Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Development of Readmission Predictive Model

재입원 예측 모형 개발에 관한 연구

  • Received : 2019.01.23
  • Accepted : 2019.04.05
  • Published : 2019.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In order to prevent unnecessary re-admission, it is necessary to intensively manage the groups with high probability of re-admission. For this, it is necessary to develop a re-admission prediction model. Two - year discharge summary data of one university hospital were collected from 2016 to 2017 to develop a predictive model of re-admission. In this case, the re-admitted patients were defined as those who were discharged more than once during the study period. We conducted descriptive statistics and crosstab analysis to identify the characteristics of rehospitalized patients. The re-admission prediction model was developed using logistic regression, neural network, and decision tree. AUC (Area Under Curve) was used for model evaluation. The logistic regression model was selected as the final re-admission predictive model because the AUC was the best at 0.81. The main variables affecting the selected rehospitalization in the logistic regression model were Residental regions, Age, CCS, Charlson Index Score, Discharge Dept., Via ER, LOS, Operation, Sex, Total payment, and Insurance. The model developed in this study was limited to generalization because it was two years data of one hospital. It is necessary to develop a model that can collect and generalize long-term data from various hospitals in the future. Furthermore, it is necessary to develop a model that can predict the re-admission that was not planned.

불필요한 재입원을 예방하기 위해서는 재입원 확률이 높은 집단을 집중적으로 관리할 필요가 있다. 이를 위해서는 재입원 예측모형의 개발이 필요하다. 재원예측 모형을 개발하기 위해 1개 대학병원의 2016년에서 2017년의 2년간의 퇴원요약환자 데이터를 수집하였다. 이때 재입원 환자는 연구 기간 내에 2번 이상 퇴원한 환자라 정의 하였다. 재입원환자의 특성을 파악하기 위해 기술통계와 교착분석을 실시하였다. 재입원 예측 모형개발은 데이터마이닝 기법인 로지스틱회귀모형, 신경망, 의사결정모형을 이용하였다. 모형평가는 AUC(Area Under Curve)를 이용하였다. 로지스틱회귀모형이 AUC가 0.81로 가장 우수하게 나옴에 따라 본 연구에서는 로지스틱 회귀모형을 최종 재입원 예측 모형으로 선정을 하였다. 로지스틱회귀모형에서 선정된 재입원에 영향을 끼치는 주요한 변수는 성별, 연령, 지역, 주진단군, Charlson 동반질환지수, 퇴원과, 응급실 경유 여부, 수술여부, 재원일수, 총비용, 보험종류 등이었다. 본 연구에서 개발한 모형은 1개병원의 2년치 자료이므로 일반화하기에는 제한점이 있다. 추후에 여러 병원 장기간의 데이터를 수집하여 일반화 할 수 있는 모형을 개발하는 것이 필요하다. 더 나아가 계획에 없던 재입원 까지 예측을 할 수 있는 모형을 개발하는 것이 필요하다.

Keywords

Table 1. Classification and definition of independent variablesPEter

SHGSCZ_2019_v20n4_435_t0001.png 이미지

Table 2. Sociodemographic characteristics of subjects

SHGSCZ_2019_v20n4_435_t0002.png 이미지

Table 3. Clinical characteristics of subjects

SHGSCZ_2019_v20n4_435_t0003.png 이미지

Table 4. Hospital Utilization of subjects

SHGSCZ_2019_v20n4_435_t0004.png 이미지

Table 5. Primary Diagnosis by CCS category

SHGSCZ_2019_v20n4_435_t0005.png 이미지

Table 6. Distribution of Charlson comorbidity index

SHGSCZ_2019_v20n4_435_t0006.png 이미지

Table 7. Distribution of Comorbidity by CCS

SHGSCZ_2019_v20n4_435_t0007.png 이미지

Table 8. Difference in readmission according to sociodemographic characteristics in subjects

SHGSCZ_2019_v20n4_435_t0008.png 이미지

Table 9. Difference in readmission according to clinical characteristics in subjects

SHGSCZ_2019_v20n4_435_t0009.png 이미지

Table 10. Difference in medical use according to readmission

SHGSCZ_2019_v20n4_435_t0010.png 이미지

Table 11. Medical use according to primary diagnosis by CCS

SHGSCZ_2019_v20n4_435_t0011.png 이미지

Table 12. Readmission by CCI

SHGSCZ_2019_v20n4_435_t0012.png 이미지

Table 13. Assessment of Model

SHGSCZ_2019_v20n4_435_t0013.png 이미지

Table 14. Characteristics affecting Readmission(Logistic regression analysis)

SHGSCZ_2019_v20n4_435_t0014.png 이미지

Table 15. Odds Ratio for Readmission

SHGSCZ_2019_v20n4_435_t0015.png 이미지

Table 16. Odds Ratio for Readmission to discharge dept.

