Medical Department Classification Based on Patient Describing Symptoms

Abstract The accurate classification of patients describing symptoms can greatly improve the efficiency of medical department classification, reduce the workload of medical staff, improve the efficiency of patients' registration process, and promote the development of medical informatization. In this study, we proposed a novel neural network based on a hybrid model integrated with an attention mechanism (HMAN), which can automatically match patients to the appropriate department based on the symptoms they described. This system relieves the pressure on the medical staff at the hospital's pre-examination desk and plays a role in diversion for the hospital, more importantly, this model is highly professional and can better avoid the waste of medical resources. Which can effectively improve the work efficiency of the hospital and play a vital role in the long-term development of the hospital. To verify the actual effect of the HMAN, we created a data set of more than 40,000 items, including eight departments, such as ENT, Pediatrics, and other common departments. Self-built dataset experiments reveal that the classification model achieves more than 93.5% accuracy and has a high generalization capacity, which is superior to traditional classification models.