Advertisement

The Use of Multivariate Autoregressive Modelling for Analyzing Dynamical Physiological Responses of Individual Critically Ill Patients

  • Kristien Van Loon
  • Jean-Marie Aerts
  • Geert Meyfroidt
  • Greta Van den Berghe
  • Daniel Berckmans
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4345)

Abstract

We attempted to find a way to distinguish survivors and non-survivors on the basis of the differences in the dynamics in both patient classes using multivariate autoregressive (MAR) time series analysis techniques. Time series data of 11 physiological variables were used to calculate MAR models. Data were taken from a subset of patients, with an intensive care unit length of stay of at least 20 days, from a database of a previously published randomized controlled trial [1]. The methodology was developed on 20 and validated on 16 patients. Based on the MAR coefficients, impulse response curves were simulated to describe the contributions of a single variable to fluctuations in another. The impulse responses of non-survivors had a tendency to be either more instable or to return to the initial level after a longer time than the responses of survivors did. This allowed us to distinguish survivors from non-survivors in the development cohort with a sensitivity of 0.70 and a selectivity of 1.00. This result was confirmed in the validation set where a sensitivity of 0.63 and a selectivity of 1.00 were reached.

Keywords

critical care mortality multivariate time series analysis outcome prediction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Van Den Berghe, G., Wouters, P., Weekers, F., Verwaest, C., Bruyninckx, F., Schetz, M., Vlasselaers, D., Ferdinande, P., Lauwers, P., Bouillon, R.: Intensive Insulin Therapy in Critically Ill Patients. New Engl. J. Med. 345, 1359–1367 (2001)CrossRefGoogle Scholar
  2. 2.
    Knaus, W.A., Draper, E.A., Wagner, D.P., Zimmerman, J.E.: Apache II: a severity of disease classification system. Crit. Care Med. 13, 818–829 (1985)CrossRefGoogle Scholar
  3. 3.
    Knaus, W.A., Wagner, D.P., Draper, E.A., Zimmerman, J.E., Bergner, M., Bastos, P.G., Sirio, C.A., Murphy, D.J., Lotring, T., Damiano, A., Harrell, F.E.: The APACHE III Prog-nostic system. Chest, 1619–1636 (1991)Google Scholar
  4. 4.
    Wyatt, J.: Nervous About Artificial Neural Networks. Lancet 346, 1175–1177 (1995)CrossRefGoogle Scholar
  5. 5.
    Dybowski, R., Weller, P., Chang, R., Gant, V.: Prediction of Outcome in Critically Ill Patients Using Artificial Neural Network Synthesised by Genetic Algorithm. Lancet 347, 1146–1150 (1996)CrossRefGoogle Scholar
  6. 6.
    Frize, M., Ennett, C.M., Stevenson, M., Trigg, H.C.E.: Clinical Decision Support Systems for Intensive Care Units: Using Artificial Neural Networks. Med. Eng. Phys. 23, 217–225 (2001)CrossRefGoogle Scholar
  7. 7.
    Ennett, C.M., Frize, M., Charette, E.: Improvement and Automation of Artificial Neural Networks to Estimate Medical Outcomes. Med. Eng. Phys. 26, 321–328 (2004)CrossRefGoogle Scholar
  8. 8.
    Sierra, B., Serrano, N., Larranaga, P., Plasencia, E.J., Inza, I., Jimenez, J.J., Revuelta, P., Mora, M.L.: Using Bayesian Networks in the Construction of a Bi-Level Multi-Classifier. A Case Study Using Intensive Care Unit Patients Data. Artif. Intell. Med. 22, 233–248 (2001)Google Scholar
  9. 9.
    Frize, M., Walker, R.: Clinical Decision-Support Systems for Intensive Care Units Using Case-Based Reasoning. Med. Eng. Phys. 22, 671–677 (2000)CrossRefGoogle Scholar
  10. 10.
    Hanson, C.W., Marshall, B.E.: Artificial Intelligence Applications in the Intensive Care Unit. Crit. Care Med. 29, 427–435 (2001)CrossRefGoogle Scholar
  11. 11.
    Lambert, C.R., Raymenants, E., Pepine, C.J.: Time-Series Analysis of Long-Term Ambu-latory Myocardial-Ischemia - Effects of Beta-Adrenergic and Calcium-Channel Blockade. Am. Heart J. 129, 677–684 (1995)CrossRefGoogle Scholar
