Skip to main content

Intelligent Monitoring System for Intensive Care Units

Journal of Medical Systems volume 36, pages 2309–2318 (2012)Cite this article

Abstract

We address in the present paper a medical monitoring system designed as a multi-agent based approach. Our system includes mainly numerous agents that act as correlated multi-agent sub-systems at the three layers of the whole monitoring infrastructure, to avoid non informative alarms and send effective alarms at time. The intelligence in the proposed monitoring system is provided by the use of time series technology. In fact, the capability of continuous learning of time series from the physiological variables allows the design of a system that monitors patients in real-time. Such system is a contrast to the classical threshold-based monitoring system actually present in the Intensive Care Units (ICUs) which causes a huge number of irrelevant alarms.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3

References

  1. Tsien C. L., Reducing false alarms in Intensive Care Units: A systematic comparison of four algorithms, Annual Fall Symposium, 1997.

  2. Siebig S., Kuhls S., Imhoff M., Gather U., Scholmerich J., Wrede CE., Intensive care unit alarms-How many do we need? Critical Care Medicine, 38 (2), pp. 451–456, 2010.

    Article  Google Scholar 

  3. Siebig S, Kuhls S, Imhoff M, Langgartner J, Reng M, Scholmerich J, Gather U, Wrede CE., Collection of annotated data in a clinical validation study for alarm algorithms in intensive care-a methodologic framework, Journal of Critical Care, 25(1), pp. 128–135, 2010.

    Article  Google Scholar 

  4. Fried, R., Gather, U. and Imhoff, M., Pattern recognition in intensive care online monitoring, In M. Schmitt et al. (Hrsg.): Computational Intelligence Techniques in Medical Diagnosis and Prognosis, Springer Verlag, pp. 129-165, 2002.

  5. Daumer M., Bauer M. and Lederer C., Average run length and mean delay for changepoint detection: robust estimates for threshold alarms, Discussion Paper 95, SFB 386, 1997.

  6. Liu X., Tucker A., Cheng G. and Loizou G., Modelling Multivariate Time Series, Intelligent Data Analysis in Medicine and Pharmacology pp. 67–78, 1999.

  7. Wei W.S., Time series analysis, Univariate and multivariate methods, Addison-Wesley, Pearson Publishing,624 pages, 2006.

  8. Dahlhauss R., Graphical interaction models for multivariate time series, Metrica 51, pp. 157–172, 2000.

    Article  Google Scholar 

  9. Gather U. and Imhoff M., Graphical models for multivariate time series from intensive care monitoring. Statistics in Medicine, 21, pp. 2685–2701, 2002.

    Article  Google Scholar 

  10. Bach F. R. and Jordan M., Learning Graphical Models for Stationary Time Series, IEEE transactions on signal processing 52 (8) pp. 2189–2199, 2004.

    MathSciNet  Article  Google Scholar 

  11. Becker C. and Fried R., Sliced Inverse Regression for high-dimensional time series, In O. Opitz, M. Schwaiger (Hrsg.): Exploratory Data Analysis in Empirical Research. Proceedings of the 25th Annual Conference of the German Classification Society, pp. 3–12, 2002.

  12. Bauer M., Gather U. and Imhoff M., Analysis of high dimensional data from intensive care medicine. In Payne, R., editor, Proceedings in computational statistics, Springer Verlag, Berlin, pp. 185–190, 1998.

    Google Scholar 

  13. Oates T., Schmill M. and Cohen P., Efficient mining of statistical dependencies. Proceedings of the 16th International joint conference on artificial intelligence, pp. 794-799, 1999.

  14. Nouira K., Ferchichi A. and Trabelsi A., Temporal multi-agent system in intensive care monitoring, in proceedings of the 24th Annual Conference and Exhibition HEALTHCARE COMPUTING (HC2007). British Computer Society (BCS), pp. 38–46, 2007.

  15. Becker C. and Gather U., The masking breakdown point of multivariate outlier identification rules, Journal of American Statistics Association, 94, pp. 947–955, 1999.

    MathSciNet  MATH  Google Scholar 

  16. Nouira K. and Trabelsi A., Time Series Analysis and Outlier Detection in Intensive Care Data, In proceedings of the 8th International Conference on Signal Processing (ICSP’06). IEEE, 2006, vol 4, pp 2499–2502, 2006.

  17. Imhoff M. , Bauer M., Gather U. and Lohlein D., Time series analysis in intensive care medicine. Applied Cardiopulmonary Pathophysiology 6, pp. 263–281, 1997.

    Google Scholar 

  18. Smith A.F.M. and West M., Monitoring renal transplants: an application of the multiprocess Kalman Filter. Biometrics 39, pp. 867–878, 1983.

    MATH  Article  Google Scholar 

  19. Justel A., Pena D., Tsay R.S., Detection of outlier patches in autoregressive time series, Statistica Sinica 11, pp. 651–673, 2001.

