Advertisement

ICU Days-to-Discharge Analysis with Machine Learning Technology

Conference paper
  • 271 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12721)

Abstract

ICU management depends on the level of occupation and the length of stay of the patients. Daily prediction of the days to discharge (DTD) of ICU patients is essential to that management. Previous studies showed a low predictive capability of internists and ML-generated models. Therefore, more elaborated combinations of ML technologies are required. Here, we present four approaches to the analysis of the DTDs of ICU patients from different perspectives: heterogeneity quantification, biomarker identification, phenotype recognition, and prediction. Several ML-based methods are proposed for each approach, which were tested with the data of 3,973 patients of a Spanish ICU. Results confirm the complexity of analyzing DTDs with intelligent data analysis methods.

Keywords

ICU Patient phenotyping Days-to-discharge prediction Feature selection 

Notes

Acknowledgements

Spanish Ministry of Science and Innovation (PID2019-105789RB-I00).

References

  1. 1.
    Marshall, J.C., Bosco, L., et al.: What is an intensive care unit? A report of the task force of the World Federation of Societies of Intensive and Critical Care Medicine. J. Critical Care 37, 270–276 (2017).  https://doi.org/10.1016/j.jcrc.2016.07.015CrossRefGoogle Scholar
  2. 2.
    Cuadrado, D., et al.: Pursuing optimal prediction of discharge time in ICUS with machine learning methods. In: Riaño, D., Wilk, S., ten Teije, A. (eds.) AIME 2019. LNCS (LNAI), vol. 11526, pp. 150–154. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-21642-9_20CrossRefGoogle Scholar
  3. 3.
    Cuadrado, D., Riaño, D. Josep Gomez, J., Rodriguez, A., Bodi, M.: Methods and measures to quantify ICU patient heterogeneity. Submitted (2021)Google Scholar
  4. 4.
    Dasta, J., Mclaughlin, T., Mody, S., Piech, C.: Daily cost of an intensive care unit day: the contribution of mechanical ventilation*. Crit. Care Med. 33, 1266–1271 (2005)CrossRefGoogle Scholar
  5. 5.
    Lopez, C., Tucker, S., Salameh, T., Tucker, C.: An unsupervised machine learning method for discovering patient clusters based on genetic signatures. J. Biomed. Inform. 85, 30–39 (2018).  https://doi.org/10.1016/j.jbi.2018.07.004CrossRefGoogle Scholar
  6. 6.
    Barak, S., Mokfi, T.: Evaluation and selection of clustering methods using a hybrid group MCDM. Expert Syst. Appl. 138, 112817 (2019)CrossRefGoogle Scholar
  7. 7.
    Jović, A., K. Brkić, K., Bogunović, N.: A review of feature selection methods with applications. In: 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, 2015, pp. 1200–1205.  https://doi.org/10.1109/MIPRO.2015.7160458
  8. 8.
    Tan, S.S., Bakker, J., et al.: Direct cost analysis of intensive care unit stay in four European countries: applying a standardized costing methodology. Value Health 15(1), 81–86 (2012).  https://doi.org/10.1016/j.jval.2011.09.007CrossRefGoogle Scholar
  9. 9.
    Nassar, A.P., Jr., Caruso, P.: ICU physicians are unable to accurately predict length of stay at admission: a prospective study. Int. J. Qual. Health Care 28(1), 99–103 (2016).  https://doi.org/10.1093/intqhc/mzv112CrossRefGoogle Scholar
  10. 10.
    Gusmão Vicente, F., Polito Lomar, F., et al.: Can the experienced ICU physician predict ICU length of stay and outcome better than less experienced colleagues? Intensive Care Med. 30(4), 655–659 (2004).  https://doi.org/10.1007/s00134-003-2139-7CrossRefGoogle Scholar
  11. 11.
    Verburg, I.W., et al.: Which models can i use to predict adult ICU length of stay? A Systematic Review. Crit. Care Med. 45(2), e222–e231 (2017).  https://doi.org/10.1097/CCM.0000000000002054CrossRefGoogle Scholar
  12. 12.
    Kramer, A.A., Zimmerman, J.E.: A predictive model for the early identification of patients at risk for a prolonged intensive care unit length of stay. BMC Med. Inform. Decis. Mak. 10, 27 (2010).  https://doi.org/10.1186/1472-6947-10-27CrossRefGoogle Scholar
  13. 13.
    Livieris, I.E., Kotsilieris, T., Dimopoulos, I., Pintelas, P.: Decision support software for forecasting patient’s length of stay. Algorithms 11, 199 (2018).  https://doi.org/10.3390/a11120199CrossRefzbMATHGoogle Scholar
  14. 14.
    Herrera, F., Carmona, C.J., González, P., et al.: An overview on subgroup discovery: foundations and applications. Knowl. Inf. Syst. 29, 495–525 (2011).  https://doi.org/10.1007/s10115-010-0356-2CrossRefGoogle Scholar
  15. 15.
    Helal, S.: Subgroup discovery algorithms: a survey and empirical evaluation. J. Comput. Sci. Technol. 31(3), 561–576 (2016).  https://doi.org/10.1007/s11390-016-1647-1CrossRefGoogle Scholar
  16. 16.
    Chandrashekar, G., Sahin, F.: A survey on feature selection methods. Comput. Electr. Eng. 40(1), 16–28 (2014)CrossRefGoogle Scholar
  17. 17.
    Selleck, MJ, Senthil, M, Wall, NR.: Making meaningful clinical use of biomarkers. Biomark Insights 12 (2017).  https://doi.org/10.1177/1177271917715236

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Universitat Rovira i VirgiliTarragonaSpain

Personalised recommendations