Advertisement

Pursuing Optimal Prediction of Discharge Time in ICUs with Machine Learning Methods

  • David Cuadrado
  • David RiañoEmail author
  • Josep Gómez
  • María Bodí
  • Gonzalo Sirgo
  • Federico Esteban
  • Rafael García
  • Alejandro Rodríguez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11526)

Abstract

In hospital intensive care units (ICU), patients are under continuous evaluation. One of the purposes of this evaluation is to determine the expected number of days to discharge. This value is important to manage ICUs. Some studies show that health care professionals are good at predicting short-term discharge times, but not as good at long-term predictions. Machine learning methods can achieve 1.79-day average prediction error. We performed a study on 3,787 patient-days in the ICU of the Hospital Joan XXIII (Spain) to obtain a data-driven model to predict the discharge time of ICU patients, in a daily basis. Our model, which is based on random forest technology, obtained an error of 1.34 days. We studied the progression of the model as more data are available and predicted that the number of instances required to reduce the error below one day is 4,745. When we trained the model with all the available data, we obtained a mean error of less than half a day with a coefficient of determination (R2) above 97% in their predictions on either ICU survivors and not survivors. Similar results were obtained differentiating by patients’ gender and age, confirming our approach as a good means to achieve optimal performance when more data will be available.

Keywords

Intelligent data analysis Intensive care units Discharge time prediction Data-driven models 

References

  1. 1.
    Nassar, A.P., Caruso, P.: ICU physicians are unable to accurately predict length of stay at admission: a prospective study. Int. J. Qual. Heal. care 28(1), 99–103 (2016)CrossRefGoogle Scholar
  2. 2.
    Vicente, F.G., et al.: Can the experienced ICU physician predict ICU length of stay and outcome better than less experienced colleagues? Int. Care Med. 30(4), 655–659 (2004)CrossRefGoogle Scholar
  3. 3.
    van Walraven, C., Forster, A.J.: The TEND (Tomorrow’s Expected Number of Discharges) model accurately predicted the number of patients who were discharged from the hospital the next day. J. Hosp. Med. 13(3), 158–163 (2018)Google Scholar
  4. 4.
    Temple, M.W., Lehnmann, C.U., Fabbri, D.: Predicting discharge dates from the NICU using progress note data. Pediatrics 136(2), e395-405 (2015)CrossRefGoogle Scholar
  5. 5.
    Awad, A., Bader-El-Den, M., McNicholas, J.: Patient length of stay and mortality prediction: a survey. Heal. Serv. Manag. Res. 30(2), 105–120 (2017)CrossRefGoogle Scholar
  6. 6.
    Gholipour, C., et al.: Using an Artificial Neural Networks (ANNs) model for prediction of Intensive Care Unit (ICU) outcome and length of stay at Hospital in Traumatic Patients. J. Clin. Diagn. Res. 9(4), OC19-23 (2015)Google Scholar
  7. 7.
    Rowan, M., Ryan, T., Hegarty, F., O’Hare, N.: The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors. Artif. Intell. Med. 40(3), 211–221 (2007)CrossRefGoogle Scholar
  8. 8.
    LaFaro, R.J., et al.: Neural network prediction of ICU length of stay following cardiac surgery based on pre-incision variables. PLoS ONE 10(12), e0145395 (2015)CrossRefGoogle Scholar
  9. 9.
    Verburg, I.W.M., et al.: Comparison of regression methods for modeling intensive care length of stay. PLoS ONE 9(10), e109684 (2014)CrossRefGoogle Scholar
  10. 10.
    Van Houdenhoven, M., et al.: Optimizing intensive care capacity using individual length-of-stay prediction models. Crit. Care 11(2), R42 (2007)CrossRefGoogle Scholar
  11. 11.
    Houthooft, R., et al.: Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores. Artif. Intell. Med. 63(3), 191–207 (2015)CrossRefGoogle Scholar
  12. 12.
    Caetano, N., Laureano, R.M.S., Cortez, P.: A data-driven approach to predict hospital length of stay - a Portuguese case study. In: Proceedings of the 16th International Conference on Enterprise Information Systems, pp. 407–414 (2014)Google Scholar
  13. 13.
    Hachesu, P.R., et al.: Use of data mining techniques to determine and predict length of stay of cardiac patients. Healthc. Inform. Res. 19(2), 121–129 (2013)CrossRefGoogle Scholar
  14. 14.
    Sirgo, G., et al.: Validation of the ICU-DaMa tool for automatically extracting variables for minimum dataset and quality indicators: the importance of data quality assessment. Int. J. Med. Inform. 112, 166–172 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • David Cuadrado
    • 1
  • David Riaño
    • 1
    Email author
  • Josep Gómez
    • 1
    • 2
  • María Bodí
    • 2
  • Gonzalo Sirgo
    • 2
  • Federico Esteban
    • 2
  • Rafael García
    • 2
  • Alejandro Rodríguez
    • 2
  1. 1.Universitat Rovira i VirgiliTarragonaSpain
  2. 2.Intensive Care UnitUniversity Hospital Joan XXIIITarragonaSpain

Personalised recommendations