A General Outpatient Triage System Based on Dynamic Uncertain Causality Graph

In order to reduce the misdiagnosis caused by outpatient triage error and help triage nurses to improve their triage accuracy, a general outpatient triage system based on the hybrid Dynamic Uncertain Causality Graph (hybrid DUCG) is presented. The hybrid DUCG is a combination of the single-valued DUCG (S-DUCG) and the multivalued DUCG (M-DUCG). In this paper, the M-DUCG is utilized to construct the basic outpatient triage knowledge base. In the knowledge base, each department is modeled as one sub-M-DUCG. It describes the causal relations between the department and its associated clinical features. All the sub-M-DUCGs are compiled into one M-DUCG as the basic outpatient triage knowledge base. The S-DUCG is employed to adjust the basic knowledge base to match the variant triage requirements for various hospitals. To validate the triage system, we constructed a basic triage knowledge base and adjusted it to match the triage requirement of a county-level hospital. Verification experiments were performed based on the adjusted triage knowledge base. The result showed that the triage system has high triage accuracy, and it can effectively assist triage nurses in outpatient triage.