Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Convergence study to predict length of stay in premature infants using machine learning

머신러닝을 이용한 미숙아의 재원일수 예측 융복합 연구

  • Kim, Cheok-Hwan (Medical Information Team, Soonchunhyang University Cheonan Hospital) ;
  • Kang, Sung-Hong (Dept. of Health Policy & Management, Inje University)
  • 김촉환 (순천향대학교 천안병원 의료정보팀) ;
  • 강성홍 (인제대학교 보건행정학과)
  • Received : 2021.05.14
  • Accepted : 2021.07.20
  • Published : 2021.07.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study was conducted to develop a model for predicting the length of stay for premature infants through machine learning. For the development of this model, 6,149 cases of premature infants discharged from the hospital from 2011 to 2016 of the discharge injury in-depth survey data collected by the Korea Centers for Disease Control and Prevention were used. The neural network model of the initial hospitalization was superior to other models with an explanatory power (R2) of 0.75. In the model added by converting the clinical diagnosis to CCS(Clinical class ification software), the explanatory power (R2) of the cubist model was 0.81, which was superior to the random forest, gradient boost, neural network, and penalty regression models. In this study, using national data, a model for predicting the length of stay for premature infants was presented through machine learning and its applicability was confirmed. However, due to the lack of clinical information and parental information, additional research is needed to improve future performance.

본 연구는 미숙아의 재원일수 예측 모형을 머신러닝 기법을 통해 개발하기 위해 수행 되었다. 모형 개발을 위해 질병관리본부에서 수집한 퇴원손상심층조사 자료의 2011년부터 2016년까지 퇴원한 미숙아 6,149건을 이용하였다. 입원 초기 신경망 모형은 설명력(R2)이 0.75로 다른 모형에 비해 우수 하였다. 입원 초기 변수에 임상진단을 CCS(Clinical class ification software)로 변환하여 추가 투입한 모형은 큐비스트(Cubist) 모형의 설명력(R2)이 0.81로 랜덤 포레스트(Random Forests), 그라디언트 부스트(Gradient boost), 신경망(neural network), 벌점화 회귀(Penalty regression) 모형에 비해 성능이 우수 하였다. 본 연구는 전국단위 데이터를 이용한 미숙아의 재원일수 예측 모형을 머신러닝을 통해 제시하고 그 활용 가능성을 확인하였다. 하지만 임상정보, 부모정보 등 데이터의 한계로 향후 성능 향상을 위한 추가 연구가 필요하다.

