVE: An intelligent triage system has been proposed for use in a triage environment to reduce human error.
METHODS: This system was developed based on the objective primary triage scale (OPTS) that is currently used in the Universiti Kebangsaan Malaysia Medical Center. Both primary and secondary triage models are required to develop this system. The primary triage model has been reported previously; this work focused on secondary triage modelling using an ensemble random forest technique. The randomized resampling method was proposed to balance the data unbalance prior to model development.
RESULTS: The results showed that the 300% resampling gave a low out-of-bag error of 0.02 compared to 0.37 without pre-processing. This model has a sensitivity and specificity of 0.98 and 0.89, respectively, for the unseen data.
CONCLUSION: With this combination, the random forest reduces the variance, and the randomized resembling reduces the bias, leading to the reduced out-of-bag error.
KEYWORDS: Decision support system; emergency department; random forest; randomized resampling
Unexpected disease outbreaks and disasters are becoming primary issues facing our world. The first points of contact either at the disaster scenes or emergency department exposed the frontline workers and medical physicians to the risk of infections. Therefore, there is a persuasive demand for the integration and exploitation of heterogeneous biomedical information to improve clinical practice, medical research and point of care. In this paper, a primary triage model was designed using two different methods: an adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN).When the patient is presented at the triage counter, the system will capture their vital signs and chief complains beside physiology stat and general appearance of the patient. This data will be managed and analyzed in the data server and the patient's emergency status will be reported immediately. The proposed method will help to reduce the queue time at the triage counter and the emergency physician's burden especially duringdisease outbreak and serious disaster. The models have been built with 2223 data set extracted from the Emergency Department of the Universiti Kebangsaan Malaysia Medical Centre to predict the primary triage category. Multilayer feed forward with one hidden layer having 12 neurons has been used for the ANN architecture. Fuzzy subtractive clustering has been used to find the fuzzy rules for the ANFIS model. The results showed that the RMSE, %RME and the accuracy which evaluated by measuring specificity and sensitivity for binary classificationof the training data were 0.14, 5.7 and 99 respectively for the ANN model and 0.85, 32.00 and 96.00 respectively for the ANFIS model. As for unseen data the root mean square error, percentage the root mean square error and the accuracy for ANN is 0.18, 7.16 and 96.7 respectively, 1.30, 49.84 and 94 respectively for ANFIS model. The ANN model was performed better for both training and unseen data than ANFIS model in term of generalization. It was therefore chosen as the technique to develop the primary triage prediction model. This primary triage model will be combined with the secondary triage prediction model to produce the final triage category as a tool to assist the medical officer in the emergency department.