Background: Named entity recognition (NER) of electronic medical records is an important task in clinical medical research. Although deep learning combined with pretraining models performs well in recognizing entities in clinical texts, because Chinese electronic medical records have a special text structure and vocabulary distribution, general pretraining models cannot effectively incorporate entities and medical domain knowledge into representation learning; separate deep network models lack the ability to fully extract rich features in complex texts, which negatively affects the named entity recognition of electronic medical records.Methods: To better represent electronic medical record text, we extract the text’s local features and multilevel sequence interaction information to improve the effectiveness of electronic medical record named entity recognition. This paper proposes a hybrid neural network model based on medical MC-BERT, namely, the MC-BERT + BiLSTM + CNN + MHA + CRF model. First, MC-BERT is used as the word embedding model of the text to obtain the word vector, and then BiLSTM and CNN obtain the feature information of the forward and backward directions of the word vector and the local context to obtain the corresponding feature vector. After merging the two feature vectors, they are sent to multihead self-attention (MHA) to obtain multilevel semantic features, and finally, CRF is used to decode the features and predict the label sequence.Results: The experiments show that the F1 values of our proposed hybrid neural network model based on MC-BERT reach 94.22%, 86.47%, and 92.28% on the CCKS-2017, CCKS-2019 and cEHRNER datasets, respectively. Compared with the general-domain BERT-based BiLSTM + CRF, our F1 values increased by 0.89%, 1.65% and 2.63%. Finally, we analyzed the effect of an unbalanced number of entities in the electronic medical records on the results of the NER experiment.

Decoupling agricultural economic growth from agricultural water pollution is of great importance to regional sustainable development. It is necessary to further explore the decoupling state and key driving factors connecting agricultural water pollution and agricultural economic growth on the basis of accurate measurement of agricultural water pollution. Accordingly, taking the Yellow River Basin (YRB) as the research object, this study combined the water footprint theory, the Logarithmic Mean Divisia Index (LMDI) model and the Tapio decoupling model (TDM) to conduct an in-depth decoupling analysis of the connection between the agricultural grey water footprint (AGWF) and agricultural economic growth in the YRB. Specifically, this study first calculated the AGWF of the YRB during 2016–2021 and objectively evaluated the water resource utilization in this region based on the AGWF. Then, the LMDI model was used to explore the driving factors of the AGWF in the YRB. Finally, the decoupling states between the AGWF and its driving factors with agricultural GDP (AGDP) were studied using the TDM. The main results are as follows: (1) The overall AGWF in the YRB showed a decreasing trend and a slow increase, decreasing by 5.39% in 2021 compared to 2016. (2) The primary promoting factor and inhibiting factor of AGWF reduction are the efficiency effect and agricultural economic effect, respectively. (3) The decoupling states of the AGWF and AGDP presented strong decoupling (SD) and then weak decoupling (WD) in the YRB during the research period. The decoupling states between the agricultural grey water footprint intensity (AGWFI) and AGDP changed from expansive negative decoupling (END) to SD. The decoupling state of population and AGDP remained SD. This study will contribute to alleviating agricultural water pollution in the YRB and help policymakers in water-stressed countries to formulate agricultural water management policies.

Model robustness is an important index in medical cybersecurity, and hard-negative samples in electronic medical records can provide more gradient information, which can effectively improve the robustness of a model. However, hard negatives pose difficulties in terms of their definition and acquisition. To solve these problems, a data augmentation approach consisting of fusing SimBERT and a knowledge graph for application to a hard-negative sample is proposed in this paper. Firstly, we selected 40 misdiagnosed cases of diabetic complications as the original data for data augmentation. Secondly, we divided the contents of the electronic medical records into two parts. One part consisted of the core disease phrases in the misdiagnosed case records, which a medical specialist selected. These denoted the critical diseases that the model diagnosed as negative samples. Based on these core symptom words, new symptom phrases were directly generated using the SimBERT model. On the other hand, the noncore phrases of misdiagnosed medical records were highly similar to the positive samples. We determined the cosine similarity between the embedding vector of the knowledge graph entities and a vector made up of the noncore phrases. Then, we used Top-K sampling to generate text. Finally, combining the generated text from the two parts and the disturbed numerical indexes resulted in 160 enhancement samples. Our experiment shows that the distances between the samples generated using the SimKG-BERT model’s samples were closer to those of the positive samples and the anchor points in the space vector were closer than those created using the other models. This finding is more in line with how hard negatives are defined. In addition, compared with the model without data augmentation, the F1 values in the three data sets of diabetic complications increased by 6.4%, 2.24%, and 5.54%, respectively. The SimKG-BERT model achieves data augmentation in the absence of misdiagnosed medical records, providing more gradient information to the model, which not only improves the robustness of the model but also meets the realistic needs of assisted-diagnosis safety.

Purpose–long–short term memory (LSTM) is widely used inrelation extraction.