Synchrony is a robust iEEG biomarker for antiseizure medication load in epileptic patients

bioRxiv (Cold Spring Harbor Laboratory) · 2026-01-12 · 1 citations

With new, minimally invasive continuous EEG and wearable monitoring systems for epilepsy nearing regulatory approval, there is a rush to determine how to make these devices most useful to patients. One application is to track biomarkers of antiseizure medication (ASM) levels to help manage seizure risk and side effects. In this paper, we validate one such biomarker, phase synchronization, during medication taper and presurgical evaluation in a cohort of 80 consecutive patients recorded with intracranial EEG (iEEG) at the University of Pennsylvania. While previous investigators have demonstrated that synchrony is negatively correlated with ASM load at the resolution of 1 day, we hypothesize that synchrony continuously tracks and can predict ASM load on a clinically useful time scale. We test this hypothesis using a pharmacokinetic model generating continuous ASM load values previously published by our group and correlate it with continuous synchrony values derived from the iEEG. We use a linear mixed effect model to examine the relationship between ASM load, synchrony, vigilance, and other time dependent factors. We use dominance analysis to rank the relative importance of predictors based on their influence on ASM load. We find that synchrony not only can predict ASM load but is also the most significant predictor. Our study highlights the potential of synchrony as a biomarker for ASM load, and its utility in an ambulatory implantable device that can alert patients to conditions lowering their medications (e.g., adherence, drug interactions, generic change, pregnancy, etc.) or potential medication toxicity. We propose that measures like synchrony, packaged in an appropriate interface, could bring substantial value to ambulatory epilepsy management devices.

An Implantable Device that Converses with Patients and Learns to Co-Manage Epilepsy

medRxiv · 2026-01-27 · 1 citations

One-third of the world's 70 million people with epilepsy have seizures that are not controlled by medication; and implantable devices are an exciting option for treatment. These devices improve seizure control and can detect impending attacks, missed medication, and impaired cognition. Unfortunately, they have no way to share this information with their hosts in real-time - a limitation common to most medical devices. This is a missed opportunity for implants and wearables to learn from patients, focus on what matters most to them, and teach them how their behavior affects their health. Here, we present a device platform that converses with patients and learns to co-manage epilepsy. The inpatient prototype links scalp and intracranial EEG (electroencephalograms) to secure large language models that communicate freely and bidirectionally with their hosts through a smartphone app. An AI agent ingests biomarkers of sleep, medication level, cognition, and seizure risk extracted from brain activity. It converses with patients to inform them of clinical events and physiological trends, records their symptoms, responses, and behaviors, and automatically retrains itself to improve performance. Both patients and the AI agent can initiate conversations to teach each other and personalize interactions. We demonstrate this platform in 13 patients undergoing inpatient video-EEG monitoring for epilepsy and validate its performance. Algorithms for detecting seizures optimized their precision over several days without expert intervention - in contrast to the months of iterative, in-person physician programming currently required. Patients responded positively to messages regarding sleep, cognition, and seizure risk while rating the system as highly usable. The platform includes several safeguards, including a system for further algorithm fine-tuning using efficient expert review, and features that ensure data security and regulate communication content. Further work will link other biosensors to measure behavior, improve performance, and optimize therapeutic stimulation. We propose this system as a scalable platform for medical devices that can rapidly adapt to patient and provider needs; one that is broadly adaptable to improving care for many medical conditions.

Multi-expert consensus annotations of spontaneous and stimulation-induced seizures in stereotactic EEG

medRxiv · 2026-01-21 · 1 citations

Automated seizure detection and localization from intracranial EEG requires validated benchmark datasets with expert annotations, yet existing open datasets lack multi-expert consensus annotations and exclude stimulation-induced seizures. We present stereotactic EEG recordings from 83 seizures (46 spontaneous, 37 stimulation-induced) across 32 patients (19 from the University of Pennsylvania, 13 from the Children's Hospital of Philadelphia) with drug-resistant epilepsy. Three board-certified epileptologists independently annotated each seizure for onset time, onset channels, and channels seizing at 10 seconds post-onset using a standardized protocol. Consensus annotations were determined through majority voting. Inter-rater agreement was κ = 0.64 for onset channels and κ = 0.62 for spread channels. Individual rater agreement with consensus was κ = 0.81 for onset and κ = 0.80 for spread. Agreement metrics did not differ between spontaneous and stimulation-induced seizures. All data follow Brain Imaging Data Structure (BIDS) standards and include electrode localizations, patient demographics, and clinical outcomes. This dataset enables the validation of seizure onset and spread detection and localization against human expert performance and supports comparative analysis of seizure networks across spontaneous and stimulation-induced seizures.

