Decision Model for Unplanned ICU Transfer in a Hospital with Association Rule Learning

Authors

  • Nanda Lestari Universitas Sumatera Utara
  • Sawaluddin universitas sumatera utara
  • Parapat Gultom universitas sumatera utara

DOI:

10.33395/sinkron.v7i3.11599

Abstract

The initial decision after treatment in the hospital emergency room is very important because apart from being an indicator of the quality of care for emergency room practitioners, it is also needed to achieve health goals, namely improving the quality of critical care and preventing death. The initial decision was also for an unplanned ICU transfer. Unplanned ICU transfer is the transfer of patients who originally came from the ER (Emergency Room), then to the Inpatient Room (having been treated for 24-48 hours), then to the ICU. Many studies have been carried out to predict the initial decision of unplanned ICU transfer using univariate analysis, logistic regression analysis, and association rules. The association rule algorithm generates rules between patient diagnosis features that form a decision model for unplanned ICU transfers, so it is essential to get an association rule algorithm that is more efficient in generating rules. In this study, we compare two association rule algorithms to get a more efficient algorithm; then, the rules are used to form a decision model for unplanned ICU transfers. The study results obtained that the Apriori algorithm requires a completion time of 3 ms and the FP-Growth algorithm requires a completion time of 31 ms. Hence, the FP-Growth algorithm is 28 ms more efficient than the Apriori algorithm, while the resulting rule generation is the same number of 67 rules. Only 11 rules meet the minsupp and minconf threshold and include the set of Class Association Rules (CAR), which are used to form a decision model for unplanned ICU transfers with binary integer programming

GS Cited Analysis

Downloads

Download data is not yet available.

References

Bapoje SR, Gaudiani JL, Narayanan V, Albert RK, 2011. Unplanned transfers to a medical intensive care unit: Causes and relationship to preventabel errors in care. Journal of Hospital Medicine, 6 (2): 68-72.

C.A -Chou, Q. Cao, S.-J Weng, C.-H. Tsai, 2020. Mixed-Integer optimization approach to learning association rules for unplanned ICU transfer, Artif. Intell, Med.103 101806

Dahn CM, Manasco AT, Breaud AH, Kim S, Rumas N, Moin O, Mitchell PM, Nelson KP, Baker W, Feldman JA, 2016. A critical analysis of unplanned icu transfer within 48 hours from ed admission as a quality measure. The American Journal of Emergency Medicine, 34 (8): 1505-1510.

Han, J., Pei, J., & Yin, Yiwen. (2004). Mining Frequent patterns without candidate

Ian H. Witten, Frank Eibe, Mark A. Hall, 2011 “Data mining: Practical. Machine Learning Tools and Techniques 3rd Edition”, Elsevier.

R. Agrawal, C. Faloutsos, and A. Swami. Efficient similarity search in sequence databases. In Proc. 4th Int. Conf. Foundations of Data Organization and Algorithms, pages 69–84, Chicago, IL, Oct. 1993

Simpson HK, Clancy M, Goldfrad C, Rowan K, 2005. Admissions to intensive care units from emergency departments: a descriptive study. Emergency Medicine Journal, 22 (6): 423-428.

Tan, Pang-Ning; Michael, Steinbach; Kumar, Vipin, 2005. Chapter 6. Association Analysis: Basic Concepts and Algorithms. Addison-Wesley. ISBN 978-0-321-32136-7.

Thabtah, Fadi, 2007.A review of associative classification mining. Knowledge Engineering Review, 22 (1). pp. 37-65. ISSN 0269-8889

Williams, H.P, 2009. Logic and integer programming. International Series in Operations Research & Man

Downloads


Crossmark Updates

How to Cite

Lestari, N., Sawaluddin, & Gultom, P. (2022). Decision Model for Unplanned ICU Transfer in a Hospital with Association Rule Learning. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 7(3), 2061-2067. https://doi.org/10.33395/sinkron.v7i3.11599