Epileptic Disorders最新文献

{"title":"Seizure improvement following intravenous immunoglobulin in drug-resistant mesial temporal lobe epilepsy associated with systemic lupus erythematosus.","authors":"Kristijonas Puteikis, Basma Marzouk, Fabrice Bartolomei, Stanislas Lagarde","doi":"10.1002/epd2.70386","DOIUrl":"https://doi.org/10.1002/epd2.70386","url":null,"abstract":"","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter to the editor: The hidden burden of sleep in adolescents with idiopathic generalized epilepsy.","authors":"Shanze Mahmood, Muhammad Shehryar","doi":"10.1002/epd2.70387","DOIUrl":"https://doi.org/10.1002/epd2.70387","url":null,"abstract":"","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epilepsy with eyelid myoclonia beyond the classical phenotype: Longitudinal electroclinical observations in a pediatric cohort.","authors":"Hande Aygün, Alper Taşkın, Özlem Yayıcı Köken, Şenay Haspolat","doi":"10.1002/epd2.70385","DOIUrl":"https://doi.org/10.1002/epd2.70385","url":null,"abstract":"<p><strong>Objective: </strong>Epilepsy with eyelid myoclonia is a childhood-onset generalized epilepsy syndrome with variable recognition of eyelid myoclonia, eye-closure sensitivity, and photosensitivity during follow-up. We aimed to characterize longitudinal clinical and electroencephalographic features in pediatric epilepsy with eyelid myoclonia, focusing on delayed recognition, reflex electroencephalographic variability, electroclinical evolution, and treatment outcomes.</p><p><strong>Methods: </strong>We retrospectively reviewed 27 children with epilepsy with eyelid myoclonia followed between April 2020 and March 2026. Clinical characteristics, seizure evolution, serial electroencephalographic findings, neuroimaging data, and antiseizure medication responses were analyzed. Longitudinal electroclinical trajectories were summarized descriptively and not considered predefined or validated disease subtypes.</p><p><strong>Results: </strong>Among 27 patients, eyelid myoclonia was recognized at presentation in 14 and during follow-up in 13. Of 10 patients initially presenting with isolated eyelid myoclonia, additional seizure types emerged in six, whereas four retained an isolated phenotype throughout follow-up. The complete classical electroclinical phenotype was present at onset in only four patients. A photoparoxysmal response was documented in five patients, and focal epileptiform discharges in four patients. Epileptiform abnormalities persisted in 10 of 21 seizure-free patients. These findings demonstrate substantial heterogeneity in clinical evolution and electroencephalographic expression. Favorable seizure outcomes were observed in many lamotrigine-treated patients.</p><p><strong>Significance: </strong>In childhood epilepsy with eyelid myoclonia, classical electroclinical features may be incomplete at onset, and eyelid myoclonia may initially be missed. Repeated clinical and electroencephalographic assessment is important when epilepsy with eyelid myoclonia is suspected, and absence of photosensitivity or classical reflex electroencephalographic features should not exclude the diagnosis when the clinical phenotype is suggestive. Persistent epileptiform abnormalities despite clinical seizure freedom should be interpreted within the broader clinical context. Although favorable outcomes were observed in many patients, the retrospective design precludes conclusions regarding comparative treatment efficacy.</p>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148809257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal light modulation from LED lighting and seizure risk: A focused review of visible flicker, invisible modulation, and evidence gaps.","authors":"Wieslaw Brodaczewski, Olivier Brodaczewski","doi":"10.1002/epd2.70366","DOIUrl":"https://doi.org/10.1002/epd2.70366","url":null,"abstract":"<p><p>Critically assess whether light emitting diode (LED) lighting temporal light modulation (TLM) is linked to seizure risk while distinguishing established evidence on visible flicker in photosensitive epilepsy from weaker evidence on prolonged exposure to invisible or supra-critical flicker fusion (CFF) modulation. The review also lists desired data: modulation depth at 100/120 Hz, waveform and driver parameters, neurological symptoms, and ethically possible seizure-incidence observations under measured lighting. The narrative focused review used a structured search of recent literature and targeted inclusion of foundational and immediately relevant findings. Intermittent photic stimulation and visible flicker, prolonged exposure to invisible or supra-CFF TLM, temporal light artifacts during eye movements, modulation depth and waveform, and practical study designs for neurological and seizure data were categorized. Visible flicker in photosensitive epilepsy, notably in the 3-65 Hz range, with maximal sensitivity at 15-25 Hz, is the strongest evidence. Susceptible people may have seizures after intense stroboscopic exposure, but this does not prove that LED illumination with high-frequency imperceptible modulation causes seizures. Even without seeing the flicker, continuous exposure to 100 Hz lights can cause headaches, eyestrain, and increased visual-cortex activity, according to foundational research. Phantom array effects reveal that supra-CFF modulation may cause visual discomfort during saccades. Direct evidence relating typical LED modulation depth to seizures is missing. Evidence suggests caution, not causality. Thus, the paper's goals are to define what is known and what should not be overinterpreted and to suggest ways to gather more data. Because seizures are rare and safety-critical, double-masked studies should initially prioritize more common and lower-risk outcomes like headache, eyestrain, visual discomfort, task performance, and cortical activation in relation to modulation depth, while seizure incidence should be examined through carefully monitored secondary endpoints or prospective surveillance under measured lighting conditions.