DOI QR코드

DOI QR Code

인공지능을 이용한 급성 뇌졸중 환자의 재원일수 예측모형 개발

Development of Predictive Model for Length of Stay(LOS) in Acute Stroke Patients using Artificial Intelligence

  • 최병관 (부산대학교 의과대학 신경외과) ;
  • 함승우 (한국원자력의학원) ;
  • 김촉환 (순천향대학교 천안병원) ;
  • 서정숙 (연세의료원 세브란스병원) ;
  • 박명화 (대한의무기록협회) ;
  • 강성홍 (인제대학교 보건행정학과)
  • 투고 : 2017.11.22
  • 심사 : 2018.01.20
  • 발행 : 2018.01.28

초록

병원 재원일수의 효율적 관리는 병원의 수익과 환자의 진료비 절감을 위해 매우 중요한 요소이다. 이러한 재원일수의 효율적 관리를 위해서는 병원들이 재원일수에 대해서 벤치마킹을 할 수 있도록 지원이 필요하고 재원일수 절감의 구체적인 방향을 제시해 줄 수 있는 재원일수 예측모형의 개발이 필요하다. 본 연구에서는 2013년과 2014년도 퇴원손상환자자료 중 급성뇌졸중 환자를 추출하여 분석용 자료를 만들고 인공지능을 이용하여 급성뇌졸중 환자의 재원일수 예측모형을 개발하였다. 분석용 자료는 훈련용 60%, 평가용 40%로 분류하였다. 모형개발은 전통적 통계기법인 다중회귀분석기법과 인공지능기법인 대화식 의사결정나무기법, 신경망 기법, 그리고 이들을 모두 통합한 앙상블기법을 이용하였다. 모형평가는 Root ASE(Absolute error) 지표를 이용하였는데, 다중회귀분석은 23.7, 대화식결정나무 23.7, 신경망 분석은 22.7, 앙상블은 22.7로 나타났고 이를 통하여 재원일수 예측모형 개발에 인공지능기법의 유용성이 입증되었다. 앞으로 재원일수 예측모형개발에 인공지능 기법을 보다 효율적으로 활용할 수 있는 방안에 대해서 계속적인 연구가 이루어 질 필요가 있다.

The efficient management of the Length of Stay(LOS) is important in hospital. It is import to reduce medical cost for patients and increase profitability for hospitals. In order to efficiently manage LOS, it is necessary to develop an artificial intelligence-based prediction model that supports hospitals in benchmarking and reduction ways of LOS. In order to develop a predictive model of LOS for acute stroke patients, acute stroke patients were extracted from 2013 and 2014 discharge injury patient data. The data for analysis was classified as 60% for training and 40% for evaluation. In the model development, we used traditional regression technique such as multiple regression analysis method, artificial intelligence technique such as interactive decision tree, neural network technique, and ensemble technique which integrate all. Model evaluation used Root ASE (Absolute error) index. They were 23.7 by multiple regression, 23.7 by interactive decision tree, 22.7 by neural network and 22.7 by esemble technique. As a result of model evaluation, neural network technique which is artificial intelligence technique was found to be superior. Through this, the utility of artificial intelligence has been proved in the development of the prediction LOS model. In the future, it is necessary to continue research on how to utilize artificial intelligence techniques more effectively in the development of LOS prediction model.