SHGSCZ_2019_v20n4_435_t0016.png 이미지

Table 17. Odds Ratio for other characteristics

SHGSCZ_2019_v20n4_435_t0017.png 이미지

References

  1. M.R. Chassin, J.M. Loeb, S.P. Schmaltz, R.M. Wachter, "Accountability measures using measurement to promote quality improvement," New England Journal of Medicine, vol. 363, no. 7, pp. 683-688, 2010. DOI: https://doi.org/10.1056/NEJMsb1002320
  2. I. Shams, S. Ajorlou, K. Yang, "A predictive analytics approach to reducing 30-day avoidable readmissions among patients with heart failure, acute myocardial infarction, pneumonia, or COPD," Health Care Manag Sci., vol. 18, no. 1, pp. 19-34, Mar. 2015. DOI: https://doi.org/10.1007/s10729-014-9278-y
  3. Health Insurance Review & Assessment Service, "Evaluation of Hospital-Wide All-Cause Quality Measures," July. 2015.
  4. S.F. Jencks, M.V. Williams, E.A. Coleman, "Rehospitalizations among patients in the Medicare fee-for-service program," New England Journal of Medicine, vol. 360, no. 14, pp. 1418-1428, 2009. DOI: https://doi.org/10.1056/NEJMsa0803563
  5. Medicare Payment Advisory Commission (MedPAC), "Promoting Greater Efficiency in Medicare," pp. 103-20, 2007.
  6. R.B. Zuckerman, S.H. Sheingold, E.J. Orav, J. Ruhter, A.M. Epstein, "Readmissions, observation, and the hospital readmissions reduction program," New England Journal of Medicine, vol. 374, no. 16, pp. 1543-1551, 2016. DOI: https://doi.org/10.1056/NEJMsa1513024
  7. Health Insurance Review & Assessment Service, "Results for Risk-Standardized Readmission Ratio in 2015(First)," Nov. 2016.
  8. Health Insurance Review & Assessment Service, "Results of Appropriateness for Risk-Standardized Readmission Ratio in 2017(Second)," Dec. 2018,
  9. Canadian Institute for Health Information, "All-Cause Readmission to Acute Care and Return to the Emergency Department," Canadian Institute for Health Information, 2012. ISBN: 978-1-77109-040-7
  10. Eun Youmg Choi, Minsu Osk, SangOil Lee, " Is the Risk-Standardized Readmission Rate Appropriate for a Generic Quality Indicator of Hospital Care?," Health Policy and Management, vol.26, N0.2, 148-152, 2016. https://doi.org/10.4332/KJHPA.2016.26.2.148
  11. Amber K. Sabbatini, M.D., M.P.H., and Brad Wright, Ph.D. Excluding Observation Stays from Readmission Rates - What Quality Measures Are Missing, N Engl J Med 2018; 378:2062-2065 DOI: https://doi.org/10.1056/NEJMp1800732
  12. Harlan M. Krumholz, M.D., Kun Wang, Ph.D., Hospital-Readmission Risk - Isolating Hospital Effects from Patient Effects, N Engl J Med 2017; 377:1055-1064 DOI: https://doi.org/10.1056/NEJMsa1702321
  13. E.Y. Choi, M.S. Ock, S.I. Lee, "Is the Risk-Standardized Readmission Rate Appropriate for a Generic Quality Indicator of Hospital Care?" Health Policy and Management, vol. 26, no.2, pp. 148-152, 2016. DOI: https://doi.org/10.4332/KJHPA.2016.26.2.148
  14. D. Kansagara, H. Englander, A. Salanitro, D. Kagen, C. Theobald, M. Freeman, S. Kripalani, "Risk prediction models for hospital readmission: a systematic review," J. Am. Med. Assoc., vol. 306, pp. 1688-1698, 2011 DOI: https://doi.org/10.1001/jama.2011.1515
  15. J. Futoma, J. Morris, J. Lucas, "A comparison of models for predicting early hospital readmissions," Journal of Biomedical Informatics, vol. 56, pp. 229-238, 2015. DOI: https://doi.org/10.1016/j.jbi.2015.05.016
  16. K. Shameer, K.W. Johnson, A. Yahi, R. Miotto, L.I. Li, D. Ricks, et al., "Predictive modeling of hospital readmission rates using electronic medical record-wide machine learning: A case-study using mount sinai heart failure cohort," Pac Symp Biocomput., vol. 22, pp. 276-287, 2017. DOI: https://doi.org/10.1142/9789813207813_0027
  17. M. Charlson, P. Pompei, K. Ales, C. MacKenzie, "A new method of classifying prognostic comorbidity in longitudinal studies: development and validation", J Chronic Dis, 40, pp. 373-383, 1987. https://doi.org/10.1016/0021-9681(87)90171-8
  18. V. Sundararajan, T. Henderson, C. Perry, A. Muggivan, H. Quan, V.A. Ghali, "New ICD-10 version of the Charlson comorbidity index predicted in-hospital mortality," J Clin Epidemiol, vol. 57, pp. 1288-94, 2004. DOI: https://doi.org/10.1016/j.jclinepi.2004.03.012
  19. C.Y. Wang, Y.S. Lin, C. Tzao, H.C. Lee, M.H. Huang, W.H. Hsu, H.S. Hsu, "Comparison of Charlson comorbidity index and Kaplan-Feinstein index in patients with stage I lung cancer after surgical resection", European Journal of ardio-Thoracic Surgery, vol. 32, no. 1 pp. 877-881, Dec. 2007. DOI: https://doi.org/10.1016/j.ejcts.2007.09.008
  20. C.N. Klabunde, J.M. Legler, J.L. Warren, L.M. Baldwin, D. Schrg, "A refined comorbidity measurement algorithm for claims-based studies of breast, prostate, colorectal, and lung cancer patients," Ann Epidemiol, vol. 17, pp. 584-90, 2007. DOI: https://doi.org/10.1016/j.annepidem.2007.03.011
  21. M. Kim, H. Kim, S.H. Hwang, "Developing a Hospital-Wide All-Cause Risk-Standardized Readmission Measure Using Administrative Claims Data in Korea: Methodological Explorations and Implications," Health Policy and Management, vol. 25, no. 3, pp. 197-206, 2015. DOI: https://doi.org/10.4332/KJHPA.2015.25.3.197
  22. Tabak YP1, Sun X, Nunez CM, Gupta V, Johannes RS., Predicting Readmission at Early Hospitalization Using Electronic Clinical Data: An Early Readmission Risk Score., 2017 Mar;55(3):267-275. DOI: https://doi.org/10.1097/MLR.0000000000000654