DOI QR코드

DOI QR Code

Deep Learning-Based Model for Classification of Medical Record Types in EEG Report

EEG Report의 의무기록 유형 분류를 위한 딥러닝 기반 모델

  • 오경수 (가천대학교 컴퓨터공학과) ;
  • 강민 (가천대학교 IT융합공학과) ;
  • 강석환 (가천대학교 컴퓨터공학과) ;
  • 이영호 (가천대학교 컴퓨터공학과)
  • Received : 2021.09.09
  • Accepted : 2021.10.12
  • Published : 2022.05.31

Abstract

As more and more research and companies use health care data, efforts are being made to vitalize health care data worldwide. However, the system and format used by each institution is different. Therefore, this research established a basic model to classify text data onto multiple institutions according to the type of the future by establishing a basic model to classify the types of medical records of the EEG Report. For EEG Report classification, four deep learning-based algorithms were compared. As a result of the experiment, the ANN model trained by vectorizing with One-Hot Encoding showed the highest performance with an accuracy of 71%.

보건의료 데이터를 사용하는 연구 및 기업이 늘어나며 세계적으로 보건의료 데이터 활성화를 위한 노력을 진행 중이다. 하지만 기관에 따라 사용하는 시스템과 서식이 다르다. 이에 본 연구는 EEG Report의 의무기록 유형을 분류하는 기저 모델 구축을 통해 향후 다기관의 텍스트 데이터를 유형에 따라 분류하는 기저 모델을 구축하였다. EEG Report 분류를 위해 4가지의 딥러닝 기반 알고리즘에 대해 비교하였다. 실험 결과 One-Hot Encoding으로 벡터화하여 학습한 ANN 모델이 71%의 정확도로 가장 높은 성능을 보였다.

Keywords

Acknowledgement

이 논문은 과학기술정보통신부 및 정보통신기획평가원의 대학 ICT센터육성지원사업의 지원으로 연구를 수행하였음(IITP-2021-2017-0-016630).

