Epilepsia最新文献

{"title":"Spanish translation, adaptation, and validation of the Epilepsy Surgery Satisfaction Questionnaire-19.","authors":"Elena Fonseca, Alejandro Thomson, Mario Alonso, Óscar Contreras, Walter de la Cruz, María Garcés-Pellejero, Enric Bellido-Castillo, Camilo Espinosa-Jovel, Alberto Velásquez, Enrique de Font-Reaulx, Cintia Flores, Luis Carlos Mayor-Romero, Paula Martínez, Xiana Rodríguez-Osorio, Álvaro Juiz, Mar Carreño, Estefanía Conde, Marta Olivera, Elliot Barreto-Acevedo, Oswaldo Rodríguez, Juan Rodríguez-Uranga, Iratxe Maestro, Mercè Falip, Guillermo Hernández, José M Serratosa, Esteban Cordero, Manuel Quintana, Samuel López-Maza, Daniel Campos-Fernández, Laura Abraira, Estevo Santamarina, Samuel Wiebe, Manuel Toledo","doi":"10.1111/epi.18631","DOIUrl":"https://doi.org/10.1111/epi.18631","url":null,"abstract":"<p><strong>Objective: </strong>The effectiveness of surgery in drug-resistant epilepsies is often focused exclusively on seizure control. The Epilepsy Surgery Satisfaction Questionnaire-19 (ESSQ_19), developed in 2020, is a reliable tool for assessing the level of satisfaction of patients undergoing surgery. We aimed to perform a Spanish translation, adaptation, and validation of the ESSQ_19 questionnaire.</p><p><strong>Methods: </strong>This was a prospective multicenter study (five Spanish-speaking countries) including an international cohort of adult patients who underwent epilepsy surgery at least 1 year prior to participation. We followed a translation and back-translation methodology to obtain the Spanish version of the questionnaire (ESP-ESSQ_19). For validation, internal consistency (Cronbach alpha) and test-retest reliability at 6 months were assessed, and psychometric properties were measured by correlating them with parallel aspects using validated questionnaires.</p><p><strong>Results: </strong>One hundred fifty patients were included (59.3% women; mean age = 39.3 ± 13 years, interquartile range [IQR] = 28-49 years), of whom 94 completed the baseline and follow-up questionnaires, with a median time since surgery of 3 (IQR = 1-7) years. Temporal lobe epilepsy was the most common (n = 112, 77.8%), as was structural etiology (n = 139, 95.2%). At inclusion, 101 patients (68.7%) had been seizure-free for ≥1 year. The ESP-ESSQ_19 questionnaire showed an internal consistency index of .88-.95 for all domains and a test-retest reliability of .91 (95% confidence interval = .87-.94). Significant correlation coefficients were observed between the ESP-ESSQ_19 questionnaire and all validated questionnaires used.</p><p><strong>Significance: </strong>The ESP-ESSQ_19 questionnaire is a Spanish-language instrument useful for assessing patient satisfaction after epilepsy surgery, with adequate psychometric properties that allow its use in clinical practice and in research.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seizure outcomes in persons with autism spectrum disorder undergoing epilepsy surgery: A systematic review and meta-analysis.","authors":"Varun R Subramaniam, Jonathan Goldstein, Ali Rafati, Paul Gorka, Churl-Su Kwon","doi":"10.1111/epi.18645","DOIUrl":"https://doi.org/10.1111/epi.18645","url":null,"abstract":"<p><strong>Objectives: </strong>Autism spectrum disorder (ASD) and epilepsy commonly co-occur. Surgical interventions are viable treatment options for individuals with drug-resistant epilepsy. However, past research in patients with ASD and epilepsy has yielded mixed results regarding seizure outcomes following epilepsy surgery.</p><p><strong>Methods: </strong>We adhered to the Preferred Reporting Item for Systematic reviews and Meta-Analyses (PRISMA) standards. Medline, Embase, and PsycInfo were queried from inception to November 2024. Included studies reported seizure frequency following epilepsy surgery in persons with ASD. Forty-six studies reporting on 325 patients with ASD and epilepsy were included for analysis. A total of 137 patients underwent resective surgery, 167 underwent neuromodulation (138 vagus nerve stimulation [VNS], 27 responsive neurostimulation [RNS], 2 deep brain stimulation [DBS]), and 21 underwent other palliative procedures (17 corpus callosotomy and 4 laser interstitial thermal therapy). Outcomes were stratified into four categories based on a combination of Engel classification and percentage seizure reduction at latest follow-up.</p><p><strong>Results: </strong>Resections yielded seizure freedom in 54% of patients, whereas neuromodulation led to >80% seizure reduction in 33.5% of patients. The incidence proportion of seizure freedom after surgery was higher in patients with MRI abnormalities was .55 (95% confidence interval [CI]: .34-.75) vs patients without MRI abnormalities (.19, 95% CI: .01-.81). Incidence proportion of seizure freedom after temporal resection was .80 (95% CI: .50-.94) vs .66 (95% CI: .48-.80) for extratemporal resection. Improvement in neuropsychiatric or quality of life outcomes was reported in the majority of patients after surgery.