Advertisement

Modelling and Monitoring the Individual Patient in Real Time

  • Catherine G. Enright
  • Michael G. MaddenEmail author
Chapter
First Online:
  • 675 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9521)

Abstract

This paper presents a framework for representing background knowledge and new data, and reasoning efficiently with this powerful combination of both knowledge and data. Domain knowledge is needed to positively bias the operation of data mining algorithms. Knowledge in the form of mathematical models can be considered sufficient statistics of all prior experimentation in the domain, embodying generic or abstract knowledge of it. We present a framework for using this knowledge in a probabilistic framework for data mining, inference, and decision making under uncertainty. Real-time data-streams, which typically contain uncertainty, are then exploited in a principled manner to individualise patient care. By combining the knowledge available in existing data streams with the expert knowledge available and an efficient inference method, we provide a powerful foundation for reasoning with uncertain and sparse data in the medical domain.

Keywords

Bayesian Network Intensive Care Unit Patient Hide Node Dynamic Bayesian Network Conditional Probability Table 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

This material is based upon works supported by the Science Foundation Ireland under Grant No. 08/RFP/CMS1254.

References

  1. 1.
    Abkai, C., Hesser, J.: Virtual intensive care unit (ICU): real-time simulation environment applying hybrid approach using dynamic bayesian networks and ODEs. Stud. Health Technol. Inform. 142, 1–6 (2009)Google Scholar
  2. 2.
    Aleks, N., et al.: Probabilistic detection of short events, with application to critical care monitoring. In: Proceedings of NIPS 2008: 22nd Annual Conference on Neural Information Processing Systems, pp. 49–56, Vancouver, Canada (2008)Google Scholar
  3. 3.
    Alexanian, S.M., McDonnell, M.E., Akhtar, S.: Creating a perioperative glycemic control program. In: Anesthesiology Research and Practice (2011)Google Scholar
  4. 4.
    Andersen, K.E., Højbjerre, M.: A bayesian approach to bergmans minimal model. In: Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, pp. 236–243 (2003)Google Scholar
  5. 5.
    Barbini, E., et al.: A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery part I: model planning. BMC Med. Inform. Decis. Mak. 7, 35 (2007)CrossRefGoogle Scholar
  6. 6.
    Bellazzi, R.: Drug delivery optimization through bayesian networks. In: Proceedings of the Annual Symposium on Computer Application in Medical Care, pp. 572–578. American Medical Informatics Association (1992)Google Scholar
  7. 7.
    Bellazzi, R., Magni, P., De Nicolao, G.: Dynamic probabilistic networks for modelling and identifying dynamic systems: a MCMC approach. Intell. Data Anal. 1, 245–262 (1997)CrossRefGoogle Scholar
  8. 8.
    Bénéteau-Burnat, B., et al.: Evaluation of the blood gas analyzer gem PREMIER 3000. Clin. Chem. Lab. Med. 42, 96–101 (2004)CrossRefGoogle Scholar
  9. 9.
    Berg, H.V.D.: Mathematical Models of Biological Systems. Oxford University Press, Oxford (2011)zbMATHGoogle Scholar
  10. 10.
    Van den Berghe, G., et al.: Intensive insulin therapy in critically ill patients. N. Engl. J. Med. 345(19), 1359 (2001)CrossRefGoogle Scholar
  11. 11.
    Bergman, R.N., Phillips, L.S., Cobelli, C.: Physiologic evaluation of factors controlling glucose tolerance in man: measurement of insulin sensitivity and beta-cell glucose sensitivity from the response to intravenous glucose. J. Clin. Invest. 68, 1456–1467 (1981). PMC370948CrossRefGoogle Scholar
  12. 12.
    Blakemore, A., et al.: Model-based insulin sensitivity as a sepsis diagnostic in critical care. J. Diab. Sci. Technol. 2, 468–477 (2008)CrossRefGoogle Scholar
  13. 13.
