Assessing epilepsy-related autonomic manifestations: Beyond cardiac and respiratory investigations

Children and Young Adults with Epilepsy Exhibit an Interictal Autonomic Dysfunction: A Prospective Exploratory Study

Dysautonomic disorders are an increasingly studied group of conditions, either as isolated diseases or associated with other neurological disorders. There is growing interest in understanding how dysautonomia affects people with epilepsy, who may report autonomic symptoms before, during and after seizures. Furthermore, autonomic abnormalities appear to play a role in sudden unexpected death in epilepsy, likely contributing to the increased mortality rate described in epilepsy. To better understand the association between epilepsy and dysautonomia, we explored electrochemical skin conductance in a group of 18 children and young adults with epilepsy compared to 15 age- and sex-matched healthy controls by the SudoscanTM test. We found a significant difference in terms of electrochemical skin conductance, suggesting that people with epilepsy suffer significantly reduced conductance in small nerve fibers. Within patients, values were significantly different according to the type of epilepsy and to neuroimaging results, with lower conductance values in epilepsies of unknown origin and in patients with morphological abnormalities of the brain. Using a non-invasive test, we identified altered conductance of small sympathetic nerve fibers in children and young adults with epilepsy, suggesting underlying dysautonomia. Further studies are needed to investigate this association and to clarify its neurobiological substrates.

Hypertension and other vascular risk factors in patients with functional seizures

OBJECTIVE

Recent literature has suggested that functional seizures are associated with an elevated risk for vascular disease and mortality. We investigated the prevalence of risk factors for vascular disease in patients who were admitted to the epilepsy monitoring unit.

METHODS

Patients who were admitted to the epilepsy monitoring unit and received a definitive diagnosis of either functional seizures or epilepsy were identified. Data collected included demographic, clinical characteristics, medication list, comorbidities, and scheduled blood pressure measurements that occurred every 12 h during the admission. The mean blood pressures were calculated and if they were above the American College of Cardiology and the American Heart Association guideline cutoff of 130/80 mm Hg or the patient had a documented history of hypertension the patient was counted as having the condition. A multiple logistic regression model was developed to evaluate the independent association of the patient's diagnosis (i.e., epilepsy or functional seizures) and vascular risk factors that controlled for the number of blood pressure measurements, age, sex, and if the patient was taking antihypertensive medications.

RESULTS

270 patients were included in this study of which 147 patients had epilepsy and 123 had functional seizures. Among those with functional seizures, 57.72 % had either a history of hypertension or a mean blood pressure above 130/80 compared to 38.78 % of those with epilepsy (p = 0.0022). In addition, 30.89 % of functional seizures patients had hyperlipidemia and 63.41 % were obese. The logistic regression model indicated that functional seizures were independently associated with high blood pressure (OR: 2.47, 95 % CI 1.10-5.69), hyperlipidemia (OR: 3.38, 95 % CI 1.35-8.86), and obesity (OR: 4.25, 95 % CI 2.22-8.36) compared to those with epilepsy. There was no significant difference in the prevalence of diabetes (OR: 0.81, 95 % CI 0.24-2.77) or current tobacco use (OR: 1.04, 95 % CI 0.48-2.25) between the groups.

SIGNIFICANCE

Patients with functional seizures had an elevated prevalence of several vascular risk factors. These findings may partially account for complications associated with functional seizures and have implications related to their pathophysiology.

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

This work presents SeizFt-a novel seizure detection framework that utilizes machine learning to automatically detect seizures using wearable SensorDot EEG data. Inspired by interpretable sleep staging, our novel approach employs a unique combination of data augmentation, meaningful feature extraction, and an ensemble of decision trees to improve resilience to variations in EEG and to increase the capacity to generalize to unseen data. Fourier Transform (FT) Surrogates were utilized to increase sample size and improve the class balance between labeled non-seizure and seizure epochs. To enhance model stability and accuracy, SeizFt utilizes an ensemble of decision trees through the CatBoost classifier to classify each second of EEG recording as seizure or non-seizure. The SeizIt1 dataset was used for training, and the SeizIt2 dataset for validation and testing. Model performance for seizure detection was evaluated using two primary metrics: sensitivity using the any-overlap method (OVLP) and False Alarm (FA) rate using epoch-based scoring (EPOCH). Notably, SeizFt placed first among an array of state-of-the-art seizure detection algorithms as part of the Seizure Detection Grand Challenge at the 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). SeizFt outperformed state-of-the-art black-box models in accurate seizure detection and minimized false alarms, obtaining a total score of 40.15, combining OVLP and EPOCH across two tasks and representing an improvement of ~30% from the next best approach. The interpretability of SeizFt is a key advantage, as it fosters trust and accountability among healthcare professionals. The most predictive seizure detection features extracted from SeizFt were: delta wave, interquartile range, standard deviation, total absolute power, theta wave, the ratio of delta to theta, binned entropy, Hjorth complexity, delta + theta, and Higuchi fractal dimension. In conclusion, the successful application of SeizFt to wearable SensorDot data suggests its potential for real-time, continuous monitoring to improve personalized medicine for epilepsy.