</p>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148809240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contraceptive management in people with epilepsy: A narrative review of drug interactions, special populations, and clinical guidance","authors":"Abrar O. Al-Faraj,&nbsp;Nicole Woodrich,&nbsp;Laura Kirkpatrick,&nbsp;Rachel Cannon,&nbsp;Trudy D. Pang","doi":"10.1002/epd2.70205","DOIUrl":"10.1002/epd2.70205","url":null,"abstract":"<p>Unintended pregnancies are common among people with epilepsy of child-bearing potential (PWECP). Unplanned pregnancies are associated with higher risks of maternal and fetal complications. In contrast, planned pregnancies are associated with more favorable outcomes, including a higher likelihood of treatment with anti-seizure medication (ASM) monotherapy, appropriate folic acid supplementation, and better seizure control. Therefore, counseling and provision of effective contraception are essential in reducing unplanned pregnancies and minimizing adverse maternal and fetal outcomes in this population. Selecting the most appropriate contraceptive method requires an in-depth understanding of the complex, bidirectional interactions between ASMs and hormonal contraception. These interactions can influence seizure control, contraceptive efficacy, and ASM serum concentrations. Despite its importance, providers' awareness of these interactions remains sub-optimal. In this review, we aim to provide a comprehensive review of the different hormonal contraceptive methods and their interactions with different ASMs. We also address contraception considerations in special populations: adolescents and people with intellectual or neurodevelopmental disabilities. Lastly, we highlight the current gaps in research about contraception use in PWECP and future research directions.</p>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":"28 4","pages":"1021-1032"},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147469843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inter-rater reliability and clinical utility of the BASED score in infantile epileptic spasms syndrome","authors":"T. P. Cramer,&nbsp;B. Johnsen,&nbsp;V. S. Hansen,&nbsp;E. Qerama,&nbsp;T. S. Engedal","doi":"10.1002/epd2.70255","DOIUrl":"10.1002/epd2.70255","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>Hypsarrhythmia is the classical EEG pattern of children with infantile epileptic spasms syndrome (IESS). Multifocal spikes, slow waves of large amplitude, and chaoticity are its main characteristics, but these lack clear definitions, and the interrater reliability (IRR) is poor. The aim of this study was to substantiate the use of the Burden of Amplitudes and Epileptiform Discharges (BASED) score for children with hypsarrhythmia on initial EEG and to compare the IRR to traditional scoring.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We identified before and after treatment EEGs from 20 consecutive patients from a local database. Clinical remission was defined as the remission of spasms. Three experienced Danish neurophysiologists, blinded to clinical information, rated each EEG separately using traditional visual analysis and the BASED score. A BASED score ≥4 and any hypsarrhythmic pattern were considered consistent with an epileptic encephalopathy. IRR was estimated using Gwet's AC1.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>IRR for scoring an epileptic encephalopathy was significantly better when using the BASED score compared with the traditional method (0.88 vs. 0.62, <i>p</i> = 0.01). Complete agreement was observed in 36 out of 40 EEGs using the BASED score vs. 28 out of 40 using the traditional method (Fisher's exact test: <i>p</i> = 0.048). IRR was near perfect or substantial in all but one of the individual components of the BASED score. Clinical remission was seen in 14 out of 19 patients, and the clinical course was consistent with EEG in 18 out of 19 patients using the BASED score and in 16 out of 19 patients using the traditional method (Fisher's exact test: <i>p</i> = 0.60).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Significance</h3>\u0000 \u0000 <p>The BASED score demonstrated very high interrater reliability, exceeding that of traditional hypsarrhythmia scoring. It also corresponded closely with the clinical course, supporting its validity.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":"28 4","pages":"1132-1140"},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/epd2.70255","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147729925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gut microbiota shifts and short-chain fatty acids alterations in pediatric epilepsy patients on a Mediterranean ketogenic diet","authors":"Sofia Zouganeli,&nbsp;Evdokia K. Mitsou,&nbsp;Mary Yannakoulia,&nbsp;Evangelia Intze,&nbsp;Konstantinos C. Mountzouris,&nbsp;Smaragdi Fessatou,&nbsp;Achilleas Attilakos,&nbsp;Adamantini Kyriacou,&nbsp;Argyrios Dinopoulos","doi":"10.1002/epd2.70269","DOIUrl":"10.1002/epd2.70269","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>The olive oil–based Mediterranean ketogenic diet (MedKD) may support patients with drug-resistant epilepsy (DRE) or neurometabolic disorders by integrating ketogenic therapy with the cardiometabolic and neuroprotective advantages of the Mediterranean diet. This study assessed alterations in gut microbiota composition and short-chain fatty acids (SCFAs) in Greek pediatric epilepsy patients under a 3-month MedKD.