Best Practice & Research Clinical Anaesthesiology
Volume 23, Issue 1 , Pages 127-143 , March 2009

Machine learning techniques to examine large patient databases

  • Geert Meyfroidt (Deputy Head of Clinics)

      Affiliations

    • Department of Intensive Care Medicine, UZ Leuven - Campus Gasthuisberg, Catholic University of Leuven, Herestraat 49, 3000 Leuven, Belgium
    • Corresponding Author InformationCorresponding author. Tel.: +32 16 34 40 21; Fax: +32 16 34 40 15.
    • ,
  • Fabian Güiza (PhD student)

      Affiliations

    • Department of Computer Sciences, Faculty of Engineering, Catholic University of Leuven, Leuven, Belgium
    • ,
  • Jan Ramon (Postdoctoral Researcher)

      Affiliations

    • Department of Computer Sciences, Faculty of Engineering, Catholic University of Leuven, Leuven, Belgium
    • ,
  • Maurice Bruynooghe (Professor, Head of Research Group Declarative Languages and Artificial Intelligence)

      Affiliations

    • Department of Computer Sciences, Faculty of Engineering, Catholic University of Leuven, Leuven, Belgium

References 

  1. Elliot TS. The rock. Faber & Faber; 1934;
  2. East TE. Computers in the ICU: panacea or plague?. Respiratory Care. 1992;37:170–180
  3. Manjoney R. Clinical information systems market – an insider's view. Journal of Critical Care. 2004;19:215–220
  4. Roncati Zanier E, Ortolano F, Ghisoni L, et al. Intracranial pressure monitoring in intensive care: clinical advantages of a computerized system over manual recording. Critical Care (London, England). 2007;11:R7
  5. Bosman RJ, Oudemans-van Straaten HM, Zandstra DF. The use of intensive care information systems alters outcome prediction. Intensive Care Medicine. 1998;24(9):953–958
  6. Bosman RJ, Rood E, Oudemans-van Straaten HM. Intensive care information system reduces documentation time of the nurses after cardiothoracic surgery. Intensive Care Medicine. 2003;29:83–90
  7. Fraenkel DJ, Cowie M, Daley P. Quality benefits of an intensive care clinical information system. Critical Care Medicine. 2003;31:120–125
  8. Colpaert K, Claus B, Somers A, et al. Impact of computerized physician order entry on medication prescription errors in the intensive care unit: a controlled cross-sectional trial. Critical Care (London, England). 2006;10:R21
  9. Shulman R, Singer M, Goldstone J, et al. Medication errors: a prospective cohort study of hand-written and computerised physician order entry in the intensive care unit. Critical Care (London, England). 2005;9:R516–R521
  10. Available from: http://www.leapfroggroup.org/media/file/Leapfrog-Computer_Physician_Order_Entry_Fact_Sheet.pdf[accessed 15.12.07]
  11. Morris AH. Decision support and safety of clinical environments. Quality & Safety in Health Care. 2002;11:69–75
  12. Berger MM, Revelly J-P, Wasserfallen J-B, et al. Impact of a computerized information system on quality of nutritional support in the ICU. Nutrition. 2006;22:221–229
  13. Ward NS. Using computers for intensive care unit research. Respiratory Care. 2004;49(5):518–524
  14. Ramon J, Fierens D, Güiza F, et al. Mining data from intensive care patients. Advanced Engineering Informatics. 2007;21:243–256
  15. In:  Mitchell T editors. Machine learning. McGraw Hill Publishing Company; 1997;
  16. Lucas P. Bayesian analysis, pattern analysis, and data mining in health care. Current Opinion in Critical Care. 2004;10:399–403
  17. Rubenfeld GD, Angus DC, Pinsky MR, et al. Outcomes research in critical care. American Journal of Respiratory and Critical Care Medicine. 1999;160:358–367
  18. Ward NS. The accuracy of clinical information systems. Journal of Critical Care. 2004;19(4):221–225
  19. Office of the Secretary, Health, and Human Services . HIPAA administrative simplification: standards for electronic health care claims attachments: proposed rule. Federal Register. 2005;70:55989–56025
  20. Hogan WR, Wagner MM. Accuracy of data in computer-based patient records. Journal of the American Medical Informatics Association : JAMIA. 1997;5:342–355
  21. Lawless ST. Crying wolf: false alarms in a pediatric intensive care unit. Critical Care Medicine. 1994;22:981–985
  22. Verduijn M, Peek N, de Keizer NF, et al. Individual and joint expert judgments as reference standards in artifact detection. Journal of the American Medical Informatics Association : JAMIA. 2008;15(2):227–234
  23. Cleveland H. Information as resource. The Futurist. 1982;34–39
