Abstract
Medical databases often contain large amounts of missing data. This poses very strict constraints to the use of exclusively computer-based feature selection techniques. Moreover, in medical data there is usually no unique combination of features that provides the best explanation of the outcome. In this paper we propose a modified Sequential Forward Selection (SFS) approach to the problem of selecting sets of physiologic variables from septic shock patients in order to predict their outcome. We were able to achieve ten different combinations of only three physiological numerical parameters, all performing better than the best set suggested up to now. The performances of these sets are higher than 0.97 for AUC and up to 0.97 for accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Berthold, M.R.: Fuzzy-models and potential outliers. In: Proc. of the 18th Int. Conf. of the North America Fuzzy Information Processing Society. IEEE Press (1999)
Bezdek, J.C., Ehrlich, R., Full, W.: FCM: the fuzzy c-means clustering algorithm. Comput. Geosci. 10, 191–203 (1984)
Brause, R., Hamker, F., Paetz, J.: Septic Shock Diagnosis by Neural Networks and Rule Based Systems. In: Computational Intelligence Techniques in Medical Diagnosis and Prognosis. Springer US (2001)
Burchardi, H., Schneider, H.: Economic Aspects of Severe Sepsis: A Review of Intensive Care Unit Costs, Cost of Illness and Cost Effectiveness of Therapy. Pharmacoeconomics 22, 793–813 (2004)
Dellinger, R.P., et al.: Surviving Sepsis Campaign: International guidelines for management of severe sepsis and septic shock: 2008. Crit. Care Med. 36, 1394–1396 (2008)
Hanisch, E., Brause, R., Arlt, B., Paetz, J., Holzer, K.: The MEDAN Database (2003), http://www.medan.de
Hua, J., Xiong, Z., Lowey, J., Suh, E., Dougherty, E.R.: Optimal number of features as a function of sample size for various classification rules. Bioinform. 21, 1509–1515 (2005)
MathWorks: MatLab R2012a Documentation for Fuzzy Logic Toolbox (2012), http://www.mathworks.com
Paetz, J.: Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions. Artif. Intel. Med. 28, 207–230 (2003)
Paetz, J., Arlt, B.: A Neuro-fuzzy Based Alarm System for Septic Shock Patients with a Comparison to Medical Scores. In: Colosimo, A., Giuliani, A., Sirabella, P. (eds.) ISMDA 2002. LNCS, vol. 2526, pp. 42–52. Springer, Heidelberg (2002)
Paetz, J., Arlt, B., Erz, K., Holzer, K., Brause, R., Hanisch, E.: Data quality aspects of a database for abdominal septic shock patients. Comput. Meth. Prog. Biomed. 75, 23–30 (2004)
Pal, N.R., Bezdek, J.C.: On cluster validity for fuzzy c-means model. IEEE Trans. Fuzzy Syst. 3, 370–379 (1995)
Pereira, R.D., et al.: Predicting Septic Shock Outcomes in a Database with Missing Data using Fuzzy Modeling. In: Proc. of the IEEE Int. Conf. on Fuzzy Systems (2011)
Takagi, T., Sugeno, M.: Fuzzy identification of system and its applications to modelling and control. IEEE Trans. Syst. Man Cyb. 15, 116–132 (1985)
Xie, X.L., Beni, G.: A Validity Measure for Fuzzy Clustering. IEEE Trans. Pattern Anal. Mach. Intel. 13, 841–847 (1991)
Yan, S.Y., Sun, Z.Q.: Universal Approximation for Takagi-Sugeno Fuzzy Systems Combining Statically and Dynamically Constructive Methods-MISO Cases. In: Proc. of the Int. Conf. on Information Management and Engineering (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pereira, R.D., Sousa, J., Vieira, S., Reti, S., Finkelstein, S. (2013). Modified Sequential Forward Selection Applied to Predicting Septic Shock Outcome in the Intensive Care Unit. In: Kruse, R., Berthold, M., Moewes, C., Gil, M., Grzegorzewski, P., Hryniewicz, O. (eds) Synergies of Soft Computing and Statistics for Intelligent Data Analysis. Advances in Intelligent Systems and Computing, vol 190. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33042-1_50
Download citation
DOI: https://doi.org/10.1007/978-3-642-33042-1_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33041-4
Online ISBN: 978-3-642-33042-1
eBook Packages: EngineeringEngineering (R0)