Berry, Brent

Abstract Objective This study investigates high‐frequency oscillations ( HFO s; 65–600 Hz) as a biomarker of epileptogenic brain and explores three barriers to their clinical translation: (1) Distinguishing pathological HFO s (path HFO ) from physiological HFO s (phys HFO ). (2) Classifying tissue under individual electrodes as epileptogenic (3) Reproducing results across laboratories. Methods We recorded HFO s using intracranial EEG ( iEEG ) in 90 patients with focal epilepsy and 11 patients without epilepsy. In nine patients with epilepsy putative phys HFO s were induced by cognitive or motor tasks. HFO s were identified using validated detectors. A support vector machine ( SVM ) using HFO features was developed to classify tissue under individual electrodes as normal or epileptogenic. Results There was significant overlap in the amplitude, frequency, and duration distributions for spontaneous phys HFO , task induced phys HFO , and path HFO , but the amplitudes of the path HFO were higher ( P < 0.0001). High gamma path HFO had the strongest association with seizure onset zone ( SOZ ), and were elevated on SOZ electrodes in 70% of epilepsy patients ( P < 0.0001). Failure to resect tissue generating high gamma path HFO was associated with poor outcomes ( P < 0.0001). A SVM classified individual electrodes as epileptogenic with 63.9% sensitivity and 73.7% specificity using SOZ as the target. Interpretation A broader range of interictal path HFO (65–600 Hz) than previously recognized are biomarkers of epileptogenic brain, and are associated with SOZ and surgical outcome. Classification of HFO s into physiological or pathological remains challenging. Classification of tissue under individual electrodes was demonstrated to be feasible. The open source data and algorithms provide a resource for future studies.

Abstract Objective . An ability to map seizure-generating brain tissue, i.e. the seizure onset zone (SOZ), without recording actual seizures could reduce the duration of invasive EEG monitoring for patients with drug-resistant epilepsy. A widely-adopted practice in the literature is to compare the incidence (events/time) of putative pathological electrophysiological biomarkers associated with epileptic brain tissue with the SOZ determined from spontaneous seizures recorded with intracranial EEG, primarily using a single biomarker. Clinical translation of the previous efforts suffers from their inability to generalize across multiple patients because of (a) the inter-patient variability and (b) the temporal variability in the epileptogenic activity. Approach . Here, we report an artificial intelligence-based approach for combining multiple interictal electrophysiological biomarkers and their temporal characteristics as a way of accounting for the above barriers and show that it can reliably identify seizure onset zones in a study cohort of 82 patients who underwent evaluation for drug-resistant epilepsy. Main results . Our investigation provides evidence that utilizing the complementary information provided by multiple electrophysiological biomarkers and their temporal characteristics can significantly improve the localization potential compared to previously published single-biomarker incidence-based approaches, resulting in an average area under ROC curve (AUC) value of 0.73 in a cohort of 82 patients. Our results also suggest that recording durations between 90 min and 2 h are sufficient to localize SOZs with accuracies that may prove clinically relevant. Significance . The successful validation of our approach on a large cohort of 82 patients warrants future investigation on the feasibility of utilizing intra-operative EEG monitoring and artificial intelligence to localize epileptogenic brain tissue. Broadly, our study demonstrates the use of artificial intelligence coupled with careful feature engineering in augmenting clinical decision making.

Abstract Objective . Automated behavioral state classification can benefit next generation implantable epilepsy devices. In this study we explored the feasibility of automated awake (AW) and slow wave sleep (SWS) classification using wide bandwidth intracranial EEG (iEEG) in patients undergoing evaluation for epilepsy surgery. Approach . Data from seven patients (age 34 ± 12 , 4 women) who underwent intracranial depth electrode implantation for iEEG monitoring were included. Spectral power features (0.1–600 Hz) spanning several frequency bands from a single electrode were used to train and test a support vector machine classifier. Main results . Classification accuracy of 97.8 ± 0.3% (normal tissue) and 89.4 ± 0.8% (epileptic tissue) across seven subjects using multiple spectral power features from a single electrode was achieved. Spectral power features from electrodes placed in normal temporal neocortex were found to be more useful (accuracy 90.8 ± 0.8%) for sleep-wake state classification than electrodes located in normal hippocampus (87.1 ± 1.6%). Spectral power in high frequency band features (Ripple (80–250 Hz), Fast Ripple (250–600 Hz)) showed comparable performance for AW and SWS classification as the best performing Berger bands (Alpha, Beta, low Gamma) with accuracy ⩾90% using a single electrode contact and single spectral feature. Significance . Automated classification of wake and SWS should prove useful for future implantable epilepsy devices with limited computational power, memory, and number of electrodes. Applications include quantifying patient sleep patterns and behavioral state dependent detection, prediction, and electrical stimulation therapies.

The ability to predict seizures may enable patients with epilepsy to better manage their medications and activities, potentially reducing side effects and improving quality of life. Forecasting epileptic seizures remains a challenging problem, but machine learning methods using intracranial electroencephalographic (iEEG) measures have shown promise. A machine-learning-based pipeline was developed to process iEEG recordings and generate seizure warnings. Results support the ability to forecast seizures at rates greater than a Poisson random predictor for all feature sets and machine learning algorithms tested. In addition, subject-specific neurophysiological changes in multiple features are reported preceding lead seizures, providing evidence supporting the existence of a distinct and identifiable preictal state.