  24. Ackoff RL. From data to wisdom. Journal of Applied Systems Analysis. 1989;16:3–9
  25. Hey J. The data, information, knowledge, wisdom chain: the metaphorical link. Available from: http://best.me.berkeley.edu/%7Ejhey03/files/reports/IS290_Finalpaper_HEY.pdf2004;[accessed August 2008]
  26. Fayyad U, Piatetsky-Shapiro G, Smyth P. From data mining to knowledge discovery: an overview. In:  Fayyad U,  Piatetsky-Shapiro G,  Smyth P, Uthurusamy  editor. Advances in knowledge discovery and data mining. The MIT Press; 1996;p. 495–515
  27. Chapman P, Clinton J, Kerber R, et al. CRISP-DM 1.0: step-by-step data mining guide. Technical report. CRISP-DM Consortium; 2000;
  28. Langley P. Elements of machine learning. San Francisco: Morgan Kaufmann; 1996;
  29. DeGroot MH. Probability and statistics. 2nd edn.. Reading, Massachusetts: Addison-Wesley; 1986;
  30. Casella G, Berger RL. Statistical inference. Pacific Grove. California: Wadsworth and Brooks/Cole; 1990;
  31. Duda R, Hart P. Pattern classification and scene analysis. New York: John Wiley & Sons Inc; 1973;
  32. Dietterich TG, Kong EB. Proper statistical tests for comparing supervised classification learning algorithms (technical report). Corvallis, OR: Department of Computer Science, Oregon State University; 1996;
  33. Michalski R, Clustering . In:  Shapiro S editors. Encyclopedia or artificial intelligence. New York: John Wiley & Sons Inc; 1987;
  34. Lavrač N. Selected techniques for data mining in medicine. Artificial Intelligence in Medicine. 1999;16:3–23
  35. Tan AC, Gilbert D. Ensemble machine learning on gene expression data for cancer classification. Applied Bioinformatics. 2003;2(3 Suppl):S75–S83
  36. Moser SA, Jones WT, Brosette SE. Application of data mining to intensive care unit microbiologic data. Emerging Infectious Diseases. 1999;5:454–457
  37. Lucas PJ, de Bruijn NC, Schurink K, Hoepelman A. A probabilistic and decision-theoretic approach to the management of infectious disease at the ICU. Artificial Intelligence in Medicine. 2000;19:251–297
  38. Biagoli B, Scoletta S, Cevenini G, et al. A multivariate Bayesian Model for assessing morbidity after coronary artery surgery. Critical Care (London, England). 2006;10:R94
  39. Abu-Hanna A, de Keizer N. Integrating classification trees with local logistic regression in intensive care prognosis. Artificial Intelligence in Medicine. 2003;29:5–23
  40. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. New York: Springer-Verlag; 2001;
  41. Witten I, Frank E. Data mining: practical machine learning tools and techniques. 2nd edn.. San Francisco: Morgan Kaufmann; 2005;
  42. Bishop CM. Pattern recognition and machine learning. New York: Springer-Verlag; 2006;
  43. Breiman L, Friedman J, Olshen R, Stone C. Classification and regression trees. California: Wadsworth and Brooks/Cole; 1984;
  44. Ganzert S, Guttmann J, Kersting K, et al. Analysis of respiratory pressure–volume curves in intensive care medicine using inductive machine learning. Artificial Intelligence in Medicine. 2002;26:69–86
  45. Andrews P, Sleeman D, McQuatt A, et al. In: Proceedings of the international conference on Artificial Intelligence in Medicine. 1999;
  46. Tsien CL, Kohane IS, McIntosh N. Multiple signal integration by decision tree induction to detect artifacts in the neonatal intensive care unit. Artificial Intelligence in Medicine. 2000;19:189–202
  47. Breiman L. Random forests. Journal of Machine Learning Research: JMLR. 2001;45:5–32
  48. Vens C, Van Assche A, Blockeel H, Dzeroski S. First order random forests with complex aggregates. In:  Camacho R,  King R,  Srinivasan A editor. ILP 2004: Proceedings of the 14th International Conference on Inductive Logic ProgrammingLecture Notes in Computer Science. 2004;p. 323–340
  49. Van Assche A, Blockeel H. Seeing the forest through the trees: learning a comprehensible model from an ensemble. In:  Kok J,  Koronacki J,  Mantaras RJ,  Mladenič D,  Skowron A editor. ECML 2007: Proceedings of the 18th European Conference on Machine LearningLecture Notes in Artificial Intelligence. 2007;p. 418–429
  50. Rumelhart D, Widrow B, Lehr M. The basic ideas in neural networks. Communications of the ACM. 1994;37:87–92
  51. Braithwaite EA, Dripps J, Lyon AJ, Murray A. In:  Dybowski R,  Gant V editor. Clinical applications of artificial neural networks. Cambridge University Press; 2001;
  52. Sargent D. Comparison of artificial neural networks with other statistical approaches. Cancer. 2001;91:1636–1642
