SOCO 2016, ICEUTE 2016, CISIS 2016: International Joint Conference SOCO’16-CISIS’16-ICEUTE’16 pp 3-12 | Cite as

Predicting 30-Day Emergency Readmission Risk

  • Arkaitz Artetxe
  • Andoni Beristain
  • Manuel Graña
  • Ariadna Besga
Conference paper
First Online:
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 527)

Abstract

Objective: Predicting Emergency Department (ED) readmissions is of great importance since it helps identifying patients requiring further post-discharge attention as well as reducing healthcare costs. It is becoming standard procedure to evaluate the risk of ED readmission within 30 days after discharge. Methods. Our dataset is stratified into four groups according to the Kaiser Permanente Risk Stratification Model. We deal with imbalanced data using different approaches for resampling. Feature selection is also addressed by a wrapper method which evaluates feature set importance by the performance of various classifiers trained on them. Results. We trained a model for each scenario and subpopulation, namely case management (CM), heart failure (HF), chronic obstructive pulmonary disease (COPD) and diabetes mellitus (DM). Using the full dataset we found that the best sensitivity is achieved by SVM using over-sampling methods (40.62 % sensitivity, 78.71 % specificity and 71.94 accuracy). Conclusions. Imbalance correction techniques allow to achieve better sensitivity performance, however the dataset has not enough positive cases, hindering the achievement of better prediction ability. The arbitrary definition of a threshold-based discretization for measurements which are inherently is an important drawback for the exploitation of the data, therefore a regression approach is considered as future work.

Keywords

Readmission risk Imbalanced datasets SVM Classification 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    World Health Organization: Global health and ageing. World Health Organization, Geneva, Switzerland (2011)Google Scholar
  2. 2.
    Besga, A., Ayerdi, B., Alcalde, G., et al.: Risk factors for emergency department short time readmission in stratified population. BioMed Res. Int. 2015, 7 pages (2015). Article ID 685067, doi: 10.1155/2015/685067
  3. 3.
    Van Walraven, C., et al.: Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. Can. Med. Assoc. J. 182(6), 551–557 (2010)CrossRefGoogle Scholar
  4. 4.
    Van Walraven, C., Wong, J., Forster, A.: LACE+ index: extension of a validated index to predict early death or urgent readmission after hospital discharge using administrative data. Open Med. 6(3), 80–89 (2012)Google Scholar
  5. 5.
    Yu, S., Farooq, F., van Esbroeck, A., Fung, G., Anand, V., Krishnapuram, B.: Predicting readmission risk with institution-specific prediction models. Artif. Intell. Med. 65(2), 89–96 (2015)CrossRefGoogle Scholar
  6. 6.
    Ho, T.K.: Random decision forests. In: 1995 Proceedings of the Third International Conference on Document Analysis and Recognition, pp. 278–282. IEEE (1995)Google Scholar
  7. 7.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)MATHGoogle Scholar
  8. 8.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  9. 9.
    Kansagara, D., Englander, H., Salanitro, A., Kagen, D., Theobald, C., Freeman, M., Kripalani, S.: Risk prediction models for hospital readmission: a systematic review. JAMA 306(15), 1688–1698 (2011)CrossRefGoogle Scholar
  10. 10.
    Health Quality Ontario - Early Identification of People At-Risk of Hospitalization. ISBN 978-1-4606-2908-6 (PDF) Queen’s Printer for Ontario (2013). Accessed 09 Mar 2016. Enlace: https://secure.cihi.ca/free_products/HARP_reportv_En.pdf
  11. 11.
    Feachem, R.G., Dixon, J., Berwick, D.M., Enthoven, A.C., Sekhri, N.K., White, K.L.: Getting more for their dollar: a comparison of the NHS with California’s Kaiser Permanente. BMJ 324(7330), 135–143 (2002)CrossRefGoogle Scholar
  12. 12.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)MATHGoogle Scholar
  13. 13.
    López, V., Fernández, A., García, S., Palade, V., Herrera, F.: An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Inf. Sci. 250, 113–141 (2013)CrossRefGoogle Scholar
  14. 14.
    Carpenter, C.R., Heard, K., Wilber, S., Ginde, A.A., Stiffler, K., Gerson, L.W., et al.: Research priorities for high-quality geriatric emergency care: medication management, screening, and prevention and functional assessment. Acad. Emerg. Med. 18(6), 644–654 (2011)CrossRefGoogle Scholar
  15. 15.
    Lopez-Aguila, S., Contel, J.C., Farre, J., Campuzano, J.L., Rajmil, L.: Predictive model for emergency hospital admission and 6-month readmission. Am. J. Manage. Care 17(9), e348–e357 (2011)Google Scholar
  16. 16.
    Han, J.H., Zimmerman, E.E., Cutler, N., Schnelle, J., Morandi, A., Dittus, R.S., et al.: Delirium in older emergency department patients: recognition, risk factors, and psychomotor subtypes. Acad. Emerg. Med. 16(3), 193–200 (2009)CrossRefGoogle Scholar
  17. 17.
    New guidelines for geriatric EDs: guidance focused on boosting environment, care processes. ED Manage 26(5), 49–53 (2014)Google Scholar
  18. 18.
    Phuong, T.M., Lin, Z., Altman, R.B.: Choosing SNPs using feature selection. In: 2005 IEEE Computational Systems Bioinformatics Conference (CSB 2005), pp. 301–309. IEEE (2005)Google Scholar
  19. 19.
    Hall, M.A.: Correlation-based feature selection for machine learning (Doctoral dissertation, The University of Waikato) (1999)Google Scholar
  20. 20.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)MATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Arkaitz Artetxe
    • 1
    • 2
  • Andoni Beristain
    • 1
    • 2
  • Manuel Graña
    • 2
  • Ariadna Besga
    • 3
  1. 1.Vicomtech-IK4 Research CentreSan SebastianSpain
  2. 2.Computation Intelligence GroupBasque University (UPV/EHU)San SebastianSpain
  3. 3.Department of Internal MedicineHospital Universitario de AlavaVitoriaSpain

Personalised recommendations