Unsupervised seizure annotation and detection with neural dynamic divergence

medRxiv · 2026-02-17 · 1 citations

Annotating seizure onset and spread in intracranial EEG is essential for epilepsy surgical planning, yet manual annotation is unreliable and cannot scale to large datasets. We introduce Neural Dynamic Divergence (NDD), an unsupervised framework that detects seizure activity by measuring deviation from patient-specific baseline neural dynamics using autoregressive models. NDD requires no labeled training data and adapts to individual patients, channels, and brain states. Validating against expert consensus annotations from 46 seizures, NDD achieves human-level agreement ( ϕ = 0.58 vs. inter-rater ϕ = 0.64) and outperforms existing algorithms on 1,019 seizures with soft labels (AUROC = 0.87). We demonstrate clinical utility by automatically annotating 2,017 seizures, revealing that seizure spread patterns distinguish epilepsy subtypes and predict surgical outcomes. NDD also generalizes to continuous ICU scalp EEG monitoring (AUROC = 0.77). We provide NDD as an open-source Python package to enable scalable seizure annotation across research centers.

Low Frequency Stimulation and Seizure Induction in Pediatric and Young Adult Patients With Drug Resistant Epilepsy Undergoing Stereoelectroencephalography

Journal of Clinical Neurophysiology · 2026-03-13

PURPOSE: Describe the tolerability and outcome of direct brain stimulation for seizure induction in children and young adults undergoing intracranial electroencephalography. METHODS: Patients received low frequency stimulation (LFS) consisting of 30 seconds of 1 Hz bipolar, biphasic brain stimulation. A subset also received high frequency stimulation (HFS) for clinical purposes. Clinical data regarding epilepsy characteristics, stimulation, and outcomes were collected. RESULTS: Fifty-four patients (aged 1.8 to 23.4 years) with pediatric onset epilepsy were enrolled at Children's Hospital of Philadelphia and the Hospital of the University of Pennsylvania. Side effects during LFS included focal sensation (22%) and motor responses (41%). Non-seizure electrographic abnormalities were noted during stimulation in 87% of patients. During LFS, typical clinical seizures were seen in 24% of patients. During HFS (50 Hz), 58% of 36 patients had seizures (71% typical semiology). In 30% of patients, stimulated typical clinical seizures identified a contact not previously identified as part of the seizure onset zone. Of 43 patients who went on to have resection, ablation, or neuromodulation, 39 patients had ≥12 months of follow-up. Although 84% of 19 patients with stimulated typical clinical seizures had a good outcome, 60% of 20 patients with atypical or no clinical seizures during stimulation had good outcomes (P = 0.09). CONCLUSIONS: LFS is well tolerated in pediatric and young adult DRE patients and in one fourth of cases identifies potential additional nodes of the seizure network. These data, consistent with adult studies, affirm that LFS has a role complementing HFS in evaluating pediatric DRE patients undergoing stereoelectroencephalography.

How Much Does the Reduced EEG Montage Matter for Seizure Detection?: A Large-Cohort Simulation Study