  53. Goss E, Ramchandani H. Survival prediction in the intensive care unit: a comparison of neural networks and binary logit regression. Socio-Economic Planning Sciences. 1998;32:189–198
  54. Jaimes F, Farbiarz J, Alvarez D, Martínes C. Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room. Critical Care (London, England). 2005;9:R150–R156
  55. Clermont G, Angus D, DiRusso S, et al. Predicting hospital mortality for patients in the intensive care unit: a comparison of artificial neural networks with logistic regression models. Critical Care Medicine. 2001;29:291–296
  56. Tong Y, Frize M, Walker R. Extending ventilator duration estimations approach from adult to neonatal intensive care patients using artificial neural networks. IEEE Transaction on Information Technology in Biomedicine. 2002;6:188–191
  57. Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Journal of Machine Learning Research : JMLR. 1997;29:131–163
  58. Lucas PJF, Gaag van der LC, Abu-Hanna A. Bayesian networks in biomedicine and health-care. Artificial Intelligence in Medicine. 2004;30:201–214
  59. Noble WS. What is a support vector machine?. Nature Biotechnology. 2006;24:1565–1567
  60. Cristianini N, Shawe-Taylor J. An introduction to Support Vector Machines and other kernel-based learning methods. Cambridge: Cambridge University Press; 2000;
  61. Pochet NLMM, Suykens JAK. Ultrasound in Obstetrics and Gynecology. 2006;27:607–608
  62. Bazzani A, Bevilacqua A, Bollini D, et al. An SVM classifier to separate false signals from microcalcifications in digital mammogram. Physics in Medicine and Biology. 2001;46:1651–1663
  63. Van Gestel T, Suykens J, Baesens B, et al. Benchmarking least squares support vector machine classifiers. Journal of Machine Learning Research : JMLR. 2004;54:5–32
  64. Van Looy S, Verplancke T, Benoit D, et al. A novel approach for prediction of tacrolimus blood concentration in liver transplantation patients in the intensive care unit through support vector regression. Critical Care (London, England). 2007;11:R83
  65. Morik K, Brockhausen P, Thorsten J. Combining statistical learning with a knowledge-based approach – a case study in intensive care monitoring. In: Proceedings of the16th International Conference on Machine Learning. 1999;p. 268–277
  66. Hiissa M, Pahikkala T, Suominen H, et al. Towards automated classification of intensive care nursing narratives. Finland: TUCS Technical Report; 2006;
  67. Giraldo B, Garde A, Arizmendi C, et al. Support vector machine classification applied on weaning trials patients. In: Proceedings of the 28th IEEE EMBS Annual International Conference. 2006;p. 5587–5590
  68. Rasmussen CE, Williams C. Gaussian processes for machine learning. Cambridge, Massachusetts: MIT Press; 2006;
  69. Rasmussen CE. Evaluation of Gaussian processes and other methods for non-linear regression. Ph.D. Thesis, Department of Computer Science, University of Toronto; 1996.
  70. Lilley M, Frean M. Neural networks: a replacement for Gaussian processes?. In: Intelligent Data Engineering and Automated Learning. vol. 3578:Springer; 2005;p. 195–202
  71. MacKay D. Gaussian processes - a replacement for supervised neural networks?. In: Tutorial lecture notes for NIPS. 1997;
  72. Güiza F, Ramon J, Blockeel H. Gaussian processes for prediction in intensive care. In:  Lawrence ND,  Schwaighofer A,  Quinonero J editor. Proceedings of the Gaussian Processes in Practice Workshop. 2006;p. 1–4
  73. Güiza F, Ramon J, Meyfroidt G, et al. Predicting blood temperature using Gaussian processes. Journal of Critical Care. 2006;21:354–355
  74. Faul S, Gregorcic G, Boylan G, et al. Gaussian process modeling of EEG for the detection of neonatal seizures. IEEE Transactions on Biomedical Engineering. 2007;54:2151–2162
  75. Güiza F, Van Loon K, Meyfroidt G, et al. Time-series analysis techniques combined with Gaussian process classifiers for prediction of clinical stability after coronary bypass surgery. In:  Hierlemann A editors. Proceedings of biomedical engineering. 2008;p. 216–221
  76. Van den Berghe G, Wouters P, Weekers F, et al. Intensive insulin therapy in critically ill patients. The New England Journal of Medicine. 2001;345:1359–1367

PII: S1521-6896(08)00083-9

doi: 10.1016/j.bpa.2008.09.003

Best Practice & Research Clinical Anaesthesiology
Volume 23, Issue 1 , Pages 127-143 , March 2009

Article Tools

* Image Usage & Resolution