DYNAMIC AUTOREGRESSIVE MODELLING OF CRITICAL CARE PATIENTS AS A BASIS FOR HEALTH MONITORING

K. Van Loon, G. Meyfroidt, T. Tambuyzer, G. Van den Berghe, D. Berckmans, J.-M. Aerts

2012

Abstract

Real-time modelling techniques could be valuable to continuously evaluate individual critically ill patients and to help the medical staff with estimation of prognosis. This preliminary study examines the possibilities to distinguish survivors from non-survivors on the basis of instabilities in the dynamics of daily measured variables. A data set, containing 140 patients, was generated in the intensive care unit (ICU) of the university hospital of Leuven. First and second order dynamic auto-regression (DAR) models were used to quantify the stability of time series of three physiological variables as a criterion to distinguish survivors from non-survivors. The best results were found for blood urea concentration with true negative fractions of 45/72 (63%) and true positive fractions of 43/68 (62%). The results indicate that the dynamics of time series of laboratory parameters from critically ill patients are indicative for their clinical condition and outcome.

References

  1. Beier, K., Eppanapally, S., Bazick, H. S., Chang, D., Mahadevappa, K., Gibbons, F. K. & Christopher, K. B. (2011). Elevation of blood urea nitrogen is predictive of long-term mortality in critically ill patients independent of “normal” creatinine. Crit Care Med, 39, 305-313.
  2. Belair, J., Glass, L., Heiden, U. A. D. & Milton, J. (1995). Dynamical Disease - Identification, Temporal Aspects and Treatment Strategies of Human Illness. Chaos, 5, 1-7.
  3. Box, G. E., Jenkins, G. M. & Reinsel, G. C. (1994). Time series analysis: forecasting and control. Prentice-Hall International, New Jersey.
  4. Buchman, T. G. (2004). Nonlinear dynamics, complex systems, and the pathobiology of critical illness. Curr Opin Crit Care, 10, 378-382.
  5. Chang, R. W. S., Jacobs, S. & Lee, B. (1988). Predicting Outcome Among Intensive-Care Unit Patients Using Computerized Trend Analysis of Daily Apache-Ii Scores Corrected for Organ System Failure. Intens Care Med, 14, 558-566.
  6. Chang, R. W. S., Jacobs, S., Lee, B. & Pace, N. (1988). Predicting Deaths Among Intensive-Care Unit Patients. Crit Care Med, 16, 34-42.
  7. Clermont, G., Kaplan, V., Moreno, R., Vincent, J. L., Linde-Zwirble, W. T., Van Hout, B. & Angus, D. C. (2004). Dynamic Microsimulation to Model Multiple Outcomes in Cohorts of Critically Ill Patients. Intens Care Med, 30, 2237-2244.
  8. Faisst, M., Wellner, U. F., Utzolino, S., Hopt, U. T. & Keck T. (2010). Elevated blood urea nitrogen is an independent risk factor of prolonged intensive care unit stay due to acute necrotizing pancreatitis. J Crit Care, 25, 105-111.
  9. Fonseca, T., Ribeiro, C. & Granja, C. (2009). Vital Signs in Intensive Care: Automatic Acquisition and Consolidation into Electronic Patient Records. J Med Syst, 33, 47-57.
  10. Glass, L. (2001). Synchronization and Rhythmic Processes in Physiology. Nature, 410, 277-284.
  11. Goldstein, B., McNames, J., McDonald, B. A., Ellenby, M., Lai, S., Sun, Z. Y., Krieger, D. & Sclabassi, R. J. (2003). Physiologic Data Acquisition System and Database for the Study of Disease Dynamics in the Intensive Care Unit. Crit Care Med, 31, 433-441.
  12. Harten, J., Hay, A., McMillan, D. C., McArdle, C. S., O'Reilly, D. S. & Kinsella, J. (2006). Postoperative Serum Urea Is Associated With 30-Day Mortality in Patients Undergoing Emergency Abdominal Surgery. Ann Clin Biochem, 43, 295-299.
  13. Imhoff, M., Bauer, M. & Gather, U. (1999). Time-Effect Relations of Medical Interventions in a Clinical Information System. Lecture Notes in Artificial Intelligence, 1701, 307-310.
  14. Jackson, C. E., Austin, D., Tsorlalis, I. K., Dalzell, J. R., Myles, R. C., Rodgers, J., Stewart, N., Spooner, R., Petrie, M. C., Cobbe, S. M. & McMurray, J. J. V. (2008). Does Blood Urea Concentration Predict Early Mortality in Patients Hospitalised With Decompensated Heart Failure Better Than Estimated Glomerular Filtration Rate? Heart, 94, A107.
  15. Lambert, C. R., Raymenants, E. & Pepine, C. J. (1995). Time-Series Analysis of Long-Term Ambulatory Myocardial-Ischemia - Effects of Beta-Adrenergic and Calcium-Channel Blockade. Am Heart J, 129, 677- 684.
  16. Lipsitz, L. A. (2002). Dynamics of Stability: the Physiologic Basis of Functional Health and Frailty. J Gerontol A-Biol, 57, B115-B125.
  17. Pedregal, D. J., Taylor, C. J. & Young, P. C. (2007). System Identification, Time Series Analysis and Forecasting: The Captain Toolbox. Handbook v2.0. Centre for Research on Environmental Systems and Statistics. Lancaster University, Lancaster.
  18. Spencer, R.G., Lessard, C.S., Davila, F. & Etter, B. (1997). Self-Organising Discovery, Recognition and Prediction of Haemodynamic Patterns in the Intensive Care Unit. Med Biol Eng Comput, 35, 117-123.
  19. Taylor, C. J., Pedregal, D. J., Young, P. C. & Tych, W. (2006). Environmental Time Series Analysis and Forecasting with the Captain Toolbox. Environ Modell Softw, 22, 797-814.
  20. Toma, T., Abu-Hanna, A. & Bosman, R. J. (2007). Discovery and Inclusion of Sofa Score Episodes in Mortality Prediction. J Biomed Inform, 40, 649-660.
  21. Toma, T., Abu-Hanna, A. & Bosman, R. J. (2008). Discovery and Integration of Univariate Patterns From Daily Individual Organ-Failure Scores for Intensive Care Mortality Prediction. Artif Intell Med, 43, 47-60.
  22. Van den Berghe, G., Wilmer, A., Hermans, G., Meersseman, W., Wouters, P. J., Milants, I., Van Wijngaerden, E., Bobbaers, H. & Bouillon, R. (2006). Intensive Insulin Therapy in the medical ICU. New Engl J Med, 354, 449-461.
  23. Van Loon, K., Guiza, F., Meyfroidt, G., Aerts, J.-M., Ramon, J., Blockeel, H., Bruynooghe, M., Van den Berghe, G. & Berckmans, D. (2010). Prediction of Clinical Conditions after Coronary Bypass Surgery using Dynamic Data Analysis. J Med Syst, 34, 229- 239.
Download


