Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Pressure Ulcer Nursing Records with Artificial Intelligence-based Natural Language Processing

인공지능 기반 자연어처리를 적용한 욕창간호기록 분석

  • Kim, Myoung Soo (Department of Nursing, Pukyong National University) ;
  • Ryu, Jung-Mi (Department of Nursing, Busan Institute of Science and Technology)
  • 김명수 (부경대학교 간호학부) ;
  • 류정미 (부산과학기술대학교 간호학부)
  • Received : 2021.09.16
  • Accepted : 2021.10.20
  • Published : 2021.10.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to examine the statements characteristics of the pressure ulcer nursing record by natural langage processing and assess the prediction accuracy for each pressure ulcer stage. Nursing records related to pressure ulcer were analyzed using descriptive statistics, and word cloud generators (http://wordcloud.kr) were used to examine the characteristics of words in the pressure ulcer prevention nursing records. The accuracy ratio for the pressure ulcer stage was calculated using deep learning. As a result of the study, the second stage and the deep tissue injury suspected were 23.1% and 23.0%, respectively, and the most frequent key words were erythema, blisters, bark, area, and size. The stages with high prediction accuracy were in the order of stage 0, deep tissue injury suspected, and stage 2. These results suggest that it can be developed as a clinical decision support system available to practice for nurses at the pressure ulcer prevention care.

본 연구의 목적은 자연어처리에 의해 생성된 욕창간호진술문의 특성을 파악하고, 욕창 단계판별 예측정확도를 평가하기 위함이다. 욕창관련 간호기록은 서술통계를 이용하여 분석하였고, 워드클라우드 생성기를 활용하여 욕창예방 간호기록에서 단어의 특성을 파악하였다. 딥러닝을 이용하여 욕창단계판별 정확도(accuracy ratio) 를 구하였다. 연구결과, 욕창의 단계에 대한 기록 중 2단계와 심부조직손상의심단계가 각각 23.1% 와 23.0 % 로 가장 많았고, 빈도수가 높은 핵심단어는 홍반, 수포, 가피, 부위, 크기 등으로 나타났다. 예측의 정확도가 높은 단계는 0단계, 심부조직손상의심단계, 2단계 순으로 나타났다. 따라서, 이를 활용하여 임상적 의사결정지지 시스템으로 개발된다면, 임상간호사의 욕창관리역량 향상 전략 개발에 기초가 될 수 있을 것이다.

