Artificial intelligence system, based on mjn-SERAS algorithm, for the early detection of seizures in patients with refractory focal epilepsy: A cross-sectional pilot study.

Around one-third of epilepsy patients develop drug-resistant seizures; early detection of seizures could help improve safety, reduce patient anxiety, increase independence, and enable acute treatment. In recent years, the use of artificial intelligence techniques and machine learning algorithms in different diseases, including epilepsy, has increased significantly. The main objective of this study is to determine whether the mjn-SERAS artificial intelligence algorithm developed by MJN Neuroserveis, can detect seizures early using patient-specific data to create a personalized mathematical model based on EEG training, defined as the programmed recognition of oncoming seizures before they are primarily initiated, usually within a period of a few minutes, in patients diagnosed of epilepsy. Retrospective, cross-sectional, observational, multicenter study to determine the sensitivity and specificity of the artificial intelligence algorithm. We searched the database of the Epilepsy Units of three Spanish medical centers and selected 50 patients evaluated between January 2017 and February 2021, diagnosed with refractory focal epilepsy who underwent video-EEG monitoring recordings between 3 and 5 days, a minimum of 3 seizures per patient, lasting more than 5 s and the interval between each seizure was greater than 1 h. Exclusion criteria included age <18 years, intracranial EEG monitoring, and severe psychiatric, neurological, or systemic disorders. The algorithm identified pre-ictal and interictal patterns from EEG data using our learning algorithm and was compared to a senior epileptologist's evaluation as a gold standard. Individual mathematical models of each patient were trained using this feature dataset. A total of 1963 h of 49 video-EEG recordings were reviewed, with an average of 39.26 h per patient. The video-EEG monitoring recorded 309 seizures as subsequently analyzed by the epileptologists. The mjn-SERAS algorithm was trained on 119 seizures and split testing was performed on 188 seizures. The statistical analysis includes the data from each model and reports 10 false negatives (no detection of episodes recorded by video-EEG) and 22 false positives (alert detected without clinical correlation or abnormal EEG signal within 30 min). Specifically, the automated mjn-SERAS AI algorithm achieved a sensitivity of 94.7% (95 %; CI 94.67-94.73), and an F-Score representing specificity of 92.2% (95 %; CI 92.17-92.23) compared to the reference performance represented by a mean (harmonic mean or average) and a positive predictive value of 91%, with a false positive rate of 0.55 per 24 h in the patient-independent model. This patient-specific AI algorithm for early seizure detection shows promising results in terms of sensitivity and false positive rate. Although the algorithm requires high computational requirements on specialized servers cloud for training and computing, its computational load in real-time is low, allowing its implementation on embedded devices for online seizure detection.

Real-world safety and effectiveness of cenobamate in patients with focal onset seizures: Outcomes from an Expanded Access Program.

OBJECTIVE: This study investigated early, real-world outcomes with cenobamate (CNB) in a large series of patients with highly drug-resistant epilepsy within a Spanish Expanded Access Program (EAP). METHOD: This was a multicenter, retrospective, observational study in 14 hospitals. Inclusion criteria were age ≥18 years, focal seizures, and EAP authorization. Data were sourced from patient clinical records. Primary effectiveness endpoints included reductions (100%, ≥90%, ≥75%, and ≥50%) or worsening in seizure frequency at 3-, 6-, and 12-month visits and at the last visit. Safety endpoints included rates of adverse events (AEs) and AEs leading to discontinuation. RESULTS: The study included 170 patients. At baseline, median epilepsy duration was 26 years and median number of seizures/month was 11.3. The median number of prior antiseizure medications (ASMs) and concomitant ASMs were 12 and 3, respectively. Mean CNB dosages/day were 176 mg, 200 mg, and 250 mg at 3, 6, and 12 months. Retention rates were 98.2%, 94.5%, and 87% at 3, 6, and 12 months. At last available visit, the rate of seizure freedom was 13.3%; ≥90%, ≥75%, and ≥50% responder rates were 27.9%, 45.5%, and 63%, respectively. There was a significant reduction in the number of seizures per month (mean: 44.6%; median: 66.7%) between baseline and the last visit (P < 0.001). Responses were maintained regardless of the number of prior or concomitant ASMs. The number of concomitant ASMs was reduced in 44.7% of patients. The cumulative percentage of patients with AEs and AEs leading to discontinuation were 68.2% and 3.5% at 3 months, 74.1% and 4.1% at 6 months, and 74.1% and 4.1% at 12 months. The most frequent AEs were somnolence and dizziness. SIGNIFICANCE: In this highly refractory population, CNB showed a high response regardless of prior and concomitant ASMs. AEs were frequent but mostly mild-to-moderate, and few led to discontinuation.

Transcutaneous Supraorbital Stimulation as a Preventive Treatment for Chronic Migraine: A Prospective, Open-Label Study.

BACKGROUND AND OBJECTIVE: Successful preventive treatment in chronic migraine (CM) remains an unmet need in some cases, and new therapeutic strategies are emerging. We aimed to test the effect of noninvasive, transcutaneous supraorbital nerve stimulation (tSNS) in a group of patients with CM. PATIENTS AND METHODS: This was an open label, quasi-experimental design. Twenty-five CM patients were recruited from two hospital headache clinics. After a one-month baseline period, monthly visits were scheduled during three months. Headache occurrence, its intensity, and symptomatic medication intake were recorded through a diary kept by each patient. Both a per-protocol analysis and an intention-to-treat analysis were performed for the main outcome measures. RESULTS: Twenty-one and 24 patients were included in the per-protocol and the intention-to-treat analyses, respectively. In the per-protocol analysis, a significant four-day decrease in the mean monthly days with moderate or severe headache was observed from baseline to the end of the study (t test, P = 0.0163), and there was a nonsignificant reduction of 2.95 in the mean monthly total headache days. In the intention-to-treat analysis, a nonsignificant 3.37 reduction in the mean monthly days with moderate or severe headache was observed for the same period, and there was a significant 2.75 reduction in the mean monthly days with any headache (t test, P = 0.016). CONCLUSIONS: tSNS could hold preventive properties in the treatment of CM, but the effect may be either mild or controversial. Double blind, sham-controlled studies are essential to confirm these findings and to outline their clinical relevance in the CM therapeutic scenario.