Haiming Zhou
ABSTRACT
In the field of medicine, the Chinese electronic medical records are complicated and professional, so the extraction of the knowledge on them is a challenging task. In this paper, a new annotation collection of electronic Chinese medical records is proposed, which aims at reducing the complexity of electronic medical record analysis through the universal annotations of the electronic medical records. Meanwhile, the Word2vec+Char2vec+BiLSTM+CRF (WCBC) model is proposed for the annotations of the electronic medical recordings. To verify the validity of the proposed method, we annotated 20000 Chinese electronic medical records manually under the support of medical experts. On this dataset, we compare the WCBC model with the state-of-the-art models such as Hidden Markov Model (HMM) and Support Vector Machine (SVM) based methods. Experiments show that the comprehensive annotation accuracy of our method is up to 85%, which outperforms other methods obviously.
- I. K. Ampomah, S.-B. Park, and S.-J. Lee. A sentence-to-sentence relation network for recognizing textual entailment. World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 10(12):2060--2063, 2016.Google Scholar
- O.Bodenreider.Theunifiedmedicallanguagesystem(umls): int egrating biomedical terminology. Nucleic acids research, 32(suppl 1):D267-- D270, 2004.Google Scholar
- F. Chang, J. Guo, W. Xu, and S. R. Chung. Application of word embeddings in biomedical named entity recognition tasks. Journal of Digital Information Management, 13(5), 2015.Google Scholar
- C. Friedman and S. B. Johnson. Natural language and text processing in biomedicine. In Biomedical Informatics, pages 312--343. Springer, 2006.Google ScholarCross Ref
- B. Gann. Giving patients choice and control: health informatics on the patient journey. Yearbook of medical informatics, 7:70--3, 2012.Google Scholar
- J. Groopman. How doctors think. Houghton Mifflin Harcourt, 2008.Google Scholar
- Z.Huang, W.Xu, and K.Yu.Bidirectionallstm-crfmodelsforsequence tagging. arXiv preprint arXiv:1508.01991, 2015.Google Scholar
- V. Jatav, R. Teja, S. Bharadwaj, and V. Srinivasan. Improving part- of-speech tagging for nlp pipelines. arXiv preprint arXiv:1708.00241, 2017.Google Scholar
- X. Kong, Y. Li, H. Li, and X. Lu. Structuralization of digestive endoscopy report based on nlp. Zhongguo yi liao qi xie za zhi= Chinese journal of medical instrumentation, 32(5):348--351, 2008.Google Scholar
- G.Lample, M.Ballesteros, S.Subramanian, K.Kawakami, and C. Dyer. Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360, 2016.Google Scholar
- L. Li, L. Jin, Y. Jiang, and D. Huang. Recognizing biomedical named entities based on the sentence vector/twin word embeddings conditioned bidirectional lstm. In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, pages 165--176. Springer, 2016.Google ScholarCross Ref
- P. Liu, X. Wang, X. Sun, X. Shen, X. Chen, Y. Sun, and Y. Pan. Hkdp: A hybrid knowledge graph based pediatric disease prediction system. In International Conference on Smart Health, pages 78--90. Springer, 2016.Google Scholar
- S. M. Meystre and P. J. Haug. Comparing natural language processing tools to extract medical problems from narrative text. In AMIA annual symposium proceedings, volume 2005, page 525. American Medical Informatics Association, 2005.Google Scholar
- T. Nakagawa, T. Kudo, and Y. Matsumoto. Unknown word guessing and part-of-speech tagging using support vector machines. In NLPRS, pages 325--331. Citeseer, 2001.Google Scholar
- J. Paparrizos, R. W. White, and E. Horvitz. Screening for pancreatic adenocarcinoma using signals from web search logs: Feasibility study and results. Journal of Oncology Practice, 12(8):737--744, 2016.Google ScholarCross Ref
- M. Rotmensch, Y. Halpern, A. Tlimat, S. Horng, and D. Sontag. Learning a health knowledge graph from electronic medical records. Scientific reports, 7(1):5994, 2017.Google ScholarCross Ref
- D. S. Sachan and Petuum. Revisiting lstm networks for semi-supervised text classification via mixed objective function. KDD-18 Deep Learning Day, 2018.Google Scholar
- E. H. Shortliffe. Mycin: Computer-based medical consultations, 1976.Google Scholar
- H. Tang and J. H. K. Ng. Googling for a diagnosisa use of google as a diagnostic aid: internet based study. Bmj, 333(7579): 1143--1145, 2006. [20] S. M. Thede and M. P. Harper. A second-order hidden markov model for part-of-speech tagging. In Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, pages 175--182. Association for Computational Linguistics, 1999.Google ScholarCross Ref
- R. W. White and E. Horvitz. Cyberchondria: studies of the escalation of medical concerns in web search. ACM Transactions on Information Systems (TOIS), 27(4):23, 2009.Google Scholar
Index Terms
- Annotations of Chinese Electronic Medical Record using BiLSTM-CRF based Networks
Recommendations
A BERT-Based Named Entity Recognition in Chinese Electronic Medical Record
ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern RecognitionNamed entity recognition, aiming at identifying and classifying named entity mentioned in the structured or unstructured text, is a fundamental subtask for information extraction in natural language processing (NLP). With the development of electronic ...
A BiLSTM-CRF Method to Chinese Electronic Medical Record Named Entity Recognition
ACAI '18: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial IntelligenceWith the application of electronic medical records in medical field, more and more people are paying attention to how to use these data efficiently. In this paper, the BiLSTM-CRF model is applied to Chinese electronic medical records to recognize ...
Semantic-Based Exchanger for Electronic Medical Record
ICCIT '08: Proceedings of the 2008 Third International Conference on Convergence and Hybrid Information Technology - Volume 01Considering the importance of the patient's medical information for the caregivers to ensure that patients receive appropriate and safe treatment, especially the emergency room (ER) patients, thus, sharing distributed medical information among ...
Comments