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Patients eligible for ketogenic diet therapy and one parent per patient as controls were enrolled. An olive oil–based KD aligned with Mediterranean principles was initiated during a 5–7-day hospital stay. Anthropometric, nutritional, biochemical and clinical data were recorded at baseline and after 3 months. Fecal samples were collected from patients at both time points, and parents provided a single baseline sample. Microbiota composition was analyzed using 16S rRNA gene next-generation sequencing, and SCFAs were quantified via gas chromatography. Written informed consent was obtained from all parents. The study was registered at ClinicalTrials.gov (NCT05898438).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The study enrolled 18 pediatric/adolescent patients (aged 2.5–15.5 years) and 17 parents at baseline (T1). After 3 months (T2), 13 patient–parent pairs completed follow-up. MedKD adherence was high, with mean ketone levels of 2.6 mmol/L and a clinical response in 85% of patients. Anthropometric measurements improved, and lipid changes were modest. No significant α-diversity differences were detected between patients and parents at T1 or between T1 and T2 in patients, whereas β-diversity differed significantly between parents and patients at baseline. Epilepsy-associated genera were more abundant in patients. At T2, patients exhibited shifts including increased members of <i>Eggerthellaceae</i> and decreased <i>Lachnospira</i> and <i>Bifidobacterium</i>. Major SCFAs remained stable, with increases limited to minor protein-derived SCFAs.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Significance</h3>\u0000 \u0000 <p>The MedKD was associated with high adherence, efficacy, and anthropometric improvements, along with modest effects on the lipid profile. Microbial and SCFA changes reflected both the epilepsy-related milieu and potential influences of the diet's high olive oil content.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":"28 4","pages":"1159-1174"},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/epd2.70269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147845365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian age-period-cohort analysis and trend prediction of epilepsy disease burden in China, 1990–2021","authors":"Chao Jiang,&nbsp;Keke Ju,&nbsp;Yiming You,&nbsp;Yan Zhao,&nbsp;Jian Wang,&nbsp;Chuang Guo,&nbsp;Zhiqiang Cui","doi":"10.1002/epd2.70264","DOIUrl":"10.1002/epd2.70264","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>This study analyzes the trends, age-period-cohort effects, and influencing factors of epilepsy burden in China from 1990 to 2021, and predicts future burden to support prevention strategies.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Data were sourced from the Global Burden of Disease Study (GBD) 2021 study. Joinpoint regression analyzed trends in incidence, prevalence, mortality, and disability-adjusted life years (DALYs). The BAPC (Bayesian Age-Period-Cohort) model evaluated age, period, and cohort effects, and an ARIMA (Autoregressive Integrated Moving Average) model projected burden to 2036.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>In 2021, epilepsy cases reached 3.086 million (a 41.67% increase since 1990), while DALYs fell to 1.375 million person-years (a 35.60% decrease). Age-standardized incidence and prevalence increased (average annual percent change [AAPC] = 0.78% and 0.42%, respectively), whereas mortality and DALY rates declined (AAPC = −2.65% and −1.79%). After 2019, incidence and prevalence rose sharply, accompanied by a short-term increase in DALY rates indicating a risk of rebound. Age-specific burden shifted from a unimodal (0–25 years) to a bimodal distribution (0–14 and 30–34 years), with the highest burden now among working-age adults. The DALY rate decreased slowest in youths (20–24 years) and fastest in middle-aged groups (45–55 years). Projections indicate continued declines in mortality but stable yet fluctuating incidence through 2036.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>Despite improved mortality and DALY rates, epilepsy incidence and prevalence have increased, and although the overall DALY rate has declined, a recent uptick since 2019 signals the need for continued vigilance and targeted intervention. The shifting burden toward working-age populations underscores the need for differentiated prevention strategies focusing on young adults and the elderly, emphasizing early intervention and long-term management.</p>\u0000 </section>\u0000 </div>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":"28 4","pages":"1188-1203"},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability of Bonini's semiological classification in frontal lobe seizures: A video-EEG based study.","authors":"Jayanti Mani, Sunita Iyer, Nilima Bhalerao","doi":"10.1002/epd2.70378","DOIUrl":"https://doi.org/10.1002/epd2.70378","url":null,"abstract":"<p><strong>Objective: </strong>Frontal lobe seizures have heterogeneous semiology, making electroclinical localization challenging. Bonini et al. proposed a semiological classification based on rostrocaudal frontal lobe organization. We evaluated its interobserver and intraobserver reliability and explored anatomical and surgical correlations.