A 3-Staged Approach to Identifying Patients at Risk of Deterioration in Emergency Departments

Thomas Schmidt, Uffe K. Wiil


The variety in patient demographics and admission reasons makes it challenging for Emergency Department clinicians to notice deterioration in patients. Recent research has found that up to 20% of non-critical patients deteriorate within the first 24 hours after admission. Unnoticed patient deterioration can lead to serious adverse events in a clinical setting where patient monitoring relies solely on manual observations of monitors at infrequent intervals. In this paper, we present a novel 3-Stage Patient Deterioration Warning System as a model to mitigate the risk of undetected deterioration while improving clinical alarm fatigue. This staged approach enables the monitoring of patients in levels of increasing descriptiveness based on multiple models of normality. The model is validated via related work, clinical observations, and patterns of patient data collected at a Danish Emergency Department bedside ward. The paper concludes with a presentation of plans for future implementation work.


  1. Blumenthal, D. & Tavenner, M., 2010. The “Meaningful Use” Regulation for Electronic Health Records. New England Journal of Medicine, 363(6), pp.501-504.
  2. Brabrand, M. et al., 2010. Risk scoring systems for adults admitted to the emergency department: a systematic review. Scandinavian journal of trauma, resuscitation and emergency medicine, 18, p.8.
  3. Clifton, L. et al., 2012. Gaussian process regression in vital-sign early warning systems. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp.6161-6164.
  4. Easterbrook, S. et al., 2008. Selecting empirical methods for software engineering research. In F. Shull, J. Singer, & D. I. K. Sjøberg, eds. Guide to Advanced Empirical Software Engineering. Springer London, pp. 285-311.
  5. Gao, H. et al., 2007. Systematic review and evaluation of physiological track and trigger warning systems for identifying at-risk patients on the ward. Intensive care medicine, 33(4), pp.667-79.
  6. Geier, F. et al., 2013. Severity illness scoring systems for early identification and prediction of in-hospital mortality in patients with suspected sepsis presenting to the emergency department. Wiener klinische Wochenschrift, 125(17-18), pp.508-515.
  7. Ghassempour, S., Girosi, F. & Maeder, A., 2014. Clustering multivariate time series using Hidden Markov Models. International journal of environmental research and public health, 11(3), pp.2741-63.
  8. Hackmann, G. et al., 2011. Toward a two-tier clinical warning system for hospitalized patients. In AMIA Annual Symposium Proceedings. pp. 511-9.
  9. Haynes, S.R., Winkler, T.E. & Ritter, F.E., 2013. Modeling Meaningful Use as Utility in Emergency Medical Services. 2013 IEEE International Conference on Healthcare Informatics, pp.455-460.
  10. Hayward, R.A. & Hofer, T.P., 2001. Estimating hospital deaths due to medical errors: preventability is in the eye of the reviewer. The Journal of the American Medical Association, 286(4), pp.415-420.
  11. Henriksen, D.P., Brabrand, M. & Lassen, A.T., 2014. Prognosis and risk factors for deterioration in patients admitted to a medical emergency department. PloS one, 9(4), p.e94649.
  12. Kellett, J. et al., 2013. Changes and their prognostic implications in the abbreviated VitalPACTM Early Warning Score (ViEWS) after admission to hospital of 18,827 surgical patients. Resuscitation, 84(4), pp.471- 6.
  13. Lauritzen, M., Skriver, C. & Dahlin, J., 2009. TriageManual. , (juni). Available at: http://www.hillerodhospital.dk/NR/rdonlyres/D20F6C 68-ABB6-402D-B463- C7293185C372/0/Triagemaster.pdf.
  14. Lyngsø, R.B., Pedersen, C.N. & Nielsen, H., 1999. Metrics and similarity measures for hidden Markov models. In Proc. Int. Conf. Intell. Syst. Mol. Biol. pp. 178-86.
