DL-PER: Deep Learning Model for Chinese Prehospital Emergency Record Classification

Abstract

Prehospital emergency records contain a large amount of information about prehospital emergency patients. Extracting important patient information from many records has become the focus of all prehospital emergency personnel. The key to solving this problem is to achieve the automatic classification of prehospital emergency records. In this study, we consider a deep learning-based pre-hospital emergency record classification model (DL-PER). The model uses a weighted text convolutional neural network to classify pre-hospital emergency records. First, we used prehospital emergency records to train a bidirectional encoder representation (BERT) model from a transformer and let BERT acquire contextual semantic information. Then, we used a bidirectional long and short-term memory (BiLSTM) model to obtain text features from a global perspective and improve the local text feature extraction capability of the model by a weighted text convolutional neural network (WTextCNN). We used activation functions instead of ReLu activation functions to improve the learning ability of the model. We conducted experiments using prehospital emergency records provided by the Handan Emergency Center. The results showed that the DL-PER model improved the F1 scores by up to 5.7%, 6.8%, 5.7%, and 4.9% on the four data sets, respectively, compared with the BiLSTM model.

Keywords

• Deep learning
• text classification
• prehospital emergency
• weighted text convolutional neural network
• bidirectional long short-term memory