medRxiv · 2026-05-06

Abstract Importance Implantable sub-scalp EEG systems with a small number of channels have emerged as promising solutions for long-term seizure monitoring in patients with epilepsy. How seizure detection performance varies by montage configuration is unknown. Objective To quantify how automated seizure detection performance differs between full and reduced montages, and how these differences vary by epilepsy characteristics. Design Retrospective cross-sectional study. Setting Single-center at the Hospital of the University of Pennsylvania Epilepsy Monitoring Unit (EMU). Participants EEG data from 2281 consecutive EMU admissions between January 2017 and December 2024 were screened. Admissions with at least one annotated seizure and one interictal clip ≥20 minutes from any seizure were included. Exposure Computational simulation of published sub-scalp device montages using standard 10-20 EEG channels. Main Outcomes and Measures The primary outcome was event-based F1 scores evaluated for three published seizure detectors—a one-class support vector machine (SVM), a convolutional neural network (SPaRCNet), and a long short-term memory autoregressive model (NDD)—across montages. Results A total of 466 admissions from 436 patients (mean [SD] age, 39.0 [14.4] years; 54.4% female) met inclusion criteria, comprising 1683 seizures and 1527 interictal clips. SPaRCNet achieved the highest performance (mean [SD] F1, 0.61 [0.30]), followed by NDD (0.56 [0.28]) and SVM (0.39 [0.25]). Performance decreased by at most 0.09 with reduced montages, depending on detectors. Patient factors accounted for the largest proportion of performance variance (29.2%), followed by detector choice (10.3%). Montage effects were minimal (0.4%), despite variation in optimal montage across detectors. Reduced-montage performance correlated moderately to highly with full-montage performance (ρ=0.29–0.73), suggesting full-montage performance could help identify patients suitable for sub-scalp devices. Missed seizures were associated with lower amplitude and bandpowers than detected seizures, though they remained distinguishable from interictal data. Conclusions and Relevance Automated seizure detection achieved comparable accuracy, with only modest reductions, under simulated reduced montages. Performance differences were driven primarily by detector- and patient-level factors rather than montage. These findings support the feasibility of accurately detecting seizures with published sub-scalp devices and highlight the need for improved algorithms to optimize performance. Key Findings Question How do automated seizure detection algorithms perform with reduced-channel montages simulating published sub-scalp devices? Findings In this retrospective cross-sectional study, seizure detection performance decreased only modestly on reduced montages relative to the full montage (absolute F1 change −0.09 to 0.014), whereas patient- and algorithm-level factors accounted for most of performance variance (29.2% and 10.3%, respectively). Algorithm performance on full montage recordings was moderately correlated with performance on reduced channel montages (ρ=0.29–0.73). Meaning Reduced-montage sub-scalp devices are promising for ultra-long-term monitoring, but best performance requires selecting the right patients. Patient-specific seizure detectors will likely be required to optimize long-term performance.

Impact of antiseizure medication taper on electroencephalographic dynamics in focal epilepsy: A stereoelectroencephalographic study

Epilepsia · 2026-02-16

OBJECTIVE: Tapering of the antiseizure medication dosage in the epilepsy monitoring unit can provoke seizures, but its effects on seizure dynamics remain poorly characterized. This study addresses three questions: (1) Does antiseizure medication tapering influence spatiotemporal dynamics of seizures? (2) Does the tapering rate affect these dynamics? (3) Does tapering have a similar effect on interictal epileptic discharges as it does on seizures? METHODS: Patients with drug-resistant epilepsy undergoing stereoelectroencephalographic (stereo-EEG) presurgical evaluations at Duke University Medical Center (n = 104) and the Montreal Neurological Institute and Hospital (n = 80) were screened. We included patients in whom the antiseizure medication dosage was tapered from the highest daily dosage (high dosage) to ≤ 50% (low dosage) during stereo-EEG monitoring, and at least one seizure from the same focus was recorded in both conditions. Using an intrapatient design, we compared seizure onset-zone, onset pattern, and propagation dynamics between the two conditions. Given the intrinsic seizure variability, comparisons were made between same-dosage and cross-dosage seizure pairs. We further assessed effects of tapering rates and examined the characteristics of interictal epileptiform discharges. RESULTS: Among 30 patients, the proportion of channels in the seizure onset zone did not differ between high-dosage and low-dosage conditions (7.25% vs. 8.95%, p = .50, d = -.04). Similarly, no differences were observed in the overlap ratio of seizure-onset regions (62% vs. 64%, p = .72, d = -.01), or the cross-correlation of seizure-onset patterns (.36 vs. .35, p = .54, d = .04) when comparing same-dosage versus cross-dosage seizure pairs. Conversely, seizures at low dosage involved more channels (40.71% vs. 81.49%, p = .001, d = -.39) and lasted longer (33.36 s vs. 74.30 s, p < .01, d = -.47). Tapering rate did not affect seizure dynamics. The mean interictal epileptiform discharge rate and number of propagation channels also remained unchanged. SIGNIFICANCE: Despite seizure exacerbation during antiseizure medication tapering, seizure-onset location remained stable. This supports the robustness of seizure-based localization even under reduced medication levels and rapid tapering regimens.

