Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach

Objectives: Hemispherotomy (HT) is a surgical option for treatment of drug-resistant seizures due to hemispheric structural lesions. Factors affecting seizure outcome have not been fully clarified. In our study, we used a brain Machine Learning (ML) approach to evaluate the possible role of Inter-hemispheric EEG Connectivity (IC) in predicting post-surgical seizure outcome. Methods: We collected 21 pediatric patients with drug-resistant epilepsy; who underwent HT in our center from 2009 to 2020; with a follow-up of at least two years. We selected 5-s windows of wakefulness and sleep pre-surgical EEG and we trained Artificial Neuronal Network (ANN) to estimate epilepsy outcome. We extracted EEG features as input data and selected the ANN with best accuracy. Results: Among 21 patients, 15 (71%) were seizure and drug-free at last follow-up. ANN showed 73.3% of accuracy, with 85% of seizure free and 40% of non-seizure free patients appropriately classified. Conclusions: The accuracy level that we reached supports the hypothesis that pre-surgical EEG features may have the potential to predict epilepsy outcome after HT. Significance: The role of pre-surgical EEG data in influencing seizure outcome after HT is still debated. We proposed a computational predictive model, with an ML approach, with a high accuracy level.

[1]  Simeon M. Wong,et al.  Decoding Intracranial EEG With Machine Learning: A Systematic Review , 2022, Frontiers in Human Neuroscience.

[2]  J. Ojemann,et al.  Hemispherectomy Outcome Prediction Scale: Development and validation of a seizure freedom prediction tool , 2021, Epilepsia.

[3]  Terence O'Brien,et al.  Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review , 2020, IEEE Reviews in Biomedical Engineering.

[4]  Emil Hadzhikolev,et al.  Determining the Number of Neurons in Artificial Neural Networks for Approximation, Trained with Algorithms Using the Jacobi Matrix , 2020, TEM Journal.

[5]  Noriaki Hattori,et al.  Electroencephalographic Phase Synchrony Index as a Biomarker of Poststroke Motor Impairment and Recovery , 2020, Neurorehabilitation and neural repair.

[6]  Daniel M Goldenholz,et al.  Machine learning applications in epilepsy , 2019, Epilepsia.

[7]  Matteo Demuru,et al.  A comparison between power spectral density and network metrics: an EEG study , 2019, bioRxiv.

[8]  C. Marras,et al.  Outcome after hemispherotomy in patients with intractable epilepsy: Comparison of techniques in the Italian experience , 2019, Epilepsy & Behavior.

[9]  C. Mulert,et al.  The interhemispheric miscommunication theory of auditory verbal hallucinations in schizophrenia. , 2019, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[10]  Chris Rorden,et al.  Deep learning applied to whole‐brain connectome to determine seizure control after epilepsy surgery , 2018, Epilepsia.

[11]  Yash Paul.  Various epileptic seizure detection techniques using biomedical signals: a review , 2018, Brain Informatics.

[12]  Dong Seok Kim,et al.  Hemispherotomy and Functional Hemispherectomy: Indications and Outcomes , 2018, Journal of epilepsy research.

[13]  Sebastien Ourselin,et al.  Structural and effective connectivity in focal epilepsy , 2017, NeuroImage: Clinical.

[14]  Kyoung Joon Min,et al.  Comparison of Electroencephalography (EEG) Coherence between Major Depressive Disorder (MDD) without Comorbidity and MDD Comorbid with Internet Gaming Disorder , 2017, Journal of Korean medical science.

[15]  J. H. Cross,et al.  Operational classification of seizure types by the International League Against Epilepsy: Position Paper of the ILAE Commission for Classification and Terminology , 2017, Epilepsia.

[16]  Samuel B. Tomlinson,et al.  Interictal network synchrony and local heterogeneity predict epilepsy surgery outcome among pediatric patients , 2017, Epilepsia.

[17]  M. Panigrahi,et al.  An observational study on outcome of hemispherotomy in children with refractory epilepsy. , 2016, International journal of surgery.

[18]  Jian-Guo Zhang,et al.  Hemispheric surgery for refractory epilepsy: a systematic review and meta-analysis with emphasis on seizure predictors and outcomes. , 2016, Journal of neurosurgery.

[19]  Varsha K. Harpale,et al.  Time and frequency domain analysis of EEG signals for seizure detection: A review , 2016, 2016 International Conference on Microelectronics, Computing and Communications (MicroCom).

[20]  Berj L. Bardakjian,et al.  Identification of brain regions of interest for epilepsy surgery planning using support vector machines , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[21]  Richard Staba,et al.  Multimodal data and machine learning for surgery outcome prediction in complicated cases of mesial temporal lobe epilepsy , 2015, Comput. Biol. Medicine.

[22]  William Stafford Noble,et al.  Machine learning applications in genetics and genomics , 2015, Nature Reviews Genetics.

[23]  Seokjun Hong,et al.  Magnetic resonance imaging pattern learning in temporal lobe epilepsy: Classification and prognostics , 2015, Annals of neurology.

[24]  Mojtaba Bandarabadi,et al.  Epileptic seizure prediction using relative spectral power features , 2015, Clinical Neurophysiology.