</p><p><strong>Significance: </strong>Our study provides the most comprehensive review to date of epilepsy surgery in ASD. Based on past work, there is potential for properly selected patients with ASD and epilepsy to experience a significant reduction in seizure frequency or seizure freedom, as well as improved quality of life, following epilepsy surgery.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nanoparticle-encapsulated neuropeptide Y provides robust seizure protection in SCN1A-derived epilepsy.","authors":"Samantha L Reed, Lauren M Aiani, Eesha Faiz, Emmanuel Adediran, Morris Benveniste, Kevin S Murnane, Martin D'Souza, Andrew Escayg, Jennifer C Wong","doi":"10.1111/epi.18649","DOIUrl":"https://doi.org/10.1111/epi.18649","url":null,"abstract":"<p><strong>Objective: </strong>Neuropeptides have garnered great interest as potential treatments for epilepsy due to their impact on neuronal excitability through modulation of ion channels and neurotransmitter receptor activity. Neuropeptide Y (NPY) is a 36-amino acid neuropeptide that is expressed primarily by γ-aminobutyric acidergic (GABAergic) interneurons. NPY has widespread effects on the brain, at both the cellular (e.g., reducing excitatory glutamatergic transmission) and circuit levels (e.g., increasing food intake, improving learning and memory, increasing seizure resistance). Previous studies have demonstrated antiseizure effects of NPY following invasive brain delivery methods or gene therapy approaches to increase the expression of NPY or its receptor activity. However, these routes of administration pose challenges for translation into clinical practice.</p><p><strong>Methods: </strong>To overcome these obstacles, we generated a nanoparticle formulation to encapsulate neuropeptides. In the current study, we evaluated the ability of nanoparticle-encapsulated NPY (NP-NPY) to increase resistance to 6 Hz-, pentylenetetrazole-, and hyperthermia-induced seizures in mouse models of SCN1A-derived epilepsy. We also examined the ability of NP-NPY treatment to protect against spontaneous seizures in Scn1a^+/- mutant mice, a model of Dravet syndrome. Quantitative reverse transcription polymerase chain reaction was performed to compare expression levels of NPY and its receptors in hippocampi from Scn1a^+/- mutants and wild-type littermates.</p><p><strong>Results: </strong>We found that intranasal NP-NPY administration was able to provide robust protection against induced seizures in two mouse models of SCN1A-derived epilepsy and reduce spontaneous seizure frequency in Scn1a^+/- mutant mice.</p><p><strong>Significance: </strong>These results provide support for further evaluation of NP-NPY as a treatment for SCN1A-derived epilepsy and possibly other epilepsy subtypes.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145274204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association between local gray matter volume differences and stereo-electroencephalography-defined epileptogenicity.","authors":"Jacob Bunyamin, Benjamin Sinclair, Thanomporn Wittayacharoenpong, Mohamad Nazem-Zadeh, Parveen Sagar, Noam Bosak, Zhibin Chen, Joshua Laing, Matthew Gutman, Martin Hunn, Meng Law, Patrick Kwan, Terence J O'Brien, Andrew Neal","doi":"10.1111/epi.18671","DOIUrl":"https://doi.org/10.1111/epi.18671","url":null,"abstract":"<p><strong>Objective: </strong>The yield of voxel-based gray matter volume (GMV) quantification to identify the epileptogenic zone (EZ) remained moderate, which may be due to the choice of \"ground truth.\" We explored whether GMV differences are associated with stereo-electroencephalography (SEEG)-defined epileptogenicity as potential EZ imaging biomarkers.</p><p><strong>Methods: </strong>We included SEEG patients along with age- and sex-matched non-epilepsy controls. We performed a non-parametric voxel-based permutation inference between each SEEG patient's non-contrast 3T T1-weighted magnetic resonance imaging (MRI) scan and controls, resulting in pseudo-t-test maps reflecting GMV differences. We classified SEEG contacts based on their involvement in (i) the EZ, defined as contacts designated for radiofrequency thermocoagulation, and (ii) active irritative zones, defined as contacts generating the top 10% of spikes, fast ripples, and cross-rates of HFO*spikes for each patient. We then performed mixed-effects logistic regressions and performance analysis.