키워드

참고문헌

  1. Accenture, "ARTIFICIAL INTELLIGENCE : Healthcare's New Nervous System", Accenture, pp.1-3, 2017.
  2. G. H. Robinson, L. E. Davis, R. P. Leifer, "Prediction of Hospital Length of Stay", Health Services RESEARCH, pp. 287-300, 1966.
  3. C. L Lin, P. H. Lin, L. W. Chou, S. J. Lan, N. H. Meng, S. F. Lo, H. D. Isaac, "Model-based Prediction of Length of Stay for Rehabilitating Stroke Patients", J Formos Med Assoc, Vol. 108, No. 8, pp. 653-662, 2009. https://doi.org/10.1016/S0929-6646(09)60386-7
  4. L. Lella, A. D. Giorgio, A. F. Dragoni, "Length of Stay Prediction and Analysis through a Growing Neural Gas Model", 4th International Workshop on Artificial Intelligence and Assistive Medicine, pp.11-20, 2015.
  5. S. Barnes, E. Hamrock, M. Toerper, S. Siddiqui, S. Levin, "Real-time prediction of inpatient length of stay for discharge prioritization", J Am Med Inform Assoc, Vol.32, pp. e2-e10, 2016.
  6. S. O. Hong, Y. T. Kim, J. H. Park, S. H. Kang, " The Variation of Factors of Severity-Adjusted Length of Stay(LOS) in Injury of Neck, Health and Social Welfare Review, Vol. 35, No. 2, pp.561-563, 2015. https://doi.org/10.15709/hswr.2015.35.2.561
  7. S. H. Chung, W. S. Han, Y. M. Suh, H. S. Rhee, "Length-of-Stay Prediction Model of Appendicitis using Artificial Neural Networks and Decision Tree", Vol. 10, No. 6, pp. 1424-1432, 2009. https://doi.org/10.5762/KAIS.2009.10.6.1424
  8. S. H. Kang, H. S. Seok, W. J. Kim, The Variation of Factors of severity-adjusted length of stay(LOS) in acute stroke patients, The Society of Digital Policy & Management, Vol.11, No.6, pp. 221-233, 2013.
  9. Y. G. Kim, " Risk-Adjusted Mortality Rate of Inpatients with Acute Strokes and the Length of their stay-Focused on Medical Institutions with 500 Beds or More-", KOREA UNIVERSITY, pp.46-64, 2013.
  10. K. H. Kim, "Comparative Study on Three Algorithms of the ICD-10 Charlson Comorbidity Index with Myocardial Infarction Patients" , Journal of Preventive Medicine and Public Health, Vol. 43, No. 1, pp.42-49, 2010. https://doi.org/10.3961/jpmph.2010.43.1.42
  11. J. H. Oh, S. W. Chung. "Multivariate Analysis for Clinicians", Clinics in Shoulder and Elbow, Vol.6, No. 1, pp.63-72, 2013.
  12. K. Y. Hwang, E. S. Lee, G. W. Kim, S. O. Hong, J. S. Park, M. S. Kwak, Y. J. Lee, C. H. Lim, T. H. Park, J. H. Park, S. H. Kang, "Development of Healthcare Data Quality Control Algorithm using Interactive Decision Tree : Focusing on Hypertension in Diabetes Mellitus Patients", The Korean Journal of Health Service Management, Vol. 10, No.3, pp.63-74, 2016. https://doi.org/10.12811/kshsm.2016.10.3.063
  13. S. Walczak, R. J. Scorpio, W. E. Pofahl, "Predicting Hospital Length of Stay with Neural Networks", Proceedings of the Eleventh International FLAIRS Conference, pp. 333-337, 1998.
  14. M. R. Poynton, B. M. Choi, Y. M. Kim, I. S. Park, G. J. Noh, S. O. Hong, Y. K. Boo, S. H. Kang, "Machine Learning Methods Applied to Pharmacokinetic Modelling of Remifentanil in Healthy Volunteers: a ulti-method Comparison", The Journal of International Medical Research, Vol. 37, pp. 1680-1691, 2009. https://doi.org/10.1177/147323000903700603
  15. IBM, "Descriptive, predictive, prescriptive: Transforming asset and facilities management with analytics", IBM, pp. 3-4, 2013.
  16. M. Sappelli, M. H.T. de Boer, "A Vision on Prescriptive Analytics", The Third International Conference on Big Data, Small Data, Linked Data and Open Data, pp. 45-50, 2017.