The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Automatic Electronic Medical Record Generation System using Speech Recognition and Natural Language Processing Deep Learning

음성인식과 자연어 처리 딥러닝을 통한 전자의무기록자동 생성 시스템

  • Hyeon-kon Son ;
  • Gi-hwan Ryu (Department of Tourism Industry, Graduate school of smart convergence, Kwangwoon University)
  • 손현곤 (광운대학교 대학원 실감융합콘텐츠학과) ;
  • 류기환 (광운대학교 스마트융합대학원)
  • Received : 2023.03.31
  • Accepted : 2023.05.01
  • Published : 2023.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the medical field has been applying mandatory Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) systems that computerize and manage medical records, and distributing them throughout the entire medical industry to utilize patients' past medical records for additional medical procedures. However, the conversations between medical professionals and patients that occur during general medical consultations and counseling sessions are not separately recorded or stored, so additional important patient information cannot be efficiently utilized. Therefore, we propose an electronic medical record system that uses speech recognition and natural language processing deep learning to store conversations between medical professionals and patients in text form, automatically extracts and summarizes important medical consultation information, and generates electronic medical records. The system acquires text information through the recognition process of medical professionals and patients' medical consultation content. The acquired text is then divided into multiple sentences, and the importance of multiple keywords included in the generated sentences is calculated. Based on the calculated importance, the system ranks multiple sentences and summarizes them to create the final electronic medical record data. The proposed system's performance is verified to be excellent through quantitative analysis.

최근 의료 현장은 전자의무기록, 전자건강기록 등의 의료 기록을 전산화하여 저장하고 관리하는 시스템이 의무적으로 적용되거나 전체 의료 현장에 보급되어 환자 개개인의 과거 의료 기록을 추가적인 의료 행위에 활용하고 있다. 그러나 일반적인 의료 문진 및 상담 간 발생하는 의료진과 환자 간의 대화는 별도로 기록되거나 저장되지 않고 있어 추가적인 환자의 주요 정보는 효율적으로 활용되지 못하고 있다. 이에 따라, 의료 문진 현장에서 발생하는 의료진과 환자와의 대화를 저장하고 이를 텍스트 데이터로 변환하여 주요한 문진 내용만 자동으로 추출, 요약하여 정보화하는 음성인식과 자연어 처리 딥러닝을 통한 의료상담 요약문을 자동으로 생성하는 전자의무기록 시스템을 제안한다. 본 시스템은 의료 종사자와 환자의 의료 상담 내용의 인식과정을 거쳐서 텍스트 정보를 획득한다. 이렇게 획득된 텍스트를 복수의 문장으로 구분하고, 생성된 문장에 포함된 복수 키워드의 중요도를 산출한다. 산출된 중요도를 기반으로 복수의 문장에 순위를 매기고, 순위를 기반으로 문장들을 요약하여 최종 전자의무기록 데이터를 생성한다. 제안하는 시스템 성능은 정량적 분석을 통하여 우수함을 확인한다.

Keywords

References

  1. Wang, Samuel J., et al., "A cost-benefit analysis of electronic medical records in primary care.", The American journal of medicine, Vol. 114. No. 5, pp. 397-403, April 2003. DOI: https://doi.org/10.1016/S0002-9343(03)00057-3
  2. Noraziani, K., et al., "An overview of electronic medical record implementation in healthcare system: Lesson to learn.", World Applied Sciences Journal, Vol. 25, No. 2, pp. 323-332, September 2013. DOI: https://doi.org/10.5829/idosi.wasj.2013.25.02.2537
  3. Li, Zhuo-Rong, et al., "A secure electronic medical record sharing mechanism in the cloud computing platform.", 2011 IEEE 15th international symposium on consumer electronics (ISCE). IEEE, pp. 98-103, August 2011. DOI: https://doi.org/10.1109/ISCE.2011.5973792
  4. SARANGI, Susanta; SAHIDULLAH, Md; SAHA, Goutam. Optimization of data-driven filterbank for automatic speaker verification. Digital Signal Processing, Vol. 104, September 2020:102795. DOI: https://doi.org/10.1016/j.dsp.2020.102795
  5. Shao, Shih-Chieh, et al., "The Chang Gung Research Database-a multi-institutional electronic medical records database for real-world epidemiological studies in Taiwan.", Pharmacoepidemiology and drug safety Vol. 28, No. 5, pp. 593-600, January 2019. DOI: https://doi.org/10.1002/pds.4713
  6. Huang, Edward W., Sheng Wang, and ChengXiang Zhai, "VisAGE: integrating external knowledge into electronic medical record visualization.", PACIFIC SYMPOSIUM ON BIOCOMPUTING 2018: Proceedings of the Pacific Symposium, pp. 278-589, January 2018. DOI: https://doi.org/10.1142/9789813235533_0053
  7. Wu, Sihua, and Jiang Du, "Electronic medical record security sharing model based on blockchain.", Proceedings of the 3rd International Conference on Cryptography, Security and Privacy, pp. 13-17, January 2019. DOI: https://doi.org/10.1145/3309074.3309079
  8. Adamu, Jibril, Raseeda Hamzah, and Marshima Mohd Rosli, "Security issues and framework of electronic medical record: A review.", Bulletin of Electrical Engineering and Informatics, Vol. 9, No. 2, pp. 565-572, April 2020. DOI:https://doi.org/10.11591/eei.v9i2.2064
  9. Shinozaki, Ayaka, "Electronic medical records and machine learning in approaches to drug development.", Artificial intelligence in Oncology drug discovery and development. IntechOpen, 2020. DOI: https://doi.org/10.5772/intechopen.92613
  10. Shickel, Benjamin, et al., "Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis.", IEEE journal of biomedical and health informatics, Vol. 22, No. 5, pp. 1589-1604, September 2018. DOI: https://doi.org/10.1109/JBHI.2017.2767063
  11. Kihun Nam, "A Study on Processing of Speech Recognition Korean Words", The Journal of the Convergence on Culture Technology, Vol. 5, No. 4, pp. 407-412, November 2019. DOI: https://doi.org/10.17703/JCCT.2019.5.4.407