</p><p><strong>Methods: </strong>We retrospectively analyzed long-term video-EEG recordings of 33 patients with suspected frontal lobe epilepsy. Two independent observers classified seizures into four Bonini groups and repeated the classification after 12 weeks. Semiology was interpreted using standardized ILAE terminology where applicable, while group allocation was based on the descriptors of the original Bonini classification. Reliability was assessed using Cohen's kappa, percentage agreement, and an interobserver confusion matrix. Neuroimaging findings were mapped to Brodmann areas and correlated with Bonini group allocation as an exploratory analysis.</p><p><strong>Results: </strong>Intraobserver reliability was excellent, with kappa values of .869 and .914. Interobserver agreement was substantial, with kappa values of .6535 and .6988 across the two trials. Group 2 seizures were most frequent, whereas Group 4 was rare. The confusion matrix showed predominant diagonal agreement, with disagreements mainly between adjacent groups. Among 13 patients with clearly localizable focal lesions, semiology correlated with anatomical localization in nine. Nine patients underwent surgery; concordance was observed in seven, and all achieved Engel Class I outcomes.</p><p><strong>Conclusion: </strong>Bonini's classification shows excellent intraobserver reliability and substantial interobserver agreement in routine video-EEG practice. Anatomical validation remains limited by the absence of systematic SEEG confirmation, but the observed imaging and surgical correlations support its clinical applicability as a reproducible framework for presurgical hypothesis generation.</p><p><strong>Significance: </strong>This is the first study to validate the reproducibility of Bonini's classification in routine video-EEG practice; however, network-based anatomical interpretation should remain cautious in the absence of systematic SEEG validation.</p>","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can epilepsy be predicted after the first febrile seizure? Insights from machine learning of postictal EEG","authors":"Boran Şekeroğlu,&nbsp;Hüseyin Öztoprak,&nbsp;Özlem Yayıcı Köken,&nbsp;Hatice Demir,&nbsp;Mehpare Sarı Yanartaş,&nbsp;Deniz Yılmaz,&nbsp;Burçin Şanlıdağ,&nbsp;Ayşegül Neşe Çıtak Kurt","doi":"10.1002/epd2.70250","DOIUrl":"10.1002/epd2.70250","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Objective&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Febrile seizures (FS) are the most common seizures in childhood, yet identifying children at risk of developing epilepsy after the first FS remains challenging. We aimed to evaluate the prognostic potential of machine learning (ML) algorithms applied to post-febrile seizure electroencephalography (EEG) recordings.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;We retrospectively reviewed 104 children (69 boys; mean age at first febrile seizure: 39.4 ± 18.2 months) who presented with their first febrile seizure between January 2018 and December 2021. Clinical data and EEG recordings obtained during N2 sleep were collected. EEG analysis was performed using separate preprocessing pipelines. For conventional EEG analysis, recordings were band-pass filtered between 1 and 40 Hz, and artifact-free segments were analyzed using Python-based pipelines (YASA, MNE) to extract 34 time-domain. The 34 extracted electrophysiological features were calculated across different bipolar EEG channels and evaluated together with aggregated inter-channel measures, resulting in a total of 93 input attributes used for ML model development. High-frequency oscillations (HFOs) were analyzed using a distinct pipeline applied to wideband EEG data before low-pass filtering. Six machine learning algorithms—J48 Consolidated Decision Tree, Random Forest, Gradient Boosting, Extreme Gradient Boosting, k-nearest neighbor, and Support Vector Machine—were trained using 10 × 7 repeated cross-validation. Model performance was evaluated using sensitivity, specificity, accuracy, area under the receiver operating characteristic curve (ROC AUC), and F1-score.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Over a median follow-up of 4.2 months, 13 patients (12.5%) developed epilepsy, and all diagnoses were made within 9 months. XGBoost achieved the highest accuracy (0.89) and specificity (0.95) but had low sensitivity (0.46). J48 achieved the highest sensitivity (0.87) and ROC AUC (0.79), with a specificity of 0.71. Incorporating clinical features, including recurrent seizures, increased sensitivity to 0.95. The most relevant predictors were patient history, frequency band power, particularly increased power in lower frequency bands, and high-frequency oscillations counts.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusion&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;ML-based analysis of initial EEG after a first febrile seizure may assist in early epilepsy risk stratification. J48 provided superior sensitivity, and combining electroencephalography-derived biomarkers with clinical data further enhanced p","PeriodicalId":50508,"journal":{"name":"Epileptic Disorders","volume":"28 4","pages":"1150-1158"},"PeriodicalIF":2.5,"publicationDate":"2026-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/epd2.70250","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147788018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}