Keywords

References

  1. Korean Statistical Information Service(2021). Population dynamics and dynamics rate. KOSIS(Online). https://kosis.kr/statHtml/statHtml.do?orgId=101&tblId=DT_1B8000F&conn_path=I2
  2. H. S. Lee. & S. J. Kang. (2020). Factors Influencing Post-traumatic Growth in Mothers with Premature Infants Admitted to the Neonatal Intensive Care Unit. Child Health Nursing Research, 26(2), 267-276. DOI : 10.4094/chnr.2020.26.2.267
  3. Yuri Lee. (2016). A Comparative Study on the Support Policy for Prematurity in Some OECD Countries. Health and Social Welfare Review, 36(4), 63-96. DOI : 10.15709/hswr.2016.36.4.63
  4. B. H. Kang, K. A. Jung, W. H. Hahn, K. S. Shim, J. Y. Chang & C. W. Bae. (2011). Regional Analysis on the Incidence of Preterm and Low Birth Weight Infant and the Current Situation on the Neonatal Intensive Care Units in Korea, 2009. Journal of the Korean Society of Neonatology, 18(1), 70. DOI : 10.5385/jksn.2011.18.1.70
  5. L. Turgeman, J. H. May & R. Sciulli. (2017). Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission. Expert Systems with Applications, 78, 376-385. DOI : 10.1016/j.eswa.2017.02.023
  6. S. E. Seaton, L. Barker, E. S. Draper, K. R. Abrams, N. Modi & B. N. Manktelow. (2018). Estimating neonatal length of stay for babies born very preterm. Archives of Disease in Childhood - Fetal and Neonatal Edition, 104(2), F182-F186. DOI : 10.1136/archdischild-2017-314405
  7. Health insurance review and Assessment services. (2019). Results of the 1st neonatal intensive care unit adequacy evaluation. HIRA(Online). https://www.hira.or.kr/cms/open/04/04/12/2019_07.pdf
  8. H. C. Lee, M. V. Bennett, J. Schulman & J. B. Gould. (2013). Accounting for variation in length of NICU stay for extremely low birth weight infants. Journal of Perinatology, 33(11), 872-876. DOI : 10.1038/jp.2013.92
  9. C. Li et al. (2019). Prediction of Length of Stay on the Intensive Care Unit Based on Least Absolute Shrinkage and Selection Operator. IEEE Access, 7, 110710-110721. DOI : 10.1109/access.2019.2934166
  10. S. Grampurohit & S. Sunkad. (2020). Hospital Length of Stay Prediction using Regression Models. In 2020 IEEE International Conference for Innovation in Technology (INOCON). IEEE. DOI : 10.1109/inocon50539.2020.9298294
  11. H. Baek, M. Cho, S. Kim, H. Hwang, M. Song, & S. Yoo. (2018). Analysis of length of hospital stay using electronic health records: A statistical and data mining approach. PLOS ONE, 13(4), e0195901. DOI : 10.1371/journal.pone.0195901
  12. G. J. Bender, D. Koestler, H. Ombao, M. McCourt, B. Alskinis, L. P. Rubin & J. F. Padbury. (2013). Neonatal intensive care unit: predictive models for length of stay. Journal of Perinatology, 33(2), 147-153. DOI : 10.1038/jp.2012.62
  13. B. K. Choi, S. W. Ham, C. H. Kim, J. S. Seo, M. H. Park, & S. H. Kang. (2018). Development of Predictive Model for Length of Stay(LOS) in Acute Stroke Patients using Artificial Intelligence. Journal of Digital Convergence, 16(1), 231-242. DOI : 10.14400/JDC.2018.16.1.231
  14. S. Bacchi, Y. Tan, L. Oakden-Rayner, J. Jannes, T. Kleinig & S. Koblar. (2020). Machine Learning in the Prediction of Medical Inpatient Length of Stay. Internal Medicine Journal. DOI : 10.1111/imj.14962
  15. H. Singh et al. (2021). Designing a bed-side system for predicting length of stay in a neonatal intensive care unit. Scientific Reports, 11(1). DOI : 10.1038/s41598-021-82957-z
  16. B. Thompson, K. O. Elish, and R. Steele. (2018). Machine Learning-Based Prediction of Prolonged Length of Stay in Newborns. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). DOI : 10.1109/ICMLA.2018.00236
  17. D. J. Whellan et al. (2011). (2011). Predictors of Hospital Length of Stay in Heart Failure: Findings from Get With the Guidelines. Journal of Cardiac Failure, 17(8), 649-656. DOI : 10.1016/j.cardfail.2011.04.005
  18. J. H. Park & S. H. Kang. (2019). A Study on the Development of Predictive Model for Severity-Adjusted Length of Stay in Nervous System Patients Using Machine Learning. Health and Social Welfare Review, 39(1), 390-427. DOI : 10.15709/hswr.2019.39.1.390
  19. J. B. Lee & H. Woo. (2020). Determinants of Length of Stay in Ischemic Heart Disease Patients. Journal of Health Informatics and Statistics, 45(1), 52-59. DOI : 10.21032/jhis.2020.45.1.52
  20. Y. H. Choi, Y. J. Kim & S. H. Kang. (2015). The Development of Convergence Bench-making system on length of stay. Journal of digital convergence, 13(5), 89-99. DOI : 10.14400/JDC.2015.13.5.89
  21. S. O. Hong, Y. T. Kim, J. H. Park & S. H. Kang (2015). The Variation of Factors of Severity-Adjusted Length of Stay (LOS) in Injury of Neck. Health and Social Welfare Review, 35(2), 561-583. DOI : 10.15709/hswr.2015.35.2.561
  22. M. Kuhn, (2008) Building Predictive Models inRUsing thecaretPackage. Journal of Statistical Software, 28(5). DOI : 10.18637/jss.v028.i05
  23. J. Elrod et al. (2021). Using Artificial Intelligence to Obtain More Evidence? Prediction of Length of Hospitalization in Pediatric Burn Patients. Frontiers in Pediatrics, 8. DOI : 10.3389/fped.2020.613736
  24. Y. C. Woo, S. Y. Lee, W. Choi, C. W. Ahn & O. K. Baek. (2019). Trend of Utilization of Machine Learning Technology for Digital Healthcare. Data Analysis, Electronics and Telecommunications Trends, 34(1), 98-110. DOI : 10.22648/ETRI.2019.J.340109
  25. Z. Zhang, Y. Zhao, A. Canes, D. Steinberg & O. Lyashevska. (2019). Predictive analytics with gradient boosting in clinical medicine. Annals of translational medicine, 7(7), 152-152. DOI : 10.21037/atm.2019.03.29
  26. Y. Zhang & A. Haghani. (2015). A gradient boosting method to improve travel time prediction. Transportation Research Part C: Emerging Technologies, 58, 308-324. DOI : 10.1016/j.trc.2015.02.019
  27. P. F. (Jennifer) Tsai et al. (2016). Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network. Journal of Healthcare Engineering, 2016, 1-11. DOI : 10.1155/2016/7035463
  28. Q. Shao, R. C. Rowe, and P. York. (2007). Investigation of an artificial intelligence technology-Model trees. European Journal of Pharmaceutical Sciences, 31(2), 137-144. DOI : 10.1016/j.ejps.2007.03.004