</p><p><strong>Results: </strong>We included 50 patients (median age 33.0 years, female 52.0%, MRI-negative 76.0%) and 51 controls (median age 37.0 years, female 56.9%). EZ: In general, increased GMV was associated with EZ contacts across the whole cohort (odds ratio [OR] 1.21, 95% confidence interval [CI] 1.11-1.31, p < .001) and the MRI-positive group (OR 1.45, 95% CI 1.28-1.64, p < .001), but not in the MRI-negative group (p = .621). Reduced GMV was associated with EZ contacts in mesiotemporal regions (OR .53, 95% CI .33-.84, p = .035) but the opposite in neocortical areas (OR 1.32, 95% CI 1.21-1.44, p < .001). Within MRI-visible lesions, increased GMV was positively associated with EZ contacts (OR 1.50, 95% CI 1.19-1.89, p = .005). Active irritative zone: In the MRI-positive group, increased GMV was linked to neocortical contacts exhibiting the top 10% of spikes (p = .040) and fast ripples (p = .008), but not in MRI-negative cases.</p><p><strong>Significance: </strong>Local GMV differences were positively associated with EZ contacts in the whole cohort and MRI-positive patients but not in MRI-negative patients, with positive associations in the neocortex and a negative one in the mesiotemporal structures. Within MRI-visible lesions, increased GMV was associated with EZ contacts.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145274258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seizure classification using a multimodal seizure monitoring system (Nelli) in Dravet and Lennox-Gastaut syndromes: A non-randomized, single-center feasibility study.","authors":"Line Kønig Wilms, Morten I Lossius, Kaapo Annala, Jonas Abdel-Khalik, Lena Fanter, Kaisa Elomaa, Jukka Peltola","doi":"10.1111/epi.18640","DOIUrl":"https://doi.org/10.1111/epi.18640","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to assess the performance of the Nelli seizure monitoring system in detecting and classifying seizures during sleep or while at rest in bed in patients with Lennox-Gastaut syndrome (LGS) and Dravet syndrome (DS).</p><p><strong>Methods: </strong>We conducted a non-interventional, single-center feasibility study from August 2023 to March 2024, involving 20 patients aged ≥2 years diagnosed with DS or LGS. Participants used Nelli for home-based seizure monitoring during sleep or while at rest in bed for 4 weeks. Seizures were detected and classified by Nelli, and results were compared to epileptologist reviews and seizure diaries.</p><p><strong>Results: </strong>Of 20 enrolled patients, 14 (70%) who experienced seizures at rest were included in the analyses. Among them, Nelli detected 368 seizures, with an accuracy of 97.8%, as confirmed by independent reviewers. Eight seizures (2.2%) detected by Nelli were false positives, identified as part of a single seizure episode. Of the 14 patients, only 35.7% reported experiencing seizures in their diaries, and only 26.1% of the seizures were documented. Seizure durations ranged from 6 to 396 s, with considerable variation. Nelli demonstrated high accuracy in seizure classification (Gwet agreement coefficient [AC1] = .81-1.00) in nine of 14 cases. However, in three of 14 patients, moderate accuracy (AC1 = .41-.60) was observed due to challenges in classifying seizures in patients with high seizure frequency or suboptimal device positioning. The average classification accuracy of Nelli for tonic-clonic seizures was .99 (150/152 seizures), tonic seizures .55 (102/186), clonic seizures 1.00 (3/3), focal motor seizures .89 (16/18), and myoclonic seizures 1.00 (1/1).</p><p><strong>Significance: </strong>Nelli demonstrated high sensitivity and classification accuracy for detecting and categorizing seizures in bed in patients with DS and LGS, outperforming seizure diaries and providing a reliable tool for seizure monitoring in home settings.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Syndromic and etiological classification predicts seizure freedom in childhood and youth onset epilepsy: A population-based study from the Norwegian Mother, Father, and Child Cohort Study.","authors":"Truls Vikin, Richard F Chin, Morten I Lossius, Dag Hofoss, Ragnhild E Brandlistuen, Kari M Aaberg","doi":"10.1111/epi.18672","DOIUrl":"https://doi.org/10.1111/epi.18672","url":null,"abstract":"<p><strong>Objective: </strong>This study was undertaken to determine the proportion of individuals with childhood and youth onset epilepsy who attain seizure freedom across seizure types, epilepsy types, etiologies, and syndromes using the latest International League Against Epilepsy (ILAE) classifications. Secondary objectives were to identify predictors of seizure freedom, evaluate time to last seizure among those achieving it, and estimate prevalence of active epilepsy.