Journal of Medical Systems

, Volume 34, Issue 4, pp 551–562 | Cite as

A Tree-Based Decision Model to Support Prediction of the Severity of Asthma Exacerbations in Children

  • Ken Farion
  • Wojtek Michalowski
  • Szymon WilkEmail author
  • Dympna O’Sullivan
  • Stan Matwin
Original Paper


This paper describes the development of a tree-based decision model to predict the severity of pediatric asthma exacerbations in the emergency department (ED) at 2 h following triage. The model was constructed from retrospective patient data abstracted from the ED charts. The original data was preprocessed to eliminate questionable patient records and to normalize values of age-dependent clinical attributes. The model uses attributes routinely collected in the ED and provides predictions even for incomplete observations. Its performance was verified on independent validating data (split-sample validation) where it demonstrated AUC (area under ROC curve) of 0.83, sensitivity of 84%, specificity of 71% and the Brier score of 0.18. The model is intended to supplement an asthma clinical practice guideline, however, it can be also used as a stand-alone decision tool.


Decision making Asthma Child Retrospective studies Decision trees 



The authors would like to thank William Klement and Morvarid Sehatkar from the School of Information Technology and Engineering, University of Ottawa for help with data analysis and Chris Drummond and Peter Turney from the National Research Council of Canada for advice about contextual normalization. The authors also would like to thank anonymous reviewers for helpful comments and suggestions. Research reported here was supported by NSERC-CIHR grant from the CHRP program.


