Noninvasive wearable devices have great potential to aid the management of epilepsy, but these devices must have robust signal quality, and patients must be willing to wear them for long periods of time. Automated machine learning classification of wearable biosensor signals requires quantitative measures of signal quality to automatically reject poor‐quality or corrupt data segments. In this study, commercially available wearable sensors were placed on patients with epilepsy undergoing in‐hospital or in‐home electroencephalographic (EEG) monitoring, and healthy volunteers. Empatica E4 and Biovotion Everion were used to record accelerometry (ACC), photoplethysmography (PPG), and electrodermal activity (EDA). Byteflies Sensor Dots were used to record ACC and PPG, the Activinsights GENEActiv watch to record ACC, and Epitel Epilog to record EEG data. PPG and EDA signals were recorded for multiple days, then epochs of high‐quality, marginal‐quality, or poor‐quality data were visually identified by reviewers, and reviewer annotations were compared to automated signal quality measures. For ACC, the ratio of spectral power from 0.8 to 5 Hz to broadband power was used to separate good‐quality signals from noise. For EDA, the rate of amplitude change and prevalence of sharp peaks significantly differentiated between good‐quality data and noise. Spectral entropy was used to assess PPG and showed significant differences between good‐, marginal‐, and poor‐quality signals. EEG data were evaluated using methods to identify a spectral noise cutoff frequency. Patients were asked to rate the usability and comfort of each device in several categories. Patients showed a significant preference for the wrist‐worn devices, and the Empatica E4 device was preferred most often. Current wearable devices can provide high‐quality data and are acceptable for routine use, but continued development is needed to improve data quality, consistency, and management, as well as acceptability to patients.

The ability to forecast seizures minutes to hours in advance of an event has been verified using invasive EEG devices, but has not been previously demonstrated using noninvasive wearable devices over long durations in an ambulatory setting. In this study we developed a seizure forecasting system with a long short-term memory (LSTM) recurrent neural network (RNN) algorithm, using a noninvasive wrist-worn research-grade physiological sensor device, and tested the system in patients with epilepsy in the field, with concurrent invasive EEG confirmation of seizures via an implanted recording device. The system achieved forecasting performance significantly better than a random predictor for 5 of 6 patients studied, with mean AUC-ROC of 0.80 (range 0.72–0.92). These results provide the first clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many patients with epilepsy.

No abstract

Objective:This study aims to evaluate the role of scalp electroencephalography (EEG; ictal and interictal patterns) in predicting resective epilepsy surgery outcomes. We use the data to further develop a nomogram to predict seizure freedom.Methods:We retrospectively reviewed the scalp EEG findings and clinical data of patients who underwent surgical resection at three epilepsy centers. Using both EEG and clinical variables categorized into 13 isolated candidate predictors and 6 interaction terms, we built a multivariable Cox proportional hazards model to predict seizure freedom 2 years after surgery. Harrell's step-down procedure was used to sequentially eliminate the least-informative variables from the model until the change in the concordance index (c-index) with variable removal was less than 0.01. We created a separate model using only clinical variables. Discrimination of the two models was compared to evaluate the role of scalp EEG in seizure-freedom prediction.Results:Four hundred seventy patient records were analyzed. Following internal validation, the full Clinical + EEG model achieved an optimism-corrected c-index of 0.65, whereas the c-index of the model without EEG data was 0.59. The presence of focal to bilateral tonic-clonic seizures (FBTCS), high preoperative seizure frequency, absence of hippocampal sclerosis, and presence of nonlocalizable seizures predicted worse outcome. The presence of FBTCS had the largest impact for predicting outcome. The analysis of the models' interactions showed that in patients with unilateral interictal epileptiform discharges (IEDs), temporal lobe surgery cases had a better outcome. In cases with bilateral IEDs, abnormal magnetic resonance imaging (MRI) predicted worse outcomes, and in cases without IEDs, patients with extratemporal epilepsy and abnormal MRI had better outcomes.