  15. Mao, Y., Chen, Y. & Hackmann, G., 2011. Medical Data Mining for Early Deterioration Warning in General Hospital Wards. In Proceedings of the 2011 IEEE 11th International Conference on Data Mining Workshops. IEEE Computer Society, pp. 1042-1049.
  16. Mcgaughey, J. et al., 2007. Outreach and Early Warning Systems ( EWS ) for the prevention of Intensive Care admission and death of critically ill adult patients on general hospital wards ( Review ). Cochrane Database System Rev, 3.
  17. Orphanidou, C. et al., 2009. Telemetry-based vital sign monitoring for ambulatory hospital patients. In Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. pp. 4650-3.
  18. Pimentel, M.A.F. et al., 2013. Modelling physiological deterioration in post-operative patient vital-sign data. Medical & biological engineering & computing, 51(8), pp.869-77.
  19. Rabiner, L., 1989. A Tutorial on Hidden Markov Models and Selected Applications in Speed Recognition. Proceedings of the IEEE, 77(2), pp.257-286.
  20. Sijs, H. Van Der et al., 2006. Overriding of drug safety alerts in computerized physician order entry. Journal of the American Medical Informatics Association, 13(2), pp.138-147.
  21. Sittig, D.F. & Factor, M., 1990. Physiologic trend detection and artifact rejection: a parallel implementation of a multi-state Kalman filtering algorithm. Computer methods and programs in biomedicine, 31(1), pp.1-10.
  22. Subbe, C.P. & Welch, J.R., 2013. Failure to rescue: using rapid response systems to improve care of the deteriorating patient in hospital. Clinical Risk, 19(1), pp.6-11.
  23. Sweeting, M.J., Farewell, V.T. & De Angelis, D., 2010. Multi-state Markov models for disease progression in the presence of informative examination times: an application to hepatitis C. Statistics in medicine, 29(11), pp.1161-74.
  24. Tarassenko, L., Hann, a & Young, D., 2006. Integrated monitoring and analysis for early warning of patient deterioration. British journal of anaesthesia, 97(1), pp.64-8.
  25. Wei, H., He, J. & Tan, J., 2011. Layered hidden Markov models for real-time daily activity monitoring using body sensor networks. Knowledge and Information Systems, 29(2), pp.479-494.
  26. Windle, J. & Williams, J., 2009. Early warning scores: are they needed in emergency care? Emergency nurse?: the journal of the RCN Accident and Emergency Nursing Association, 17(2), pp.22-6.
  27. Zegers, M. et al., 2009. Adverse events and potentially preventable deaths in Dutch hospitals: results of a retrospective patient record review study. Quality & safety in health care, 18(4), pp.297-302.
  28. Zeng, J., Duan, J. & Wu, C., 2010. A new distance measure for hidden Markov models. Expert Systems with Applications, 37(2), pp.1550-1555.
  29. Zhang, Y., Silvers, C.T. & Randolph, A.G., 2007. Realtime evaluation of patient monitoring algorithms for critical care at the bedside. In Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE. pp. 2783-6.
  30. Zmiri, D., Shahar, Y. & Taieb-Maimon, M., 2012. Classification of patients by severity grades during triage in the emergency department using data mining methods. Journal of evaluation in clinical practice, 18(2), pp.378-88.

Paper Citation

in Harvard Style

Schmidt T. and Wiil U. (2015). A 3-Staged Approach to Identifying Patients at Risk of Deterioration in Emergency Departments . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015) ISBN 978-989-758-068-0, pages 470-477. DOI: 10.5220/0005226004700477

in Bibtex Style

author={Thomas Schmidt and Uffe K. Wiil},
title={A 3-Staged Approach to Identifying Patients at Risk of Deterioration in Emergency Departments},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015)},

in EndNote Style

JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015)
TI - A 3-Staged Approach to Identifying Patients at Risk of Deterioration in Emergency Departments
SN - 978-989-758-068-0
AU - Schmidt T.
AU - Wiil U.
PY - 2015
SP - 470
EP - 477
DO - 10.5220/0005226004700477