    Britton, N.F.: Essential Mathematical Biology. Springer, London, New York (2003)zbMATHCrossRefGoogle Scholar
  14. 14.
    Buchanan, B.G., Shortliffe, E.H.: Rule Based Expert Systems: the Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in Artificial Intelligence). Addison-Wesley Longman Publishing Co., Reading, MA (1984)Google Scholar
  15. 15.
    Butcher, J.C.: Numerical Methods for Ordinary Differential Equations, 2nd edn. Wiley, Hoboken (2008)zbMATHCrossRefGoogle Scholar
  16. 16.
    Celi, L.A., et al.: An artificial intelligence tool to predict fluid requirement in the intensive care unit: a proof-of-concept study. Crit. Care 12(6), R151 (2008)CrossRefGoogle Scholar
  17. 17.
    Cevenini, G., et al.: A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery part II: an illustrative example. BMC Med. Inform. Decis. Mak. 7, 36 (2007)CrossRefGoogle Scholar
  18. 18.
    Charitos, T., et al.: A dynamic bayesian network for diagnosing ventilator-associated pneumonia in ICU patients. Expert Syst. Appl. 36(2), 1249–1258 (2009)CrossRefGoogle Scholar
  19. 19.
    Chase, J.G., et al.: Model-based glycaemic control in critical care a review of the state of the possible. Biomed. Signal Process. Control 1(1), 3–21 (2006)CrossRefGoogle Scholar
  20. 20.
    Chase, J.G., et al.: Tight glycemic control in critical care - the leading role of insulin sensitivity and patient variability: a review and model-based analysis. Comput. Methods Programs Biomed. 102, 156–171 (2011)CrossRefGoogle Scholar
  21. 21.
    Chase, J.G., et al.: Physiological modeling, tight glycemic control, and the ICU clinician: what are models and how can they affect practice? Ann. Intensive Care 1, 11 (2011)CrossRefGoogle Scholar
  22. 22.
    Chatterjee, S., Russell, S.: Why are DBNs sparse? In: International Conference on Artificial Intelligence and Statistics, pp. 81–88, Sardinia (2010)Google Scholar
  23. 23.
    Chen, H.Y., et al.: Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients. Ther. Drug Monit. 21(1), 50–56 (1999)CrossRefGoogle Scholar
  24. 24.
    Dean, T., Kanazawa, K.: A model for reasoning about persistence and causation. Comput. Intell. 5(2), 142–150 (1989)CrossRefGoogle Scholar
  25. 25.
    Dempster, A.P., et al.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodological) 39(1), 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  26. 26.
    D’Errico, J.: Matlab function fminsearchbnd (2006)Google Scholar
  27. 27.
    Domingos, P.: Toward knowledge-rich data mining. Data Min. Knowl. Disc. 15, 21–28 (2007)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Egi, M., et al.: Variability of blood glucose concentration and short-term mortality in critically ill patients. Anesthesiology 105, 244–252 (2006)CrossRefGoogle Scholar
  29. 29.
    Enright, C.G.. A Probabilistic Framework Based on Mathematical Models with Application to Medical Data Streams. Ph.D thesis, National University of Ireland, Galway (2012)Google Scholar
  30. 30.
    Enright, C.G., et al.: Bayesian networks for mathematical models: techniques for automatic construction and efficient inference. Int. J. Approximate Reasoning 54, 323–342 (2013)zbMATHMathSciNetCrossRefGoogle Scholar
  31. 31.
    Enright, C.G., Madden, M.G., Madden, N., Laffey, J.G.: Clinical time series data analysis using mathematical models and DBNs. In: Peleg, M., Lavrač, N., Combi, C. (eds.) AIME 2011. LNCS, vol. 6747, pp. 159–168. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  32. 32.
    Enright, C.G., et al.: Modelling glycaemia in ICU patients: a dynamic Bayesian network approach. In: Proceedings of BIOSIGNALS-2010, Part of the 3rd International Joint Conference on Biomedical Engineering Systems and Technologies, pp. 452–459, Valencia (2010)Google Scholar
  33. 33.
    Evers, S., Lucas, P.J.F.: Constructing bayesian networks for linear dynamic systems. In: The 8th Bayesian Modelling Appications Workshop, UAI 2011, pp. 26–33, Barcelona (2011)Google Scholar