Optimization of cortico-cortical spectral response analysis parameters for seizure onset zone localization

Clinical Neurophysiology · 2026-03-17

• Specific features of cortico-cortical spectral responses (CCSRs) may hold more localizing potential for seizure onset zone. • Spectral power in defined time–frequency zones was evaluated for correlation with clinical annotations of epileptogenicity. • High frequency, slow transient responses may be a biomarker of the epileptogenic network. While cortico-cortical spectral responses (CCSRs) have shown potential for seizure onset zone (SOZ) localization, it is unclear which features of the CCSR are most localizing, limiting their use as potential biomarkers of the SOZ. Single-pulse electrical stimulation (SPES) was performed during intracranial EEG (sEEG and ECoG) monitoring in 27 patients, and CCSRs were calculated. We quantified significant increases and decreases in the CCSR and then segmented the CCSRs into 11 time–frequency zones (TFZs). We compared brain regions with the most significant responses in each TFZ to the hypothesized SOZ to determine the localization potential of individual TFZs. We found that the contacts having the strongest responses in the TFZ spanning the high gamma frequency band (50–250 Hz) and the N2 time interval (50–500 ms) were more related to the SOZ than other TFZs. These findings suggest that changes in high gamma power 50–500 ms following SPES hold the greatest SOZ localizing potential and may be optimal parameters for investigating the CCSR for biomarkers of the SOZ. Optimal interpretation of CCSRs may lead to improved SOZ localization and more favorable treatment outcomes for those with drug-resistant epilepsy.

Association between Interictal Spike Rate and Seizure Frequency in a Large Epilepsy Cohort

medRxiv · 2026-02-26

ABSTRACT Importance Tracking and predicting seizure frequency in patients with epilepsy is important for prognostication and therapy management. Interictal spikes have been proposed as a biomarker of seizure burden, but their association with seizure frequency has not been well quantified across epilepsy subtypes. Objective To measure the association between spike rate and seizure frequency and how this varies by epilepsy subtype. Design, Setting and Participants We studied 3,614 consecutive routine outpatient EEGs from 3,245 patients with epilepsy. A validated automated detector (SpikeNet2) estimated spike frequency. Validated large language models performed natural language processing on outpatient clinic notes to extract seizure frequency and epilepsy subtype. Main Outcomes and Measures Spearman correlation between spike frequency (spikes/hour) and seizure frequency (seizures/month) for all patients with epilepsy and for patients with generalized epilepsy, temporal lobe epilepsy, and frontal lobe epilepsy. Results Overall, spike frequency was modestly associated with seizure frequency (N = 3,245, ρ = 0.11, p &lt; 0.001). Significant positive associations were observed in generalized epilepsy (N = 625, ρ = 0.23, Bonferroni-adjusted p &lt; 0.001) and temporal lobe epilepsy (N = 834, ρ = 0.12, p = 0.0013), but not in frontal lobe epilepsy (N = 263, ρ = 0.11, p = 0.22). Conclusions and Relevance In this large outpatient cohort, higher interictal spike rates on routine EEG were associated with higher seizure frequencies, with the strongest relationship observed in generalized epilepsy. These associations support interictal spike rate as a quantitative EEG marker of seizure burden. Spike rate may have clinical utility for risk stratification at diagnosis and for monitoring longitudinal changes in seizure burden in response to therapy.

Intrinsic and extrinsic connectivity of the seizure onset zone at rest and during stimulation

medRxiv · 2026-03-02

, defined as the brain areas whose removal causes cessation of seizures. Altered network connectivity has emerged as a candidate biomarker of the epileptogenic zone, but how connectivity is altered in the epileptogenic zone remains uncertain, with prior studies reporting inconsistent results. We hypothesized that a difference in intrinsic versus extrinsic connectivity of the epileptogenic zone may explain prior discrepant findings. We studied a multicenter cohort of adult and pediatric patients who underwent intracranial EEG recording and brain stimulation as part of epilepsy surgery planning. We measured spontaneous connectivity using Pearson correlation and perturbational connectivity using stimulation evoked potentials, modeling the connectivity according to the location of contacts in relation to the seizure onset zone (SOZ) while controlling for inter-electrode distance. We analyzed 79 patients (37 adults, 42 children). For both adult and pediatric patients, resting connectivity was higher within compared to outside the SOZ, but resting connectivity between SOZ and non-SOZ contacts was reduced. Stimulation connectivity followed a similar pattern, with elevated within-SOZ connectivity but reduced connectivity between SOZ and non-SOZ. The results support the hypothesis that the epileptogenic zone is disconnected from the rest of the brain but intrinsically hyperconnected. This result helps reconcile prior inconsistencies across studies, aligns with the results of basic science studies, and suggests that future translational work should model this heterogeneous pattern to increase the yield of using connectivity to localize the epileptogenic zone.