Dataset Information

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy.

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.

SUBMITTER: Varatharajah Y

PROVIDER: S-EPMC6108188 | biostudies-literature | 2018 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy.

Varatharajah Yogatheesan Y Berry Brent B Cimbalnik Jan J Kremen Vaclav V Van Gompel Jamie J Stead Matt M Brinkmann Benjamin B Iyer Ravishankar R Worrell Gregory G

Journal of neural engineering 20180601 4

<h4>Objective</h4>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, pr ...[more]

PMID: 29855436

Similar Datasets

Project description:EEG source imaging is becoming widely used for the evaluation of medically refractory focal epilepsy. The validity of EEG source imaging has been established in several studies comparing source imaging to the surgical resection cavity and subsequent seizure freedom. We present a cohort of 87 patients and compare EEG source imaging of both ictal and interictal scalp EEG to the seizure onset zone on intracranial EEG. Concordance of EEG source imaging with intracranial EEG was determined on a sublobar level and was quantified by measuring the distance between the source imaging result and the centroid of the active seizure onset zone electrodes. The EEG source imaging results of a subgroup of 26 patients with high density 76-channel EEG were compared with the localization of three experienced epileptologists. Of 87 patients, 95% had at least one analysis concordant with intracranial EEG and 74% had complete concordance. There was a higher rate of complete concordance in temporal lobe epilepsy compared to extratemporal (89.3 and 62.8%, respectively, P = 0.015). Of the total 282 analyses performed on this cohort, higher concordance was also seen in temporal discharges (95%) compared to extratemporal (77%) (P = 0.0012), but no difference was seen comparing high-density EEG with standard (32-channel) EEG. Subgroup analysis of ictal waveforms showed greater concordance for ictal spiking, compared with rhythmic activity, paroxysmal fast activity, or obscured onset. Median distances from the dipole and maximum distributed source to a centroid of seizure onset zone electrodes were 30.0 and 32.5 mm, respectively, and the median distances from dipole and maximum distributed source to nearest seizure onset zone electrode were 22.8 and 21.7, respectively. There were significantly shorter distances in ictal spiking. There were shorter distances in patients with Engel Class 1 outcome from surgical resection compared to patients with worse outcomes. For the subgroup of 26 high-density EEG patients, EEG source localization had a significantly higher concordance (92% versus 65%), sensitivity (57% versus 35%) and positive predictive value (60% versus 36%) compared with epileptologist localization. Our study demonstrates good concordance between ictal and interictal source imaging and intracranial EEG. Temporal lobe discharges have higher concordance rates than extratemporal discharges. Importantly, this study shows that source imaging has greater agreement with intracranial EEG than visual review alone, supporting its role in surgical planning.

Project description:Aim: In neuroscience research, data are quite often characterized by an imbalanced distribution between the majority and minority classes, an issue that can limit or even worsen the prediction performance of machine learning methods. Different resampling procedures have been developed to face this problem and a lot of work has been done in comparing their effectiveness in different scenarios. Notably, the robustness of such techniques has been tested among a wide variety of different datasets, without considering the performance of each specific dataset. In this study, we compare the performances of different resampling procedures for the imbalanced domain in stereo-electroencephalography (SEEG) recordings of the patients with focal epilepsies who underwent surgery. Methods: We considered data obtained by network analysis of interictal SEEG recorded from 10 patients with drug-resistant focal epilepsies, for a supervised classification problem aimed at distinguishing between the epileptogenic and non-epileptogenic brain regions in interictal conditions. We investigated the effectiveness of five oversampling and five undersampling procedures, using 10 different machine learning classifiers. Moreover, six specific ensemble methods for the imbalanced domain were also tested. To compare the performances, Area under the ROC curve (AUC), F-measure, Geometric Mean, and Balanced Accuracy were considered. Results: Both the resampling procedures showed improved performances with respect to the original dataset. The oversampling procedure was found to be more sensitive to the type of classification method employed, with Adaptive Synthetic Sampling (ADASYN) exhibiting the best performances. All the undersampling approaches were more robust than the oversampling among the different classifiers, with Random Undersampling (RUS) exhibiting the best performance despite being the simplest and most basic classification method. Conclusions: The application of machine learning techniques that take into consideration the balance of features by resampling is beneficial and leads to more accurate localization of the epileptogenic zone from interictal periods. In addition, our results highlight the importance of the type of classification method that must be used together with the resampling to maximize the benefit to the outcome.

Dataset Information

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy.

Publications

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets