Abstract
This paper presents an ensemble based classification proposal for predicting neurological outcome of severely traumatized patients. The study comprises both the whole group of patients and a subgroup containing those patients suffering traumatic brain injury (TBI). Data was gathered from patients hospitalized in the Intensive Care Unit (ICU) of the University Hospital in Salamanca. Predictive models were induced from both epidemiologic and clinical variables taken at the emergency room and along the stay in the ICU. The large number of variables leads to a low accuracy in the classifiers even when feature selection methods are used. In addition, the presence of a much larger number of instances of one of the classes in the subgroup of TBI patients produces a significantly lesser precision for the minority class. Usual ways of dealing with the last problem is to use undersampling and oversampling strategies, which can lead to the loss of valuable data and overfitting problems respectively. Our proposal for dealing with these problems is based in the use of ensemble multiclassifiers as well as in the use of an ensemble playing the role of base classifier in multiclassifiers. The proposed strategy gave the best values of the selected quality measures (accuracy, precision, sensitivity, specificity, F-measure and area under the Receiver Operator Characteristic curve) as well as the closest values of precision for the two classes under study in the case of the classification from imbalanced data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Berikol, G.B., Yildiz, O., and Özcan, I.T., Diagnosis of acute coronary syndrome with a support vector machine. J. Med. Syst. 40:84, 2016.
Boyd, C.R., Tolson, M.A., and Copes, W.S., Evaluating trauma care: The TRISS method. J. Trauma. 27:370–378, 1984.
Breiman, L., Bagging predictors. Mach. Learn. 24(2):123–140, 1996.
Breiman, L., Random forests. Mach. Learn. 45(1):5–32, 2001.
Chawda, M.N., Hildebrand, F., Pape, H.C., and Giannoudis, P.V., Predicting outcome after multiple trauma: Which scoring system. Injury. 35(4):347–358, 2004.
Chen, H., Tan, C., Lin, Z., and Wu, T., The diagnostics of diabetes mellitus based on ensemble modeling and hair/urine element level analysis. Comput. Biol. Med. 50(2014):70–75, 2014.
Chen, D., Wang, H., Sheng, L., Hueman, M.T., Henson, D.E., Schwartz, A.M., and Patel, J.A., An algorithm for creating prognostic Systems for Cancer. J. Med. Syst. 40:160, 2016.
Cohen, N.H., The real reasons not to rely on severity scores. Crit. Care Med. 38(2010):334–335, 2010.
Cooper, G.F., and Herskovits, E., A Bayesian method for the induction of probabilistic networks from data. Mach. Learn. 9:309–347, 1992.
Dossett, L.A., Redhage, L.A., Sawyer, R.G., and May, A.K., Revisiting the validity of APACHE II in the trauma ICU: Improved risk stratification in critically injured adults. Injury. 40(9):993–998, 2009.
Freund, Y., and Schapire, R.E., Experiments with a new boosting algorithm. Proceedings 13th International Conference on Machine Learning:148–156, 1996.
Gama, J., and Brazdil, P., Cascade Generalization. Mach. Learn. 41(3):315–343, 2000.
Hall, M. A. Correlation-based Feature Selection for Machine Learning. PhD Thesis, University of Waikato, Hamilton, Nueva Zelanda, 1999.
Hemmila, M. R., Jakubus, J. L., Maggio, P. M., et al. Real money: Complications and hospital costs in trauma patients. Surgery 144(2):307–316, 2008.
Hoffmann, M., Lefering, R., Rueger, J.M., Kolb, J.P., Izbicki, J.R., Ruecker, A.H., Rupprechtz, M., and Lehmann, W., Pupil evaluation in addition to Glasgow coma scale components in prediction of traumatic brain injury and mortality. Br J Surg. 99(1):122–130, 2012.
Hulse, J., Khoshgoftaar, T., and Napolitano, A., Experimental perspectives on learning from imbalanced data. Proceedings of the 24th International Conference on Machine learning:935–942, 2007.
Hunter, A., Kennedy, L., Henry, J., and Ferguson, I., Application of neural networks and sensitivity analysis to improved prediction of trauma survival. Comput. Methods Prog. Biomed. 62(2000):11–19, 2000.
Kuncheva, L.I., Combining pattern classifiers: Methods and algorithms. John Wiley & Sons, 2004.
Li, S., Tang, B., and He, H., An imbalanced learning based MDR-TB early warning system. J. Med. Syst. 40:164, 2016.
Marmarou, A., Lu, J., Butcher, I., et al., Prognostic value of the Glasgow coma scale and pupil reactivity in traumatic brain injury assessed pre-hospital and on enrollment: An IMPACT análisis. J. Neurotrauma. 24(2):270–280, 2007.
Martín, F., González, J., Sánchez, F., and Moreno, M.N., Success/failure prediction of noninvasive mechanical ventilation in intensive care units. Using multiclassifiers and feature selection methods. Methods Inf. Med. 55(3):234–241, 2016.
NAEMT, PHTLS: Prehospital Trauma Life Support. Mosby/JEMS, 2010. isbn:0-323-06502-3.
Özcift, A., Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. Comput. Biol. Med. 41(2011):265–271, 2011.
Platt, J. Fast. Training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C and Smola A (Eds.), Advances in Kernel Methods. Support Vector Learning. MIT Press, 1998.
Quinlan JR (1993) C4.5: Programs for machine learning. Morgan Kaufmann, San Mateo, CA., USA, 1993.
Schetinin, V., Jakaite, L., Jakaitis, J., and Krzanowski, W., Bayesian decision trees for predicting survival of patients: A study on the US national trauma data bank. Comput. Methods Prog. Biomed. 111(2013):602–612, 2013.
Wagholikar, K.B., Sundararajan, V., and Deshpande, A.W., Modeling paradigms for medical diagnostic decision support: A survey and future directions. J. Med. Syst. 36:3029–3049, 2012.
Wolpert, D., and Stacked, H., Generalization. Neural Netw. 5:241–259, 1992.
Acknowledgements
The authors thank the staff of the Medical Records Department of the University Hospital of Salamanca for their support in providing patient data.
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on Patient Facing Systems
Electronic supplementary material
Online resource 1
(DOCX 44 kb)
Rights and permissions
About this article
Cite this article
González-Robledo, J., Martín-González, F., Sánchez-Barba, M. et al. Multiclassifier Systems for Predicting Neurological Outcome of Patients with Severe Trauma and Polytrauma in Intensive Care Units. J Med Syst 41, 136 (2017). https://doi.org/10.1007/s10916-017-0789-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-017-0789-1