DOI QR코드

DOI QR Code

Length-of-Stay Prediction Model of Appendicitis using Artificial Neural Networks and Decision Tree

신경망과 의사결정 나무를 이용한 충수돌기염 환자의 재원일수 예측모형 개발

  • Published : 2009.06.30

Abstract

For the efficient management of hospital sickbeds, it is important to predict the length of stay (LoS) of appendicitis patients. This study analyzed the patient data to find factors that show high positive correlation with LoS, build LoS prediction models using neural network and decision tree models, and compare their performance. In order to increase the prediction accuracy, we applied the ensemble techniques such as bagging and boosting. Experimental results show that decision tree model which was built with less number of variables shows prediction accuracy almost equal to that of neural network model, and that bagging is better than boosting. In conclusion, since the decision tree model which provides better explanation than neural network model can well predict the LoS of appendicitis patients and can also be used to select the input variables, it is recommended that hospitals make use of the decision tree techniques more actively.

충수돌기염 환자의 LoS(Length of Stay)를 예측하는 것은 병상의 운영에 적지 않은 영향을 준다. 본 논문에서는 Neural Networks와 Decision Tree를 이용하여 LoS와 연관이 높은 입력변수들을 찾아 그 의미를 분석하며, 찾아낸 입력변수들을 이용하여 다양한 LoS 예측 모형을 개발하고 그 성능을 비교하였다. 모형의 예측 정확성을 높이기 위하여 Bagging과 Boosting 등의 Ensemble 기법도 적용하였다. 실험 결과, Decision Tree 모형이 Neural Networks 모형보다 좀 더 적은 수의 속성을 가지고도 거의 통일한 예측력을 보였으며, Ensemble 기법 중에서는 Bagging 기법이 Boosting 기법보다 좋은 결과를 보여주었다. 의사결정나무 기법은 Neural Networks 기법에 비해 설명력이 있으며, 충수돌기염의 LoS 예측에 매우 효과적이었고, 중요 입력 변수의 선정에도 좋은 결과를 보여줌에 따라 향후 적극적인 기법의 도입이 필요하다고 할 수 있다.

Keywords

References

  1. Walczak S.,Pofahl WE, Scorpio RJ, "A decision support tool for allocating hospital bed resources and determining required acuity of care", Decis Support Syst, 34. pp. 445-56, 2003. https://doi.org/10.1016/S0167-9236(02)00071-4
  2. Doering LV, Esmalian F., Imperial-Perez F, Monsein S, "Determinants of intensive care unit length of stay after coronary artery bypass graft surgery", Heart Lung, 30, pp. 9-17, 2001. https://doi.org/10.1067/mhl.2001.112502
  3. Lee AH, Ng SK, Yau KKW, "Determinants of maternity length of stay: a gamma mixture risk-adjusted model", Health Care Manage Sci. 4, pp. 249-55, 2001. https://doi.org/10.1023/A:1011810326113
  4. Wang K, Yau KKW, "Lee AH. Factors influencing hospitalization of infants for recurrent gastroenteritis in Western Australia", Meth Inform Med, 4, pp. 251-4, 2003.
  5. Mitchell, Tom M, "Machine Learning and Data Mining", Communications of the ACM, 42, pp. 30-36, 1999.
  6. Leung KM, Robert ME, Karen SR, Malik MH, Antonio PL, "Hospital- and Patient-Related Characteristics Determining Maternity Length of Stay: A Hierarchical Linear Model Approach", American Journal of Public Health, 88, pp. 377-381, 1999. https://doi.org/10.2105/AJPH.88.3.377
  7. Zizza C, Amy HH, June S, Barry MP, "Length of Hospital Stays among Obese Individuals", American Journal of Public Health, 94, pp. 1587-1591, 2004. https://doi.org/10.2105/AJPH.94.9.1587
  8. Ottenbacher KJ, Pam MS, Sandra BI, Roger CF, Carl VG, "Length of Stay and Hospital Readmission for Persons with Disabilities", American Journal of Public Health, 90, pp.1920-1923, 2000. https://doi.org/10.2105/AJPH.90.12.1920
  9. Epstein AM, Leighton R, Martha H. The Relation of Body Weight to Length of Stay and Charges for Hospital Services for Patients Undergoing Elective Surgery: A Study of Two Procedures. American Journal of Public Health,77,pp.993-997,1987 https://doi.org/10.2105/AJPH.77.8.993
  10. Hyman I, Tonia F, Janice DM, Sarah O, Marsha MC, "The Association Between Length of Stay in Canada and Intimate Partner Violence Among Immigrant Women", American Journal of Public Health, 96, pp. 654-659, 2006. https://doi.org/10.2105/AJPH.2004.046409
  11. Daniel WW, Edward NB, J. Paul C, "The use of Demographic Characteristics in Predicting Length of Stay in a State Mental Hospital", American Journal of Public Health, 58, pp. 938-948, 1968. https://doi.org/10.2105/AJPH.58.5.938
  12. Dombi GW, Nandi P, Saxe JM, Ledgerwood AM, Lucas CE, "Prediction of rib fracture injury outcome by an artificial neural-network", J Trauma, 39, pp. 915-21, 1995 https://doi.org/10.1097/00005373-199511000-00016
  13. Pofahl WE, Walczak SM, Rhone E, Izenberg SD, "Use of an artificial neural network to predict length of stay in acute pancreatitis", Am Surgeon, 64, pp. 868-72, 1998.
  14. Lowell WE, Davis GE, "Predicting length of stay for psychiatric diagnosis-related groups using neural networks", J Am Med Inform Assoc, 1, pp. 459-66, 1994. https://doi.org/10.1136/jamia.1994.95153435
  15. Sheng WH, Wang JT, Lu DCT, Chic WC, Chen YC, Chang SC, "Comparative impact of hospital-acquired infections on medical costs, length of hospital stay and outcome between community hospitals and medical centres", Journal of Hospital Infection, 59, pp. 205-214, 2005. https://doi.org/10.1016/j.jhin.2004.06.003
  16. Demir CC, Celik Y, Gider O, Yagci G, Sahin B, Turgut T, Col AA, Gen DS, "The Factors Length of Stay of the Patients Undergoing Appendectomy Surgery in a Military Teaching Hospital", Military Medicine, 172, pp. 634-639, 2007. https://doi.org/10.7205/MILMED.172.6.634
  17. Mohammed AO, Muhammad MM, Robin SM, "Epidemiologic features of acute appendicitis in Ontario, Canada", Canadian Journal of Surgery, 46, pp 263, 2003.
  18. Towfigh S, Chen C, Mason R, Katkhouda N, Chan L, Berne T, Endosc S, "Laparoscopic appendectomy significantly reduces length of stay for perforated appendicitis", 20, pp 495-499, 2006. https://doi.org/10.1007/s00464-005-0249-8
  19. Berry MJA, Linoff G, "Data Mining Techniques, John Wiley & Sons", Inc, 1997.
  20. Kohavi, R, "A study of cross-validation and bootstrap for accuracy estimation and model selection, In S. Wermter, E. Riloff, & G. Scheler(Eds.)", The fourteenth international joint conference on artificial intelligence (IJCAI), Montreal, Quebec, Canada, San Francisco, CA: Morgan Kaufman Publishing, pp. 1137-1145, 1995.

Cited by

  1. Economic Length of Stay and Opportunity Income of Appendectomy and Pneumonia Using Activity-based Costing vol.23, pp.2, 2013, https://doi.org/10.4332/KJHPA.2013.23.2.124