  1. 1.
    McDermott, M. F., Grant, E. N., Turner-Roan, K., Li, T., and Weiss, K. B., Asthma care practices in Chicago-area emergency departments. Chest. 116(4 Suppl 1):167–173, 1999. doi: 10.1378/chest.116.suppl_2.167S.CrossRefGoogle Scholar
  2. 2.
    Barnett, P. J., and Oberklaid, F., Acute asthma in children: Evaluation of management in a hospital emergency department. Med. J. Aust. 154(11):729–733, 1991.Google Scholar
  3. 3.
    Scribano, P. V., Lerer, T., Kennedy, D., and Cloutier, M. M., Provider adherence to a clinical practice guideline for acute asthma in a pediatric emergency department. Acad. Emerg. Med. 8(12):1147–1152, 2001. doi: 10.1111/j.1553-2712.2001.tb01131.x.CrossRefGoogle Scholar
  4. 4.
    National Heart, Lung and Blood Institute, Guidelines for the diagnosis and management of asthma. Available from Last accessed on September 15, 2008.
  5. 5.
    Canadian Association of Emergency Physicians, Guidelines for emergency management of paediatric asthma. Available from Last accessed on September 15, 2008.
  6. 6.
    Shiffman, R. N., Michel, G., Essaihi, A., and Thornquist, E., Bridging the guideline implementation gap: A systematic, document-centered approach to guideline implementation. J. Am. Med. Inform. Assoc. 11(5):418–426, 2004. doi: 10.1197/jamia.M1444.CrossRefGoogle Scholar
  7. 7.
    Waitman, L. R., and Miller, R. A., Pragmatics of implementing guidelines on the front lines. J. Am. Med. Inform. Assoc. 11(5):436–438, 2004. doi: 10.1197/jamia.M1621.CrossRefGoogle Scholar
  8. 8.
    van der Windt, D. A., Nagelkerke, A. F., Bouter, L. M., Dankert-Roelse, J. E., and Veerman, A. J., Clinical scores for acute asthma in pre-school children. A review of the literature. J. Clin. Epidemiol. 47(6):635–646, 1994. doi: 10.1016/0895-4356(94)90211-9.CrossRefGoogle Scholar
  9. 9.
    van der Windt, D. A., Promises and pitfalls in the evaluation of pediatric asthma scores. J. Pediatr. 137(6):744–746, 2000. doi: 10.1067/mpd.2000.111458.CrossRefGoogle Scholar
  10. 10.
    Bishop, J., Carlin, J., and Nolan, T., Evaluation of the properties and reliability of a clinical severity scale for acute asthma in children. J. Clin. Epidemiol. 45(1):71–76, 1992. doi: 10.1016/0895-4356(92)90190-X.CrossRefGoogle Scholar
  11. 11.
    Parkin, P. C., Macarthur, C., Saunders, N. R., Diamond, S. A., and Winders, P. M., Development of a clinical asthma score for use in hospitalized children between 1 and 5 years of age. J. Clin. Epidemiol. 49(8):821–825, 1996. doi: 10.1016/0895-4356(96)00027-3.CrossRefGoogle Scholar
  12. 12.
    Gorelick, M. H., Stevens, M. W., Schultz, T. R., and Scribano, P. V., Performance of a novel clinical score, the Pediatric Asthma Severity Score (PASS), in the evaluation of acute asthma. Acad. Emerg. Med. 11(1):10–18, 2004.Google Scholar
  13. 13.
    Ducharme, F. M., Chalut, D., Plotnick, L., Savdie, C., Kudirka, D., Zhang, X., Meng, L., and McGillivray, D., The pediatric respiratory assessment measure: A valid clinical score for assessing acute asthma severity from toddlers to teenagers. J. Pediatr. 152(4):476–480, 2008. doi: 10.1016/j.jpeds.2007.08.034.CrossRefGoogle Scholar
  14. 14.
    Smith, S. R., Baty, J. D., and Hodge, D., Validation of the pulmonary score: An asthma severity score for children. Acad. Emerg. Med. 9(2):99–104, 2002. doi: 10.1111/j.1553-2712.2002.tb00223.x.CrossRefGoogle Scholar
  15. 15.
    Gorelick, M. H., Stevens, M. W., Schultz, T. R., and Scribano, P. V., Difficulty in obtaining peak expiratory flow measurements in children with acute asthma. Pediatr. Emerg. Care. 20(1):22–26, 2004. doi: 10.1097/01.pec.0000106239.72265.16.CrossRefGoogle Scholar
  16. 16.
    Hanson, C. W., and Marshall, B. E., Artificial intelligence applications in the intensive care unit. Crit. Care Med. 29(2):427–435, 2001. doi: 10.1097/00003246-200102000-00038.CrossRefGoogle Scholar
