Prediction of Outcome in the Vegetative State by Machine Learning Algorithms: A Model for Clinicians?

Purpose of this study was to compare different Machine Learning classifiers (C4.5, Support Vector Machine, Naive Bayes, K-NN) in the early prediction of outcome of the subjects in vegetative state due to traumatic brain injury. Accuracy proved acceptable for all compared methods (AUC > 0.8), but sensitivity and specificity varied considerably and only some classifiers (in particular, Support Vector Machine) appear applicable models in the clinical routine. A combined use of classifiers is advisable.

[1]  Multi-Society Task Force on Pvs.  Medical aspects of the persistent vegetative state (1). , 1994, The New England journal of medicine.

[2]  B. Jennett,et al.  Assessment of coma and impaired consciousness. A practical scale. , 1974, Lancet.

[3]  Ariel Rubinstein,et al.  A Course in Game Theory , 1995 .

[4]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[5]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[6]  F. Plum,et al.  Persistent vegetative state after brain damage. A syndrome in search of a name. , 1972, Lancet.

[7]  A. Rovlias,et al.  Classification and regression tree for prediction of outcome after severe head injury using simple clinical and laboratory variables. , 2004, Journal of neurotrauma.

[8]  B. Jennett.  The vegetative state , 2002, Journal of neurology, neurosurgery, and psychiatry.

[9]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[10]  J. Minderhoud,et al.  Prognosis of the posttraumatic vegetative state , 2005, Acta Neurochirurgica.

[11]  R. Dennis Cook,et al.  Cross-Validation of Regression Models , 1984 .

[12]  R. Thatcher,et al.  Quantitative EEG Normative Databases: Validation and Clinical Correlation , 2003 .

[13]  B. Jennett,et al.  ASSESSMENT OF OUTCOME AFTER SEVERE BRAIN DAMAGE A Practical Scale , 1975, The Lancet.

[14]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[15]  M. Musen,et al.  Handbook of Medical Informatics , 2002 .

[16]  Claudio Sartori.  02.1 Machine Learning With WEKA , 2012 .

[17]  Steven Laureys.  The neural correlate of (un)awareness: lessons from the vegetative state , 2005, Trends in Cognitive Sciences.

[18]  G. Dolce,et al.  The Post-traumatic Vegetative State , 2002 .

[19]  W. Sannita,et al.  The Glasgow outcome scale in vegetative state: A possible source of bias , 2009, Brain injury.

[20]  Rong Ge,et al.  Joint cluster analysis of attribute and relationship data withouta-priori specification of the number of clusters , 2007, KDD '07.

[21]  F. Gianfelici,et al.  Nearest-Neighbor Methods in Learning and Vision (Shakhnarovich, G. et al., Eds.; 2006) [Book review] , 2008 .

[22]  Stefan Golaszewski,et al.  Prediction of recovery from post-traumatic vegetative state with cerebral magnetic-resonance imaging , 1998, The Lancet.

[23]  V. Lagani,et al.  Clinical signs and early prognosis in vegetative state: A decisional tree, data-mining study , 2008, Brain injury.

[24]  K. Andrews.  International Working Party on the Management of the Vegetative State: summary report. , 1996, Brain injury.

[25]  R. Newcombe.  Consciousness , 1996, Journal of Clinical Neuroscience.

[26]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[27]  Margaret S. Pepe,et al.  A regression modelling framework for receiver operating characteristic curves in medical diagnostic testing , 1997 .

[28]  W Zucchini,et al.  On the statistical analysis of ROC curves. , 1989, Statistics in medicine.

[29]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[30]  Trevor Darrell,et al.  Nearest-Neighbor Methods in Learning and Vision , 2008, IEEE Trans. Neural Networks.