Goals of automated detection of epileptic seizures using wearable devices include objective documentation of seizures, prevention of sudden unexpected death in epilepsy (SUDEP) and seizure-related injuries, obviating both the unpredictability of seizures and potential social embarrassment, and finally to develop seizure-triggered on-demand therapies. Automated seizure detection devices are based on the analysis of EEG signals (scalp-EEG, subcutaneous EEG and intracranial EEG), of motor manifestations of seizures (surface EMG, accelerometry), and of physiologic autonomic changes caused by seizures (heart and respiration rate, oxygen saturation, sweat secretion, body temperature). While the detection of generalized tonic-clonic and of focal to bilateral tonic-clonic seizures can be achieved with high sensitivity and low false alarm rates, the detection of focal seizures is still suboptimal, especially in the everyday ambulatory setting. Multimodal seizure detection devices in general provide better performance than devices based on single measurement parameters. Long-term use of seizure detection devices in home environments helps to improve the accuracy of seizure diaries and to reduce seizure-related injuries, while evidence for prevention of SUDEP is still lacking. Automated seizure detection devices are generally well accepted by patients and caregivers.

Accurate seizure documentation is essential in guiding treatment decisions in epilepsy but still heavily relies on highly subjective and sometimes unreliable patient reports. We report a case of medically refractory mesial temporal lobe epilepsy where subcutaneous EEG revealed persistence of seizures following add‐on antiseizure medication despite the patient's self‐report of seizure freedom. Thus, ultralong‐term EEG subcutaneous monitoring provided valuable information on medical refractoriness and supported the decision to proceed to surgical intervention. Subcutaneous EEG monitoring was continued after resective surgery and has shown no further seizures to this date. To our knowledge, this is the first reported case utilizing subcutaneous EEG for objective seizure documentation both pre‐ and post‐surgery. Plain Language Summary: Making the right treatment decisions depends on knowing the seizure frequency of a person with epilepsy, but patients' reports are often inaccurate. In our case, we describe a patient in which seizures were only detected because of a small electrode implanted under the skin to record brain activity (subcutaneous EEG). Based on this information, the patient received brain surgery, and the device was left in place after surgery, showing no further seizures. To our knowledge, this is the first reported case where this type of EEG device was used to track seizures both before and after epilepsy surgery.

To quantify short-term antiseizure medication (ASM) effects on interictal epileptiform discharge (IED) rates during long-term video-EEG monitoring (LT-VEM) in idiopathic generalized epilepsy (IGE) using pharmacokinetic modeling and automated IED detection. In a retrospective cohort of 38 IGE patients undergoing LT-VEM with ASM tapering (January 2010-December 2024), we applied AI-based hybrid IED detection and first-order pharmacokinetic modeling to calculate hourly normalized IED rates and cumulative DDD-normalized ASM drug-load profiles. We compared each patient's IED rate between their lowest- and highest-load 24-hour windows using paired t-tests in the full cohort and in a benzodiazepine-naïve subgroup. IED rate was reduced by a median 63.6% (IQR 17.8-92.3%) between each patient's lowest- and highest-load 24-hour windows (p < 0.001; Cohen's d = - 0.81, 95% CI - 1.24 to - 0.37). The effect was preserved in the benzodiazepine-naïve subgroup (n = 18; p = 0.007; Cohen's d = - 0.84, 95% CI - 1.48 to - 0.19), ruling out acute benzodiazepine-induced effects as the driver. Pharmacokinetic modeling combined with automated IED quantification demonstrates a large, robust short-term ASM effect on IED rates in IGE across a multi-day monitoring scale. These findings support IED quantification as a candidate neurophysiological biomarker for individualized treatment response assessment.