[25]  R. Tubbs,et al.  Hemispherectomy for treatment of refractory epilepsy in the pediatric age group: a systematic review. , 2015, Journal of neurosurgery. Pediatrics.

[26]  W. Mueller,et al.  Fifty consecutive hemispherectomies: outcomes, evolution of technique, complications, and lessons learned. , 2014, Neurosurgery.

[27]  Mark S. Cohen,et al.  The utility of data-driven feature selection: Re: Chu et al. 2012 , 2014, NeuroImage.

[28]  Yu-Ri Lee,et al.  A Novel EEG Feature Extraction Method Using Hjorth Parameter , 2014 .

[29]  Richard C. Burgess,et al.  Functional Connectivity Estimated from Intracranial EEG Predicts Surgical Outcome in Intractable Temporal Lobe Epilepsy , 2013, PloS one.

[30]  Andreas Schulze-Bonhage,et al.  Reoperation for refractory epilepsy in childhood: a second chance for selected patients. , 2013, Neurosurgery.

[31]  C. Bulteau,et al.  Epilepsy surgery for hemispheric syndromes in infants: Hemimegalencepahly and hemispheric cortical dysplasia , 2013, Brain and Development.

[32]  C. Elger,et al.  Prediction of post-surgical seizure outcome in left mesial temporal lobe epilepsy , 2013, NeuroImage: Clinical.

[33]  C. Bielza,et al.  Machine Learning Approach for the Outcome Prediction of Temporal Lobe Epilepsy Surgery , 2013, PloS one.

[34]  Wesley T. Kerr,et al.  Computer-Aided Diagnosis and Localization of Lateralized Temporal Lobe Epilepsy Using Interictal FDG-PET , 2013, Front. Neurol..

[35]  P. Kotagal,et al.  Longitudinal seizure outcome and prognostic predictors after hemispherectomy in 170 children , 2013, Neurology.

[36]  Wesley T. Kerr,et al.  Automated diagnosis of epilepsy using EEG power spectrum , 2012, Epilepsia.

[37]  Graeme D. Jackson,et al.  Cortical and thalamic resting-state functional connectivity is altered in childhood absence epilepsy , 2012, Epilepsy Research.

[38]  I. S. Gousias,et al.  Classification and Lateralization of Temporal Lobe Epilepsies with and without Hippocampal Atrophy Based on Whole-Brain Automatic MRI Segmentation , 2012, PloS one.

[39]  G. Avanzini,et al.  Enhanced frontocentral EEG connectivity in photosensitive generalized epilepsies: A partial directed coherence study , 2012, Epilepsia.

[40]  R T Constable,et al.  Resting functional connectivity between the hemispheres in childhood absence epilepsy , 2011, Neurology.

[41]  W. Smoker,et al.  Differential Diagnosis of Cerebral Hemispheric Pathology , 2011, Clinical Neuroradiology.

[42]  M. R. Herbert,et al.  Reduced functional connectivity in visual evoked potentials in children with autism spectrum disorder , 2010, Clinical Neurophysiology.

[43]  U. Rajendra Acharya,et al.  Automatic Identification of Epileptic and Background EEG Signals Using Frequency Domain Parameters , 2010, Int. J. Neural Syst..

[44]  P. Ferroli,et al.  Hemispherotomy and functional hemispherectomy: Indications and outcome , 2010, Epilepsy Research.

[45]  Nicole Krämer,et al.  Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces , 2009, Neural Networks.

[46]  O. Delalande,et al.  Hemispherotomy and other disconnective techniques. , 2008, Neurosurgical focus.

[47]  C. Sarkar,et al.  Hemispherotomy for intractable epilepsy. , 2008, Neurology India.

[48]  N. Tandon.  Vertical parasagittal hemispherotomy: surgical procedures and clinical long-term outcomes in a population of 83 children , 2008 .

[49]  I. Jambaqué,et al.  VERTICAL PARASAGITTAL HEMISPHEROTOMY: SURGICAL PROCEDURES AND CLINICAL LONG‐TERM OUTCOMES IN A POPULATION OF 83 CHILDREN , 2007, Neurosurgery.

[50]  E. Sherman,et al.  Hemispheric Surgery in Children with Refractory Epilepsy: Seizure Outcome, Complications, and Adaptive Function , 2007, Epilepsia.

[51]  J M Freeman,et al.  Hemispherectomy for intractable unihemispheric epilepsy Etiology vs outcome , 2003, Neurology.

[52]  O. Devinsky,et al.  Neural network analysis of preoperative variables and outcome in epilepsy surgery. , 1999, Journal of neurosurgery.

[53]  J. Gates,et al.  Predicting Outcome of Anterior Temporal Lobectomy Using Simulated Neural Networks , 1998, Epilepsia.

[54]  G. Holmes,et al.  EEG prior to hemispherectomy: correlation with outcome and pathology. , 1995, Electroencephalography and clinical neurophysiology.

[55]  Jerome Engel,et al.  Outcome with respect to epileptic seizures. , 1993 .

[56]  J Gotman,et al.  Interhemispheric Relations During Bilateral Spike‐and‐Wave Activity , 1981, Epilepsia.