  17. 17.
    Podgorelec, V., Kokol, P., Stiglic, B., and Rozman, I., Decision trees: An overview and their use in medicine. J. Med. Syst. 26(5):445–463, 2002. doi: 10.1023/A:1016409317640.CrossRefGoogle Scholar
  18. 18.
    Grassi, M., Villani, S., and Marinoni, A., Classification methods for the identification of ‘case’ in epidemiological diagnosis of asthma. Eur. J. Epidemiol. 17(1):19–29, 2001. doi: 10.1023/A:1010987521885.CrossRefGoogle Scholar
  19. 19.
    Becker, A. B., Nelson, N. A., and Simons, F. E., The pulmonary index: Assessment of a clinical score for asthma. Am. J. Dis. Child. 138(6):574–576, 1984.Google Scholar
  20. 20.
    Kelly, A. M., Kerr, D., and Powell, C., Is severity assessment after one hour of treatment better for predicting the need for admission in acute asthma? Respir. Med. 98(8):777–781, 2004. doi: 10.1016/j.rmed.2004.01.008.CrossRefGoogle Scholar
  21. 21.
    Schuh, S., Johnson, D., Stephens, D., Callahan, S., and Canny, G., Hospitalization patterns in severe acute asthma in children. Pediatr. Pulmonol. 23(3):184–192, 1997. doi: 10.1002/(SICI)1099-0496(199703)23:3<184::AID-PPUL3>3.0.CO;2-O.CrossRefGoogle Scholar
  22. 22.
    Smith, M., Iqbal, S. M. S. I., Rowe, B. H., and N’Diaye, T., Corticosteroids for hospitalised children with acute asthma. Cochrane Database Syst. Rev. 1:CD002886, 2003.Google Scholar
  23. 23.
    Pearson, S. D., Goulart-Fisher, D., and Lee, T. H., Critical pathways as a strategy for improving care: Problems and potential. Ann. Intern. Med. 123(12):941–948, 1995.Google Scholar
  24. 24.
    de Rooij, S. E., Abu-Hanna, A., Levi, M., and de Jonge, E., Identification of high-risk subgroups in very elderly intensive care unit patients. Crit. Care. 11(2):R33, 2007. doi: 10.1186/cc5716.CrossRefGoogle Scholar
  25. 25.
    Abu-Hanna, A., and Lucas, P. J. F., Prognostic models in medicine. AI and statistical approaches. Methods Inf. Med. 40:1–5, 2001.Google Scholar
  26. 26.
    Quinlan, R., C4.5: programs for machine learning. Morgan Kaufmann, San Mateo, CA, p. 302, 1993.Google Scholar
  27. 27.
    Witten, I. H., and Frank, E., Data mining: Practical machine learning tools and techniques, 2nd edition. Morgan Kaufmann, San Francisco, CA, p. 525, 2005.zbMATHGoogle Scholar
  28. 28.
    Breiman, L., Friedman, J., Stone, C. J., and Olshen, R. A., Classification and regression trees. Wadsworth & Brooks, New York, 1984.zbMATHGoogle Scholar
  29. 29.
    Kohavi, R., and Quinlan, R., Decision-tree discovery. In: Klosgen, W., and Zytkow, J. M. (Eds.), Handbook of Data Mining and Knowledge Discovery. Oxford University Press, New York, pp. 267–276, 2002.Google Scholar
  30. 30.
    Cios, K. J., and Moore, G. W., Uniqueness of medical data mining. Artif. Intell. Med. 26(1–2):1–24, 2002. doi: 10.1016/S0933-3657(02)00049-0.CrossRefGoogle Scholar
  31. 31.
    Beck, J. R., Garcia, M. E., Zhong, M., Georgiopoulos, M., and Anagnostopoulos, G. C., A backward adjusting strategy and optimization of the C4.5 parameters to improve C4.5’s performance. In: Wilson, D., and Lane, H. C., (Eds.), Proceedings of the 21st International Florida Artificial Intelligence Research Society (FLAIRS) Conference (FLAIRS 2008), Coconut Grove, Florida, USA, May 15–17, 2008, p. 35–40.Google Scholar
  32. 32.
    Faraggi, D., and Reiser, B., Estimation of the area under the ROC curve. Stat. Med. 21(20):3093–3106, 2002. doi: 10.1002/sim.1228.CrossRefGoogle Scholar
  33. 33.
    Fawcett, T., An introduction to ROC analysis. Pattern Recognit. Lett. 27(8):861–874, 2006. doi: 10.1016/j.patrec.2005.10.010.CrossRefMathSciNetGoogle Scholar
  34. 34.
    Grzymala-Busse, J.W., and Hu, M., A comparison of several approaches to missing attribute values in data mining. In: Ziarko, W., and Yao, Y. Y., (Eds.), Rough Sets and current Trends in Computing. Second International Conference, RSCTC 2000 Banff, Canada, October 16–19, 2000. Revised papers. Berlin: Springer,, p. 378–385, 2000.Google Scholar
