Abstract
BackgroundWith the rapid spread of electronic medical records and the arrival of medical big data era, the application of natural language processing technology in biomedicine has become a hot research topic.MethodsIn this paper, firstly, BiLSTM-CRF model is applied to medical named entity recognition on Chinese electronic medical record. According to the characteristics of Chinese electronic medical records, obtain the low-dimensional word vector of each word in units of sentences. And then input the word vector to BiLSTM to realize automatic extraction of sentence features. And then CRF performs sentence-level word tagging. Secondly, attention mechanism is added between the BiLSTM and the CRF to construct Attention-BiLSTM-CRF model, which can leverage document-level information to alleviate tagging inconsistency. In addition, this paper proposes an entity auto-correct algorithm to rectify entities according to historical entity information. At last, a drug dictionary and post-processing rules are well-built to rectify entities, to further improve performance.ResultsThe final F1 scores of the BiLSTM-CRF and Attention-BiLSTM-CRF model on given test dataset are 90.15 and 90.82% respectively, both of which are higher than 89.26%, which is the best F1 score on the test dataset except ours.ConclusionOur approach can be used to recognize medical named entity on Chinese electronic medical records and achieves the state-of-the-art performance on the given test dataset.
Highlights
With the rapid spread of electronic medical records and the arrival of medical big data era, the application of natural language processing technology in biomedicine has become a hot research topic
By adding attention mechanism into BiLSTM-conditional random field (CRF), we construct Attention-BiLSTM-CRF model and apply it to Named Entity Recognition (NER) in Chinese Electronic medical record (EMR), which aims at alleviating tagging inconsistency problem by leveraging document-level information
The test results of the two neural network models on the given test dataset are shown in Table 3, which are provided by the Conference on Knowledge Graph and Semantic Computing (CCKS) 2018 evaluation platform [19], and the definition of strict index can be found on this evaluation platform, too
Summary
With the rapid spread of electronic medical records and the arrival of medical big data era, the application of natural language processing technology in biomedicine has become a hot research topic. Named Entity Recognition (NER) is a basic task in Natural Language Processing (NLP). NER is to recognize three kinds of named entity, which are name, place, and organization [1]. With rapid development of electronic medical records and clinical information, doctors need information-based. Different hospitals and even different doctors may name the same entity differently; secondly, there may be several names for one entity, e.g. a drug can have tens of trade names; thirdly, new entities are constantly being created; last but not least, usage of Chinese is flexible. Some words cannot be judged as named entities without context, and there is no space between Chinese characters as boundary mark
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have