  12. 12.
    Imhoff, M., Bauer, M., Gather, U., Lohlein, D.: Statistical Pattern Detection in Univariate Time Series of Intensive Care on-Line Monitoring Data. Intens. Care Med. 24, 1305–1314 (1998)CrossRefGoogle Scholar
  13. 13.
    Akaike, H.: On the use of a linear model for the identification of feedback systems. Ann. I. Stat. Math. 20, 425–439 (1968)zbMATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Jones, R.W. (ed.): Principles of biological regulation: an introduction to feedback systems. Academic Press Inc, New York (1973)Google Scholar
  15. 15.
    Box, G.E., Jenkins, G.M., Reinsel, G.C. (eds.): Time series analysis: forecasting and control. Prentice-Hall International, New Jersey (1994)zbMATHGoogle Scholar
  16. 16.
    Wada, T., Akaike, H., Yamada, Y., Udagawa, E.: Application of Multivariate Autoregressive Modeling for Analysis of Immunological Networks in Man. Comput. Math. Appl. 15, 713–722 (1988)zbMATHCrossRefGoogle Scholar
  17. 17.
    Wada, T., Yamada, H., Inoue, H., Iso, T., Udagawa, E., Kuroda, S.: Clinical Usefulness of Multivariate Autoregressive (Ar) Modeling as a Tool for Analyzing Lymphocyte-T Subset Fluctuations. Math. Comput. Model 14, 610–613 (1990)zbMATHCrossRefGoogle Scholar
  18. 18.
    Wada, T., Sato, S., Matsuo, N.: Application of Multivariate Autoregressive Modeling for Analyzing Chloride Potassium Bicarbonate Relationship in the Body. Med. Biol. Eng. Comput. 31, S99–S107 (1993)CrossRefGoogle Scholar
  19. 19.
    Miwakeichi, F., Galka, A., Uchida, S., Arakaki, H., Hirai, N., Nishida, M., Maehara, T., Kawai, K., Sunaga, S., Shimizu, H.: Impulse Response Function Based on Multivariate Ar Model Can Differentiate Focal Hemisphere in Temporal Lobe Epilepsy. Epilepsy Res. 61, 73–78 (2004)CrossRefGoogle Scholar
  20. 20.
    Tschacher, W., Scheier, C., Hashimoto, Y.: Dynamical Analysis of Schizophrenia Courses. Biol. Psychiat. 41, 428–437 (1997)CrossRefGoogle Scholar
  21. 21.
    Clermont, G., Neugebauer, E.A.M.: Systems Biology and Translational Research. J. Crit. Care 20, 381–382 (2005)CrossRefGoogle Scholar
  22. 22.
    Kitano, H.: Computational Systems Biology. Nature 420, 206–210 (2002)CrossRefGoogle Scholar
  23. 23.
    Seely, A.J.E., Macklem, P.T.: Complex Systems and the Technology of Variability Analysis. Crit. Care 8, R367–R384 (2004)CrossRefGoogle Scholar
  24. 24.
    Buchman, T.G.: Nonlinear dynamics, complex systems, and the pathobiology of critical illness. Curr. Opin. Crit. Care 10, 378–382 (2004)CrossRefGoogle Scholar
  25. 25.
    Glass, L.: Synchronization and Rhythmic Processes in Physiology. Nature 410, 277–284 (2001)CrossRefGoogle Scholar
  26. 26.
    Lipsitz, L.A.: Dynamics of Stability: the Physiologic Basis of Functional Health and Frailty. J Gerontol. A-Biol. 57, 115–125 (2002)Google Scholar
  27. 27.
    Poon, C.S., Merrill, C.K.: Decrease of Cardiac Chaos in Congestive Heart Failure. Nature 389, 492–495 (1997)CrossRefGoogle Scholar
  28. 28.
    Ivanov, P.C., Amaral, L.A.N., Goldberger, A.L., Havlin, S., Rosenblum, M.G., Struzik, Z.R., Stanley, H.E.: Multifractality in Human Heartbeat Dynamics. Nature 399, 461–465 (1999)CrossRefGoogle Scholar
  29. 29.
    Bruhn, J., Ropcke, H., Hoeft, A.: Approximate Entropy as an Electroencephalographic Measure of Anesthetic Drug Effect During Desflurane Anesthesia. Anesthesiology 92, 715–726 (2000)CrossRefGoogle Scholar
  30. 30.
    Pincus, S.M.: Approximate Entropy as a Measure of System-Complexity. P. Natl. Acad. Sci. USA 88, 2297–2301 (1991)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kristien Van Loon
    • 1
  • Jean-Marie Aerts
    • 1
  • Geert Meyfroidt
    • 2
  • Greta Van den Berghe
    • 2
  • Daniel Berckmans
    • 1
  1. 1.Division Measure, Model & Manage BioresponsesKatholieke Universiteit LeuvenLeuvenBelgium
  2. 2.Department of Intensive Care MedicineUniversity Hospital GasthuisbergLeuvenBelgium

Personalised recommendations