References

  1. D. Charles, M. Gabriel, and M. F. Furukawa, "Adoption of electronic health record systems among US non-federal acute care hospitals: 2008-2014," Washington, DC: Office of the National Coordinator for Health Information Technology, No.23, pp.1-10, 2015.
  2. Korea University Anam Hospital, EEG, curious about that [Internet], http://anam.kumc.or.kr/info/examInfoView.do?BNO=13&cPage=1&BOARD_ID=S003.
  3. Y. Gao, B. Gao, Q Chen, J. Liu, and Y. Zhang, "Deep convolutional neural network-based epileptic electroencephalogram (EEG) signal classification," Frontiers in Neurology, Vol.11, 2020.
  4. S. Raghu, N Sriraam, Y Temel, S. V. Rao, and P. L. Kubben, "EEG based multi-class seizure type classification using convolutional neural network and transfer learning," Neural Networks, Vol.124, pp.202-212, 2020. https://doi.org/10.1016/j.neunet.2020.01.017
  5. Y. Wang et al., "A clinical text classification paradigm using weak supervision and deep representation," BMC Medical Informatics and Decision Making, Vol.19, No.1, pp.1-13, 2019. https://doi.org/10.1186/s12911-018-0723-6
  6. T. R. Goodwin and S. M. Harabagiu, "Deep learning from EEG reports for inferring underspecified information," in AMIA Joint Summits on Translational Science Proceedings, pp.112-121, 2017.
  7. J. Kim, D. Seo, H. Kim, and P. Kang, "Facebook spam post filtering based on instagram-based transfer learning and meta information of posts," Journal of the Korean Institute of Industrial Engineers, Vol.43, No.3, pp.192-202, 2017. https://doi.org/10.7232/JKIIE.2017.43.3.192
  8. D. Kim and M. W. Koo, "Categorization of Korean news articles based on convolutional neural network using Doc2Vec and Word2Vec," Journal of Korean Institute of Information Scientists and Engineers, Vol.44, No.7, pp.742-747, 2017.
  9. G. Liu and J. Guo, "Bidirectional LSTM with attention mechanism and convolutional layer for text classification," Neurocomputing, Vol.337, pp.325-338, 2019. https://doi.org/10.1016/j.neucom.2019.01.078
  10. Y. Chen, X. Zhang, and T. Li, "Medical records classification model based on text-image dual-mode fusion," in 2021 4th International Conference on Artificial Intelligence and Big Data (ICAIBD), IEEE, pp.432-436, 2021.
  11. L. Qing, W. Linhong, and D. Xuehai, "A novel neural Network-Based method for medical text classification," Future Internet, Vol.11, No.12, pp.255, 2019. https://doi.org/10.3390/fi11120255
  12. I. Y. Jung, "Startup trends using domestic and foreign health and medical big data" [Internet], https://repository.hira.or.kr/handle/2019.oak/1473.
  13. M. D. Wilkinson, M. Dumontier, and I. J. Aalbersberg, "The FAIR guiding principles for scientific data management and stewardship," Scientific Data, Vol.3, No.1, pp.1-9, 2016.
  14. National Institutes of Health, STRIDES Initiative [Internet], https://datascience.nih.gov/strides.
  15. S. A. Kim, "Meanings and tasks of the three revised bills which ease regulations on the use of personal information," Jouranl of Information and Security, Vol.20, No.2, pp.59-68, 2020. https://doi.org/10.33778/kcsa.2020.20.2.059
  16. K. J. Kim, B. Y. Jang, J. Y. Jung, and O. W. Park, "The coming of the 4th industrial revolution and the HRD Issues for nurses - prospects and challenges," Korean Journal of Resources Development, Vol.21, No.3, pp.137-159, 2018. https://doi.org/10.24991/kjhrd.2018.09.21.3.137
  17. Health Insurance Review & Assessment Service, Current status of introduction and development of electronic medical records in Korea [Internet], https://www.hira.or.kr/bbsDummy.do?pgmid=HIRAA030096000000&brdScnBltNo=4&brdBltNo=623.
  18. Korea Health Information Service, 2020 Health and Medical Informatization Survey Results Report [Internet], https://www.k-his.or.kr/board.es?mid=a10306040000&bid=0005&act=view&list_no=283&tag=&nPage=1.
  19. J. Y. Lee, Y. Kim, and G. Kim, "A study on the analysis and methods to improve the medical records management in a large university hospital," Journal of Korean Society of Archives and Records Management, Vol.13, No.1, pp.107-134, 2013. https://doi.org/10.14404/JKSARM.2013.13.1.107
  20. E. M. Lee, M. Kim, and J. Hee, "A study on the current status and tasks of medical records management: Focused on applying the KS X ISO 15489 to the Y hospital," Journal of the Korean Society for information Management, Vol.29, No.3, pp.257-285, 2012. https://doi.org/10.3743/KOSIM.2012.29.3.257
  21. American Clinical Neurophysiology Society, "Guideline 7: guidelines for writing EEG reports," American Journal of Electroneurodiagnostic Technology, Vol.46, No.3, pp.231-235, 2006. https://doi.org/10.1080/1086508x.2006.11079582
  22. I. Obeid and J. Picone, "The temple university hospital EEG data corpus," Frontiers in Neuroscience, Data Report, Vol. 10, No.196, 2016.
  23. S. Bird, "NLTK: The natural language toolkit," in Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions, pp.69-72, 2006.
  24. S. Bird, E. Klein, and E. Loper, "Natural language processing with Python: Analyzing text with the natural language toolkit," O'Reilly Media, Inc., 2009.
  25. Google Developers, Step 3: Prepare Your Data [Internet], https://developers.google.com/machine-learning/guides/text-classification/step-3.
  26. R. Zhao and K. Mao, "Fuzzy bag-of-words model for document representation," IEEE Transactions on Fuzzy Systems, Vol.26, No.2, pp.794-804, 2018. https://doi.org/10.1109/tfuzz.2017.2690222
  27. W. Zhang, T. Yoshida, and X. Tang, "A comparative study of TF* IDF, LSI and multi-words for text classification," Expert Systems with Applications, Vol.38, No.3, pp.2758-2765, 2011. https://doi.org/10.1016/j.eswa.2010.08.066
  28. M. Bihis and S. Roychowdhury, "A generalized flow for multiclass and binary classification tasks: An azure ML approach," 2015 IEEE International Conference on Big Data (Big Data), pp.1728-1737, 2015.
  29. S. S. Lim, H. Lee, and Y. M. Yoon, "Prediction of new drug-side effect relation using Word2Vec model-based word similarity," Journal of Korean Institute of Information Technology, Vol.18, No.11, pp.25-33, 2020. https://doi.org/10.14801/jkiit.2020.18.11.25
  30. A. M. Shah, X. Yan, and A. Qayyum, "Social network analysis of an online smoking cessation community to identify users' smoking status," Healthcare Informatics Research, Vol.27, No.2, pp.116-126, 2021. https://doi.org/10.4258/hir.2021.27.2.116
  31. J. Xu, X. Ren, J. Lin, and X. Sun, "DP-GAN: Diversity-promoting generative adversarial network for generating informative and diversified text," arXiv preprint arXiv: 1802.01345, 2018.