    MathSciNet  MATH  Google Scholar 

  20. Becker C. and Gather U., The largest non identifiable outlier: a comparison of multivariate simultaneous outlier identification rules, Computational Statistics & Data Analysis, 36, pp. 119–127, 2001.

    MathSciNet  MATH  Article  Google Scholar 

  21. Daumer M., Falk M. and Beyer U., On-line monitoring using Multiprocess Kalman Filtering, Discussion Paper 54 of SFB 386, 1996.

  22. Daumer M. and Falk M., On-line detection for state space models using multi-process Kalman Filters, in proceedings of the international linear algebra society symposium on fast algorithms for control, signals and image processing, Ed. D. O’Leary, Amsterdam, Elsvier, pp. 125–135, 1998.

  23. Tukey J.W., Exploratory data analysis, Princeton University, Adison-Wesley, 688 pages, 1977.

  24. Prado R. and West M., Exploratory modelling of multiple non-stationary time series: latent process structure and decompositions, In Modelling Longitudinal and Spatially Correlated Data (ed: T. Gregoire), Springer-Verlag, pp. 349–362, 1997.

  25. Krystal A.D., Prado R. and West M., New methods of time series analysis of non-stationary EEG data: Eigenstructure decompositions of time varying autoregression, Clinical Neurophysiology, 110, pp. 2197–2206, 1999.

    Article  Google Scholar 

  26. Prado R., Huerta G. and West M., Bayesian time-varying autoregressions: Theory, methods and applications, Special issue on Time Series and Related Topics of “Resenhas”, Journal of the Institute of Mathematics and Statistics of the University of Sao Paolo, 4, pp. 405–422, 2000.

  27. West M., Bayesian time series: Models and computations for the analysis of time series in the physical sciences, In Maximum Entropy and Bayesian Methods, 15, pp. 23–34, 1997.

    Google Scholar 

  28. Fried R., Gather U., Imhoff M., Keller M. and Lanius V., Combining Graphical models and PCA for statistical process control, Conference COMPSTAT 2002, Berlin, Germany, pp. 237–242, 2002.

  29. Gather U., Fried R., Lanius V. and Imhoff M., On-line monitoring of high dimensional physiological Time series—a case study, Estadistica, 53, pp. 259–298, 2001.

  30. Bauer M., Fried R., Gather U. and Imhoff M., Dimension Reduction for Highdimensional Online-Monitoring Data in Intensive Care, in Medical Infobahn for Europe, Proceedings of MIE2000 and GMDS 2000, eds. A. Hasman, B. Blobel, J. Dudek, R. Engelbrecht, G. Gell, H.-U. Prokosch, Amsterdam, IOS Press, pp. 767–771, 2000.

  31. Carroll R.J. and Li K.C., Binary regressors in dimension reduction models: a new look at treatment comparisons, Statistica, Sinica 5, pp. 667–688, 1995.

    MathSciNet  MATH  Google Scholar 

  32. Dragoslav D. S. , Decentralized control of complex systems, Academic Press Inc., New York, 1991.

    Google Scholar 

  33. Sokolova M. and Fernandez-Caballero A., Modeling and implementing an agent-based environmental health impact decision support system, Expert Systems with Applications, 36, pp. 2603–2614, 2009.

    Article  Google Scholar 

  34. Nouira K. and Trabelsi A., Online Multiagent Monitoring in Intensive Care Units, to appear in proceedings of International Colloquium on Computing, Communication, Control, and Management(CCCM 2010), IEEE, Yangzhou China, pp. 561–564, 2010.

  35. Moret-Bonillo V., Mosqueira-Rey E. and Alonso-Betanzos A., “Information Analysis and Validation of Intelligent Monitoring Systems in Intensive Care Units” IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, vol 1 No 2, pp. 87–99, JUNE 1997.

  36. Chebrolu S., Abraham A. and Thomas J.P., Feature deduction and ensemble design of intrusion detection systems, Computer & Security, 24, pp. 295–307, 2005.

    Article  Google Scholar 

  37. Gather U., Fried R. and Imhoff M., On-line classification of states in intensive care, In W. Gaul, O. Opitz, M. Schader (Hrsg.): Data Analysis. Scientific Modeling and Practical Application. Springer, Berlin, pp. 413–428, 2000.

    Google Scholar 

Download references

Author information

Affiliations

  1. Business and Economic Statistics Modeling Laboratory, Institut Supérieur de Gestion de Tunis, University of Tunis, Tunis, Tunisia

    Kaouther Nouira & Abdelwahed Trabelsi

Authors
  1. Kaouther Nouira
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Abdelwahed Trabelsi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kaouther Nouira.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Nouira, K., Trabelsi, A. Intelligent Monitoring System for Intensive Care Units. J Med Syst 36, 2309–2318 (2012). https://doi.org/10.1007/s10916-011-9698-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10916-011-9698-x

Keywords

  • Online monitoring system
  • ICUs
  • Multi-agent system
  • Time series