Improved Diagnosis in Children with Partial Epilepsy Using a Multivariable Prediction Model Based on EEG Network Characteristics

Background Electroencephalogram (EEG) acquisition is routinely performed to support an epileptic origin of paroxysmal events in patients referred with a possible diagnosis of epilepsy. However, in children with partial epilepsies the interictal EEGs are often normal. We aimed to develop a multivariable diagnostic prediction model based on electroencephalogram functional network characteristics. Methodology/Principal Findings Routinely performed interictal EEG recordings at first presentation of 35 children diagnosed with partial epilepsies, and of 35 children in whom the diagnosis epilepsy was excluded (control group), were used to develop the prediction model. Children with partial epilepsy were individually matched on age and gender with children from the control group. Periods of resting-state EEG, free of abnormal slowing or epileptiform activity, were selected to construct functional networks of correlated activity. We calculated multiple network characteristics previously used in functional network epilepsy studies and used these measures to build a robust, decision tree based, prediction model. Based on epileptiform EEG activity only, EEG results supported the diagnosis of with a sensitivity and specificity of 0.77 and 0.91 respectively. In contrast, the prediction model had a sensitivity of 0.96 [95% confidence interval: 0.78–1.00] and specificity of 0.95 [95% confidence interval: 0.76–1.00] in correctly differentiating patients from controls. The overall discriminative power, quantified as the area under the receiver operating characteristic curve, was 0.89, defined as an excellent model performance. The need of a multivariable network analysis to improve diagnostic accuracy was emphasized by the lack of discriminatory power using single network characteristics or EEG's power spectral density. Conclusions/Significance Diagnostic accuracy in children with partial epilepsy is substantially improved with a model combining functional network characteristics derived from multi-channel electroencephalogram recordings. Early and accurate diagnosis is important to start necessary treatment as soon as possible and inform patients and parents on possible risks and psychosocial aspects in relation to the diagnosis.

[1]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[2]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[3]  Stefan Burr,et al.  The Mathematics of networks , 1982 .

[4]  F. Harrell,et al.  Regression modelling strategies for improved prognostic prediction. , 1984, Statistics in medicine.

[5]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[6]  P. Bonacich.  Power and Centrality: A Family of Measures , 1987, American Journal of Sociology.

[7]  R. Clancy.  Electroencephalography: Basic principles, clinical applications and related fields, ed 2. Edited by Ernst Niedermeyer Fernando Lopes da Silva Baltimore, Urban and Schwarzenberg, 1987 940 pp, illustrated, $110.00 , 1988 .

[8]  D. Goodin,et al.  Detection of epileptiform activity by different noninvasive EEG methods in complex partial epilepsy , 1990, Annals of neurology.

[9]  Brian D. Ripley,et al.  The R Project in Statistical Computing , 2001 .

[10]  C. Hirst.  The LTSN MathsTEAM Project: LTSN Maths, Stats & OR Network, LTSN Engineering and The UK Centre for Materials Education , 2002 .

[11]  C. Stam,et al.  Synchronization likelihood: an unbiased measure of generalized synchronization in multivariate data sets , 2002 .

[12]  Cornelis J Stam,et al.  Seizure detection in the neonatal EEG with synchronization likelihood , 2003, Clinical Neurophysiology.

[13]  K. Zou,et al.  Statistical validation based on parametric receiver operating characteristic analysis of continuous classification data. , 2003, Academic radiology.

[14]  Ewout W Steyerberg,et al.  Internal and external validation of predictive models: a simulation study of bias and precision in small samples. , 2003, Journal of clinical epidemiology.

[15]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[16]  O. Sporns,et al.  Organization, development and function of complex brain networks , 2004, Trends in Cognitive Sciences.

[17]  Cornelis J Stam,et al.  Different EEG frequency band synchronization during nocturnal frontal lobe seizures , 2004, Clinical Neurophysiology.

[18]  M. Newman.  Power laws, Pareto distributions and Zipf's law , 2005 .

[19]  P. Lucas,et al.  The formation of stars , 2005 .

[20]  Rodrigo Quian Quiroga,et al.  Nonlinear multivariate analysis of neurophysiological signals , 2005, Progress in Neurobiology.

[21]  K. Kaski,et al.  Intensity and coherence of motifs in weighted complex networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  S. Smith.  EEG in the diagnosis, classification, and management of patients with epilepsy , 2005, Journal of Neurology, Neurosurgery & Psychiatry.

[23]  Francesca Bovolo,et al.  Automatic selection of frequency and time intervals for classification of EEG signals , 2007 .

[24]  Mikko Kivelä,et al.  Generalizations of the clustering coefficient to weighted complex networks. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  Cornelis J Stam,et al.  Graph theoretical analysis of complex networks in the brain , 2007, Nonlinear biomedical physics.

[26]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[27]  C. Stam,et al.  Small-world networks and epilepsy: Graph theoretical analysis of intracerebrally recorded mesial temporal lobe seizures , 2007, Clinical Neurophysiology.

[28]  E. Wirrell,et al.  Diagnostic Inaccuracy in Children Referred with “First Seizure”: Role for a First Seizure Clinic , 2007, Epilepsia.

[29]  J. Pastor,et al.  Synchronization Clusters of Interictal Activity in the Lateral Temporal Cortex of Epileptic Patients: Intraoperative Electrocorticographic Analysis , 2008, Epilepsia.

[30]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[31]  P. Chauvel,et al.  Decreased basal fMRI functional connectivity in epileptogenic networks and contralateral compensatory mechanisms , 2009, Human brain mapping.

[32]  E. Bullmore,et al.  Human brain networks in health and disease , 2009, Current opinion in neurology.

[33]  Xavier Robin,et al.  pROC: an open-source package for R and S+ to analyze and compare ROC curves , 2011, BMC Bioinformatics.

[34]  C. Stam,et al.  ‘Functional Connectivity’ Is a Sensitive Predictor of Epilepsy Diagnosis after the First Seizure , 2010, PloS one.

[35]  John Skvoretz,et al.  Node centrality in weighted networks: Generalizing degree and shortest paths , 2010, Soc. Networks.

[36]  Huafu Chen,et al.  Altered Functional Connectivity and Small-World in Mesial Temporal Lobe Epilepsy , 2010, PloS one.

[37]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[38]  J Martinerie,et al.  Functional modularity of background activities in normal and epileptic brain networks. , 2008, Physical review letters.

[39]  K. Lehnertz,et al.  State dependent properties of epileptic brain networks: Comparative graph–theoretical analyses of simultaneously recorded EEG and MEG , 2010, Clinical Neurophysiology.

[40]  P. Hofman,et al.  Loss of network efficiency associated with cognitive decline in chronic epilepsy , 2011, Neurology.

[41]  C. Stam,et al.  r Human Brain Mapping 32:413–425 (2011) r Network Analysis of Resting State EEG in the Developing Young Brain: Structure Comes With Maturation , 2022 .

[42]  R Todd Constable,et al.  Functional MRI connectivity as a predictor of the surgical outcome of epilepsy , 2011, Epilepsia.

[43]  Bin He,et al.  Graph analysis of epileptogenic networks in human partial epilepsy , 2011, Epilepsia.

[44]  Max Kuhn,et al.  caret: Classification and Regression Training , 2015 .