  35. 35.
    O’Sullivan, D., Elazmeh, W., Wilk, S., Farion, K., Matwin, S., Michalowski, W., Sehatkar, M., Using secondary knowledge to support decision tree classification of retrospective clinical data. In: Ras, Z, Zighed, D, and Tsumoto, S, (Eds.), Mining Complex Data. ECML/PKDD 2007 Third International Workshop, MCD 2007, Warsaw, Poland, September 17–21, 2007. Revised selected papers. Berlin: Springer, p. 238–251, 2008.Google Scholar
  36. 36.
    Acuna, E., and Rodriguez, C., The treatment of missing values and its effect in the classifier accuracy. In: Banks, D., House, L., McMorris, F. R., Arabie, P., and Gaul, W., (Eds.), Classification, Clustering and Data Mining Applications. Proceedings of the Meeting of the International Federation of Classification Societies (IFCS), Illinois Institute of Technology, Chicago, 15–18 July 2004. Berlin: Springer, p. 639–648, 2004.Google Scholar
  37. 37.
    Turney, P., and Halasz, M., Contextual normalization applied to aircraft gas turbine engine diagnosis. J. Appl. Intell. 3:109–19, 1993. doi: 10.1007/BF00871892.CrossRefGoogle Scholar
  38. 38.
    Chey, T., Jalaludin, B., Hanson, R., and Leeder, S., Validation of a predictive model for asthma admission in children: How accurate is it for predicting admissions? J. Clin. Epidemiol. 52(12):1157–1163, 1999. doi: 10.1016/S0895-4356(99)00111-0.CrossRefGoogle Scholar
  39. 39.
    Crighton, E. J., Mamdani, M. M., and Upshur, R. E. G., A population based time series analysis of asthma hospitalisations in Ontario, Canada: 1988 to 2000. BMC Health Serv. Res. 1(1):7–7, 2001. doi: 10.1186/1472-6963-1-7.CrossRefGoogle Scholar
  40. 40.
    Peek, N., Arts, D. G. T., Bosman, R. J., van der Voort, P. H. J., and de Keizer, N. F., External validation of prognostic models for critically ill patients required substantial sample sizes. J. Clin. Epidemiol. 60:491–501, 2007.CrossRefGoogle Scholar
  41. 41.
    Obuchowski, N. A., and Lieber, M. L., Confidence intervals for the receiver operating characteristic area in studies with small samples. Acad. Radiol. 5(8):561–571, 1998. doi: 10.1016/S1076-6332(98)80208-0.CrossRefGoogle Scholar
  42. 42.
    Zimmerman, J. E., Kramer, A. A., McNair, D. S., and Malila, F. M., Acute physiology and chronic health evaluation (APACHE) IV: Hospital mortality assessment for today’s critically ill patients. Crit. Care Med. 34(5):1297–1310, 2006. doi: 10.1097/01.CCM.0000215112.84523.F0.CrossRefGoogle Scholar
  43. 43.
    Li, D., German, D., Lulla, S., Thomas, R. G., and Wilson, S. R., Prospective study of hospitalization for asthma. A preliminary risk factor model. Am. J. Respir. Crit. Care Med. 151(3 Pt 1):647–655, 1995.Google Scholar
  44. 44.
    Holt, G., Letter to the Editor. Clinical benchmarking for the validation of AI medical diagnostic classifiers. Artif. Intell. Med. 35(3):259–260, 2005. doi: 10.1016/j.artmed.2005.10.001.CrossRefGoogle Scholar
  45. 45.
    Kerem, E., Tibshirani, R., Canny, G., Bentur, L., Reisman, J., Schuh, S., Stein, R., and Levison, H., Predicting the need for hospitalization in children with acute asthma. Chest. 98(6):1355–1361, 1990. doi: 10.1378/chest.98.6.1355.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Ken Farion
    • 1
  • Wojtek Michalowski
    • 2
  • Szymon Wilk
    • 2
    Email author
  • Dympna O’Sullivan
    • 2
  • Stan Matwin
    • 3
    • 4
  1. 1.Departments of Pediatrics and Emergency MedicineUniversity of OttawaOttawaCanada
  2. 2.Telfer School of ManagementUniversity of OttawaOttawaCanada
  3. 3.School of Information Technology and EngineeringUniversity of OttawaOttawaCanada
  4. 4.Institute of Computer SciencePolish Academy of SciencesWarsawPoland

Personalised recommendations