Paper Citation


in Harvard Style

Van Loon K., Meyfroidt G., Tambuyzer T., Van den Berghe G., Berckmans D. and Aerts J. (2012). DYNAMIC AUTOREGRESSIVE MODELLING OF CRITICAL CARE PATIENTS AS A BASIS FOR HEALTH MONITORING . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012) ISBN 978-989-8425-89-8, pages 85-90. DOI: 10.5220/0003784800850090


in Bibtex Style

@conference{biosignals12,
author={K. Van Loon and G. Meyfroidt and T. Tambuyzer and G. Van den Berghe and D. Berckmans and J.-M. Aerts},
title={DYNAMIC AUTOREGRESSIVE MODELLING OF CRITICAL CARE PATIENTS AS A BASIS FOR HEALTH MONITORING},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)},
year={2012},
pages={85-90},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003784800850090},
isbn={978-989-8425-89-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2012)
TI - DYNAMIC AUTOREGRESSIVE MODELLING OF CRITICAL CARE PATIENTS AS A BASIS FOR HEALTH MONITORING
SN - 978-989-8425-89-8
AU - Van Loon K.
AU - Meyfroidt G.
AU - Tambuyzer T.
AU - Van den Berghe G.
AU - Berckmans D.
AU - Aerts J.
PY - 2012
SP - 85
EP - 90
DO - 10.5220/0003784800850090