Expert-Level Intracranial Electroencephalogram Ictal Pattern Detection by a Deep Learning Neural Network.

Background: Decision-making in epilepsy surgery is strongly connected to the interpretation of the intracranial EEG (iEEG). Although deep learning approaches have demonstrated efficiency in processing extracranial EEG, few studies have addressed iEEG seizure detection, in part due to the small number of seizures per patient typically available from intracranial investigations. This study aims to evaluate the efficiency of deep learning methodology in detecting iEEG seizures using a large dataset of ictal patterns collected from epilepsy patients implanted with a responsive neurostimulation system (RNS). Methods: Five thousand two hundred and twenty-six ictal events were collected from 22 patients implanted with RNS. A convolutional neural network (CNN) architecture was created to provide personalized seizure annotations for each patient. Accuracy of seizure identification was tested in two scenarios: patients with seizures occurring following a period of chronic recording (scenario 1) and patients with seizures occurring immediately following implantation (scenario 2). The accuracy of the CNN in identifying RNS-recorded iEEG ictal patterns was evaluated against human neurophysiology expertise. Statistical performance was assessed via the area-under-precision-recall curve (AUPRC). Results: In scenario 1, the CNN achieved a maximum mean binary classification AUPRC of 0.84 ± 0.19 (95%CI, 0.72-0.93) and mean regression accuracy of 6.3 ± 1.0 s (95%CI, 4.3-8.5 s) at 30 seed samples. In scenario 2, maximum mean AUPRC was 0.80 ± 0.19 (95%CI, 0.68-0.91) and mean regression accuracy was 6.3 ± 0.9 s (95%CI, 4.8-8.3 s) at 20 seed samples. We obtained near-maximum accuracies at seed size of 10 in both scenarios. CNN classification failures can be explained by ictal electro-decrements, brief seizures, single-channel ictal patterns, highly concentrated interictal activity, changes in the sleep-wake cycle, and progressive modulation of electrographic ictal features. Conclusions: We developed a deep learning neural network that performs personalized detection of RNS-derived ictal patterns with expert-level accuracy. These results suggest the potential for automated techniques to significantly improve the management of closed-loop brain stimulation, including during the initial period of recording when the device is otherwise naïve to a given patient's seizures.

Quantifying a frequency modulation response biomarker in responsive neurostimulation.

Objective.Responsive neurostimulation (RNS) is an effective treatment for controlling seizures in patients with drug-resistant focal epilepsy who are not suitable candidates for resection surgery. A lack of tools for detecting and characterizing potential response biomarkers, however, contributes to a limited understanding of mechanisms by which RNS improves seizure control. We developed a method to quantify ictal frequency modulation, previously identified as a biomarker of clinical responsiveness to RNS.Approach.Frequency modulation is characterized by shifts in power across spectral bands during ictal events, over several months of neurostimulation. This effect was quantified by partitioning each seizure pattern into segments with distinct spectral content and measuring the extent of change from the baseline distribution of spectral content using the squared earth mover's distance.Main results.We analyzed intracranial electroencephalography data from 13 patients who received RNS therapy, six of whom exhibited frequency modulation on expert evaluation. Patients in the frequency modulation group had, on average, significantly larger and more sustained changes in their squared earth mover's distances (mean = 13.97 × 10-3± 1.197 × 10-3). In contrast, those patients without expert-identified frequency modulation exhibited statistically insignificant or negligible distances (mean = 4.994 × 10-3± 0.732 × 10-3).Significance.This method is the first step towards a quantitative, feedback-driven system for systematically optimizing RNS stimulation parameters, with an ultimate goal of truly personalized closed-loop therapy for epilepsy.

Ictal Onset Signatures Predict Favorable Outcomes of Laser Thermal Ablation for Mesial Temporal Lobe Epilepsy.

Background: Laser interstitial thermal therapy (LiTT) has emerged as a minimally invasive option for surgical treatment of refractory epilepsy. However, LiTT of the mesial temporal (MT) structures is still inferior to anterior temporal lobectomy (ATL) in terms of postoperative outcome. In this pilot study, we identify intracranial EEG (iEEG) biomarkers that distinguish patients with favorable outcome from those with poor outcome after MT LiTT. Methods: We performed a retrospective review of 9 adult refractory epilepsy patients who underwent stereotactic electroencephalography (sEEG) followed by LiTT of MT structures. Their iEEG was retrospectively reviewed in both time and frequency domains. Results: In the time-domain, the presence of sustained 14-30 Hz in MT electrodes coupled with its absence from extra-MT electrodes at ictal onset was highly correlated with favorable outcomes, whereas the appearance of sustained 14-30 Hz or >30 Hz activity in extra-MT sites was negatively correlated to favorable outcomes. In the frequency domain, a declining spectral phase, beginning at the high frequency range (>14 Hz) at ictal onset and following a smooth progressive decline toward lower frequencies as the seizure further evolved, was positively correlated with improved outcomes. On the contrary, low frequency (<14 Hz) patterns and "crescendo-decrescendo" patterns with an early increasing frequency component at ictal onset that reaches the high-beta and low gamma bands before decreasing smoothly, were both correlated with poor surgical outcomes. Conclusions: This pilot study demonstrates the first evidence that iEEG analysis can provide neurophysiological markers for successful MT LiTT and therefore we strongly advocate for systematic sEEG investigations before offering MT LiTT to TLE and MTLE patients.

Neurostimulant use is associated with improved survival in comatose patients after cardiac arrest regardless of electroencephalographic substrate.

AIM: Identify EEG patterns that predict or preclude favorable response in comatose post-arrest patients receiving neurostimulants. METHODS: We examined a retrospective cohort of consecutive electroencephalography (EEG)-monitored comatose post-arrest patients. We classified the last day of EEG recording before neurostimulant administration based on continuity (continuous/discontinuous), reactivity (yes/no) and malignant patterns (periodic discharges, suppression burst, myoclonic status epilepticus or seizures; yes/no). In subjects who did not receive neurostimulants, we examined the last 24h of available recording. For our primary analysis, we used logistic regression to identify EEG predictors of favorable response to treatment (awakening). RESULTS: In 585 subjects, mean (SD) age was 57 (17) years and 227 (39%) were female. Forty-seven patients (8%) received a neurostimulant. Neurostimulant administration independently predicted improved survival to hospital discharge in the overall cohort (adjusted odds ratio (aOR) 4.00, 95% CI 1.68-9.52) although functionally favorable survival did not differ. No EEG characteristic predicted favorable response to neurostimulants. In each subgroup of unfavorable EEG characteristics, neurostimulants were associated with increased survival to hospital discharge (discontinuous background: 44% vs 7%, P=0.004; non-reactive background: 56% vs 6%, P<0.001; malignant patterns: 63% vs 5%, P<0.001). CONCLUSION: EEG patterns described as ominous after cardiac arrest did not preclude survival or awakening after neurostimulant administration. These data are limited by their observational nature and potential for selection bias, but suggest that EEG patterns alone should not affect consideration of neurostimulant use.