  34. 34.
    Fahy, B.G., Sheehy, A.M., Coursin, D.B.: Glucose control in the intensive care unit. Crit. Care Med. 37, 1769–1776 (2009)CrossRefGoogle Scholar
  35. 35.
    Flores, J.M., et al.: Incorporating expert knowledge when learning bayesian network structure: a medical case study. Artif. Intell. Med. 53, 181–204 (2011)CrossRefGoogle Scholar
  36. 36.
    Friedman, N., Murphy, K., Russell, S.: Learning the structure of dynamic probabilistic networks. In: Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, pp. 139–147 (1998)Google Scholar
  37. 37.
    van Gerven, M.A.J., Taal, B.G., Lucas, P.J.F.: Dynamic bayesian networks as prognostic models for clinical patient management. J. Biomed. Inform. 41(4), 515–529 (2008)CrossRefGoogle Scholar
  38. 38.
    Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-gaussian bayesian state estimation. IEE Proc. F (Radar and Signal Processing) 140(2), 107–113 (1993)CrossRefGoogle Scholar
  39. 39.
    Hanson III, C.W., Marshall, B.E.: Artificial intelligence applications in the intensive care unit. Crit. Care Med. 29, 427 (2001)CrossRefGoogle Scholar
  40. 40.
    Hart, A., Wyatt, J.: Evaluating black-boxes as medical decision aids: Issues arising from a study of neural networks. Med. Inform. 15, 229–236 (1990)CrossRefGoogle Scholar
  41. 41.
    Haverbeke, N., et al.: Nonlinear model predictive control with moving horizon state and disturbance estimation application to the normalization of blood glucose in the critically ill. In: Proceedings of the 17th IFAC World Congress (2008)Google Scholar
  42. 42.
    Hejlesen, O.K., et al.: DIAS the diabetes advisory system: an outline of the system and the evaluation results obtained so far. Comput. Methods Programs Biomed. 54(1), 49–58 (1997)CrossRefGoogle Scholar
  43. 43.
    Hovorka, R., et al.: A simulation model of glucose regulation in the critically ill. Physiol. Meas. 29(8), 959–978 (2008)CrossRefGoogle Scholar
  44. 44.
    The NICE-SUGAR Study Investigators.: Intensive versus conventional glucose control in critically ill patients. N. Engl. J. Med. 360(13), 1283–1297 (2009)Google Scholar
  45. 45.
    Iserles, A.: A First Course in the Numerical Analysis of Differential Equations. Cambridge University Press, Cambridge (2008)CrossRefGoogle Scholar
  46. 46.
    Kanji, S., et al.: Reliability of point-of-care testing for glucose measurement in critically ill adults. Crit. Care Med. 33, 2778–2785 (2005)CrossRefGoogle Scholar
  47. 47.
    Kansagara, D., et al.: Intensive insulin therapy in hospitalized patients: a systematic review. Ann. Intern. Med. 154, 268–282 (2011)CrossRefGoogle Scholar
  48. 48.
    Kavanagh, B.P., McCowen, K.C.: Glycemic control in the ICU. N. Engl. J. Med. 363(26), 2540–2546 (2010)CrossRefGoogle Scholar
  49. 49.
    Kloeden, P.E.: Numerical Solution of Stochastic Differential Equations, 3rd edn. Springer, Berlin, New York (1999)Google Scholar
  50. 50.
    Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. The MIT Press, Cambridge (2009)Google Scholar
  51. 51.
    Krinsley, J.S., Grover, A.: Severe hypoglycemia in critically ill patients: risk factors and outcomes. Crit. Care Med. 35, 2262–2267 (2007)CrossRefGoogle Scholar
  52. 52.
    Lagarias, J.C., et al.: Convergence properties of the nelder-mead simplex method in low dimensions. SIAM J. Optim. 9(1), 112–147 (1998)zbMATHMathSciNetCrossRefGoogle Scholar
  53. 53.
    Li, Q., Mark, R.G., Clifford, G.D.: Artificial arterial blood pressure artifact models and an evaluation of a robust blood pressure and heart rate estimator. BioMed. Eng. Online 8(1), 13 (2009)zbMATHCrossRefGoogle Scholar
  54. 54.
    Lind, L., Lithell, H.: Impaired glucose and lipid metabolism seen in intensive care patients is related to severity of illness and survival. Int. J. Crit. Coron. Care Med. 5, 100–105 (1994)Google Scholar
  55. 55.