Keywords

References

  1. D. H. Seong & B. K. Yi. (2017). Research trends in clinical natural language processing. Korea Institute Informatics Scientists Engineers, 35(5), 20-26.
  2. P. M. Nadkarni, L. Ohno-Machado & W. W. Chapman. (2011). Natural language processing: an introduction. Journal of American Medical Informatics Association, 18(5), 544-551. DOI : 10.1136/amiajnl-2011-000464
  3. W. W. Yim, M. Yetisgen, W. P. Harris & S. W. Kwan. (2016). Natural language processing in oncology: a review. Journal of the American Medical Association Oncology, 2(6), 797-804. DOI : 10.1001/jamaoncol.2016.0213
  4. S. k. Hyun, S. B. Johnson & S. Bakken. (2009). Exploring the ability of natural language processing to extract data from nursing narratives. Journal of Computer Informatics Nursing, 27(4), 215-225. DOI : 10.1097/NCN.0b013e3181a91b58
  5. T. A. Koleck, C. Dreisbach, P. E. Bourne & S. Bakken. (2019). Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review. Journal of American Medical Informatics Association, 26(4), 364-379. DOI : 10.1093/jamia/ocy173
  6. X. Zhang, M. F. Bellolio, P. Medrano-Gracia, K. Werys, S. Yang & P. Mahajan. (2019). Use of natural language processing to improve predictive models for imaging utilization in children presenting to the emergency department. BMC Medical Informatics Decision Making, 19, 287. https://doi.org/10.1186/s12911-019-1006-6
  7. A. V. Gundlapalli, G. Divita, A. Redd, M. Carter, D. Ko, M. Rubin et al. (2017). Detecting the presence of an indwelling urinary catheter and urinary symptoms in hospitalized patients using natural language processing. Journal of Biomedical Informatics, 71, S39-S45. DOI : 10.1016/j.jbi.2016.07.012
  8. M. Topaz, K. Lai, D. Dowding, V. J. Lei, A. Zisberg, Bowles et al. (2016). Automated identification of wound information in clinical notes of patients with heart diseases: developing and validating a natural language processing application. International Journal of Nursing Studies, 64, 25-31. DOI : 10.1016/j.ijnurstu.2016.09.013
  9. M. S. Kim & J. M. Ryu. (2020). Development and utilization of a clinical decision support system contents for pressure ulcer prevention care. Journal of Health Informatics and Statistics, 45(4), 365-372. DOI : 10.21032/jhis.2020.45.4.365
  10. J. Hurdle, C, Weir, B. Roth, J. Hoffman, & J. Nebeker. (2003). Critical gaps in the world's largest electronic medical record: Ad Hoc nursing narratives and invisible adverse drug events. AMIA Annu Symptom Process, 309-312.
  11. R. I. Bjarnadottir & R. J. Lucero. (2018). What can we learn about fall risk factors from EHR nursing notes? A text mining study. eGEMs The Journal for Electronic Health Data and Methods, 6(1), 21. DOI : 10.5334/egems.237
  12. C. I. Kim, E. W. H. Choi & N. Staggers. (2016). Comparing usability testing outcomes and functions of six electronic nursing record systems. International Journal of Medication Informatics, 88, 78-85. DOI : 10.1016/j.ijmedinf.2016.01.007
  13. National Pressure Ulcer Advisory Panel (NPUAP). (2016). National Pressure Ulcer Advisory Panel (NPUAP) announces a change in terminology from pressure ulcer to pressure injury and updates the stages of pressure injury [Internet]. Washington, DC: NPUAP;c2016 [cited 2016 Apr 13].
  14. M. Gray (2010). Optimal management of incontinence-associated dermatitis in the elderly. American Journal of Clinical Dermatology, 11(3), 201-210. DOI : 10.2165/11311010-000000000-00000
  15. M. S. Kim & J. M. Ryu. (2019). Canonical correlation between knowledge -barriers/facilitators for pressure ulcer prevention nursing variables and attitude-performance variables. Journal of Health Informatics and Statistics, 44(3), 227-236. DOI : 10.21032/jhis.2019.44.3.227
  16. F. Coyer, A. Gardner, A. Doubrovsky, R. Cole, F. M. Ryan, C. Allen et al. (2015). Reducing pressure injuries in critically ill patients by using a patient skin integrity care bundle (Inspire). Americal Journal of Critical Care, 24(3), 199-209. DOI : 10.4037/ajcc2015930.
  17. J. Apold, & D. Rydrych. (2012). Preventing device-related pressure ulcers: using data to guide statewide change. Journal of Nursing Care Quality. 27(1), 28-34. DOI : 10.1097/NCQ.0b013e31822b1fd9
  18. M. J. Gu, Y. A & I. S. Sim. (2019). KangRisk factors of medical device-related pressure ulcer in intensive care units. Journal of Korean Academy of Nursinf, 49(1), 36-45. DOI : 10.4040/jkan.2019.49.1.36
  19. M. Moreiras-Plaza. (2010). Abdominal wall skin pressure ulcer due to a peritoneal catheter. Journal of the International Society Peritoneal Dialysis, 30(2), 257-258. DOI : 10.3747/pdi.2009.00128.
  20. Y. J. Lee, S. M. Park, J. Y. Kim, C. G. Kim & S. K. Cha. (2013). Clinical nurses' knowledge and visual differentiation ability in pressure ulcer classification system and incontinence-associated dermatitis. Journal of Korean Academic Nursing, 43(4), 526-535. DOI : 10.4040/jkan.2013.43.4.526
  21. C. Mehta, J. V. George, Y. Mehta, N. Wangmo. (2015). Pressure ulcer and patient characteristics-a point prevalence study in a tertiary hospital of India based on the European Pressure Ulcer Advisory Panel minimum data set. Journal of Tissue Viability, 24(3), 123-130. DOI : 10.1016/j.jtv.2015.04.001
  22. M. K. Kang & M. S. Kim. (2020). Risk factors for medical device-related oral mucosa pressure ulcer development of intubated patients in adult intensive care unit. Journal of Korean Biological Nursing Science, 22(4), 271-278. DOI : 10.7586/jkbns.2020.22.4.271
  23. Y. J. Lee & S. M. Park. (2014). Effects of pressure ulcer classification system education program on knowledge and visual discrimination ability of pressure ulcer classification and incontinence-associated dermatitis for hospital nurses. Journal of Korean Biological Nursing Science, 16(4), 342-348. DOI : 10.7586/jkbns.2014.16.4.342