Multiclassifier Systems for Predicting Neurological Outcome of Patients with Severe Trauma and Polytrauma in Intensive Care Units

• Published in: Journal of medical systems Vol. 41; no. 9; p. 136
• Main Authors: González-Robledo, Javier, Martín-González, Félix, Sánchez-Barba, Mercedes, Sánchez-Hernández, Fernando, Moreno-García, María N.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2017; Springer Nature B.V
• Subjects: Algorithms; Brain; Brain Injuries, Traumatic; Classification; Classifiers; Emergencies; Emergency medical care; Emergency medical services; Epidemiology; Head injuries; Health Informatics; Health Sciences; Hospitals; Humans; Intensive care; Intensive Care Units; Medical prognosis; Medicine; Medicine & Public Health; Multiple Trauma; Oversampling; Patient Facing Systems; Patients; Prediction models; Sensitivity and Specificity; Statistics for Life Sciences; Trauma; Traumatic brain injury; Severe trauma; Polytrauma; Data mining; Mortality; Ensemble classifiers; Multiclassifiers
• ISSN: 0148-5598; 1573-689X; 1573-689X
• DOI: 10.1007/s10916-017-0789-1

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.