    Lucas, P.J.F., van der Gaag, L.C., Abu-Hanna, A.: Bayesian networks in biomedicine and health-care. Artif. Intell. Med. 30(3), 201–214 (2004)CrossRefGoogle Scholar
  56. 56.
    McCowen, K.C., Malhotra, A., Bistrian, B.R.: Stress-induced hyperglycemia. Crit. Care Clin. 17(1), 107–124 (2001)CrossRefGoogle Scholar
  57. 57.
    Murphy, K.P.: Dynamic Bayesian Networks: Representation, Inference and Learning. Ph.D thesis, Department of Computer Science, UC Berkeley (2002)Google Scholar
  58. 58.
    Nhan, A.T.: Numerical solutions of models for glucose and insulin levels in critically ill patients. MA thesis, National University of Ireland, Galway, June 2011Google Scholar
  59. 59.
    Ottesen, J.T., Olufsen, M.S., Larsen, J.K.: Applied mathematical models in human physiology. In: SIAM: Society for Industrial and Applied Mathematics, 1 edn, February 2004Google Scholar
  60. 60.
    Pitkin, A.D., Rice, M.J.: Challenges to glycemic measurement in the perioperative and critically ill patient: a review. J. Diab. Sci. Technol. 3(6), 1270–1281 (2009)CrossRefGoogle Scholar
  61. 61.
    Radstake, N., Lucas, P.J.F., Velikova, M., Samulski, M.: Critiquing knowledge representation in medical image interpretation using structure learning. In: Riaño, D., ten Teije, A., Miksch, S., Peleg, M. (eds.) KR4HC 2010. LNCS, vol. 6512, pp. 56–69. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  62. 62.
    Roberts, J.M., et al.: Bayesian networks for cardiovascular monitoring. In: Engineering in Medicine and Biology Society, EMBS 2006, 28th Annual International Conference of the IEEE, pp. 205–209 (2006)Google Scholar
  63. 63.
    Robinson, J.W., Hartemink, A.J.: Non-stationary dynamic bayesian networks. In: Advances in Neural Information Processing Systems, pp. 1369–1376 (2008)Google Scholar
  64. 64.
    Rudge, A.D., et al.: Physiological modelling of Aagitationsedation dynamics. Med. Eng. Phys. 28, 629–638 (2006)CrossRefGoogle Scholar
  65. 65.
    Russell, S., Norvig, P.: Artificial Intelligence: a Modern Approach, 2nd edn. Prentice Hall, Upper Saddle River (2002)Google Scholar
  66. 66.
    Starfinger, C., et al.: Model-based cardiac diagnosis of pulmonary embolism. Comput. Methods Programs Biomed. 87(1), 46–60 (2007)CrossRefGoogle Scholar
  67. 67.
    Sundaresan, A., et al.: A minimal model of lung mechanics and model-based markers for optimizing ventilator treatment in ARDS patients. Comput. Methods Programs Biomed. 95(2), 166–180 (2009)CrossRefGoogle Scholar
  68. 68.
    Van Herpe, T.: Blood Glucose Control in Critically Ill Patients: Design of Assessment Procedures and a Control System. Ph.D thesis, Katholieke Universiteit Leuven, Belgium (2008)Google Scholar
  69. 69.
    Van Herpe, T., et al.: A minimal model for glycemia control in critically ill patients. In: Engineering in Medicine and Biology Society, EMBS 2006. 28th Annual Conference of the IEEE, pp. 5432–5435. IEEE (2006)Google Scholar
  70. 70.
    Van Herpe, T., et al.: Prediction performance comparison between three intensive care unit glucose models. In: Proceedings of the 7th IFAC Symposium on Modelling and Control in Biomedical Systems, Aalborg, Denmark (2009)Google Scholar
  71. 71.
    Van Looy, S., et al.: A novel approach for prediction of tacrolimus blood concentration in liver transplantation patients in the intensive care unit through support vector regression. Crit. Care 11, R83 (2007)CrossRefGoogle Scholar
  72. 72.
    Voortman, M., Dash, D., Druzdzel, M.J.: Learning why things change: the difference-based causality learner. In: Proceedings of the 26th Annual Conference on Uncertainty in Artificial Intelligence (2010)Google Scholar
  73. 73.
    Zhang, Y., Szolovits, P.: Patient-specific learning in real time for adaptive monitoring in critical care. J. Biomed. Inform. 41(3), 452–460 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.National University of IrelandGalwayIreland

Personalised recommendations

Cite chapter

Buy options