Abstract
In the intensive care unit (ICU), a common task for clinicians is to choose patients who are ready-for-transfer to a lower ward in order to make limited capacity available for new arrivals. To support this process, we build three predictive models based on historical data from more than 25,000 ICU cases to evaluate patients according to their actual medical state. The decision is modeled as a classification problem to predict the chance of adverse patient outcome defined by ICU-readmission within 72 h or readmission with subsequent exitus. In addition to a screening method based on critical criteria, we propose logistic regression models relying on critical parameter counts and metrical features from measurements, scores, and patient characteristics, respectively. Performance testing using ICU data demonstrates the ability of our approach to assist the process of patient selection for transfer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
This refers to the scenario with exitus cases included as NRFT.
- 2.
Time windows for aggregation were defined by offset-days, i.e. multiples of 24-h prior to the date of discharge.
References
Bai, J., et al.: Operations research in ICU management: a literature review. Health care Manage. Sci. 21(1), 1–24 (2018)
Kim, S.H., et al.: ICU admission control: an empirical study of capacity allocation and its implication for patient outcomes. Manage. Sci. 61(1), 19–38 (2015)
Roumani, Y.F., et al.: Classifying highly imbalanced ICU data. Health Care Manage. Sci. 16(2), 119–128 (2013)
Skowronski, G.A.: Bed rationing and allocation in the intensive care unit. Current Opin. Crit. Care 7(6), 480–484 (2001)
McWilliams, C.J., et al.: Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol. BMJ Open. 9, e025925 (2019)
Badawi, O., Breslow, M.J.: Readmissions and death after ICU discharge: development and validation of two predictive models. PLoS One 7, e48758 (2012)
Desautels, T., et al.: Prediction of early unplanned ICU readmission in a UK tertiary care hospital: a crosssectional machine learning approach. BMJ Open 7, e017199 (2017)
Kramer, A.: A novel method using vital signs information for assistance in making a discharge decision from the ICU. Med. Res. Arch. 5(12) (2017)
Rosa, R.G., et al.: Comparison of unplanned intensive care unit readmission scores: a prospective study. PLoS ONE 10(11), e0143127 (2015)
Acknowledgement
This study was funded by Else-Kröner-Fresenius Zentrum (EKFZ) for Digital Health. The authors are grateful for the valuable comments by the reviewer.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ehm, F., Franz, V., Regner, M., Buscher, U., Held, HC., Spieth, P. (2022). Classifying Ready-for-Transfer Patients in the Intensive Care Unit Based on Clinical Data. In: Trautmann, N., Gnägi, M. (eds) Operations Research Proceedings 2021. OR 2021. Lecture Notes in Operations Research. Springer, Cham. https://doi.org/10.1007/978-3-031-08623-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-08623-6_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08622-9
Online ISBN: 978-3-031-08623-6
eBook Packages: Business and ManagementBusiness and Management (R0)