</p><p><strong>Methods: </strong>We used data from the Norwegian Mother, Father, and Child Cohort Study, a nationwide population-based cohort of ~114 000 children born 1999-2009. Pediatric epileptologists validated and classified epilepsy cases through medical record review. Analyses included 1044 individuals with ≥12 months of follow-up. Seizure freedom was ≥12 months without seizures, with or without antiseizure medication (ASM), at end of follow-up. Predictors of seizure freedom were assessed using log-binomial regression adjusted for follow-up. Time to last seizure was analyzed using Accelerated Failure Time models. Active epilepsy at any age was defined as seizures during the preceding 2 years and/or ASM use at that age; prevalence was calculated annually from ages 0 to 18 years.</p><p><strong>Results: </strong>Median follow-up was 10.6 years. A total of 78% achieved seizure freedom. Predictors of reduced likelihood of seizure freedom included early (<2 years) or adolescent onset, multiple seizure types, status epilepticus, developmental comorbidities, and abnormal neurologic findings. Seizure freedom was most common in focal epilepsy (84%) and least in combined generalized and focal epilepsy (26%). It was highest for unknown etiology (89%) and lowest for structural (58%) and identified genetic etiologies (54%). Favorable outcomes were seen in self-limited focal epilepsies, childhood absence epilepsy, and self-limited infantile syndromes. Developmental and epileptic encephalopathies had lower rates. Among those seizure-free, median time to last seizure was 2.0 years. Prevalence peaked at age 11 years (490 per 100 000) and varied by syndrome.</p><p><strong>Significance: </strong>This population-based study supports the prognostic value of syndrome- and etiology-based ILAE classifications in clinical care.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing naming and verbal memory in bilingual epilepsy: Challenges and insights for surgical planning.","authors":"Alena Stasenko, Yosefa Modiano, Oscar Woolnough, Erik Kaestner, Jonathan Rodriguez, Rhea Cho, Gabrielle Flores, Anny Reyes, Jerry J Shih, Taha Gholipour, Nitin Tandon, Carrie R McDonald","doi":"10.1111/epi.18662","DOIUrl":"https://doi.org/10.1111/epi.18662","url":null,"abstract":"<p><strong>Objective: </strong>Naming and verbal memory are key components of epilepsy evaluations, as impairments often reflect left temporal dysfunction, and baseline performance helps estimate postsurgical risk. The utility of naming tests in bilingual individuals with epilepsy, however, has been questioned. We examined whether naming and verbal memory performance reflects seizure laterality in bilingual adults, how bilingualism affects baseline scores, and whether bilingual factors moderate the effects of seizure laterality on cognition.</p><p><strong>Methods: </strong>We analyzed naming and verbal memory data from 148 monolingual and 63 bilingual adults with unilateral epilepsy across two centers. Participants completed English-based tests of visual naming, story recall, and word-list recall. Analyses of covariance and Bayesian models tested effects of seizure laterality, bilingual status, and their interaction. Regressions tested the moderating effects of bilingual factors (e.g., age at acquisition, proficiency, English immersion).</p><p><strong>Results: </strong>Bilinguals scored lower on naming than monolinguals, but both groups showed worse naming in left versus right hemisphere epilepsy (nonsignificant interaction). Using monolingual norms, naming impairment was far more frequent in bilinguals (90%-92% left onset, 63%-71% right onset) than monolinguals, but rates normalized after adjusting for the bilingual naming disadvantage. Among non-US-born bilinguals, greater immersion was associated with better naming in right-but not left-hemisphere epilepsy. For verbal memory, seizure laterality effects were present in story recall, and in word-list recall among patients with mesial temporal sclerosis, but did not differ by bilingual status.</p><p><strong>Significance: </strong>Naming and verbal memory remain reliable markers of seizure laterality in bilingual adults with epilepsy. For naming, however, improved measures and bilingual-specific norms are essential to avoid misclassification and support accurate clinical decision-making.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unilateral ultra long-term subcutaneous EEG monitoring in drug-refractory idiopathic generalized epilepsy.","authors":"Tudor Munteanu, Bryoni Daly, Cara O'Donnell, Annette Breen, Tenzin Choekyi, Breege Staunton-Grufferty, Donncha O'Brien, Kieron Sweeney, Ronan Kilbride, Peter Widdess-Walsh, Hany El-Naggar, Norman Delanty","doi":"10.1111/epi.18644","DOIUrl":"https://doi.org/10.1111/epi.18644","url":null,"abstract":"<p><strong>Objective: </strong>Seizure self-reporting is known to be unreliable, particularly with non-convulsive seizures. There is increasing interest in long-term monitoring systems to detect and count seizures, including the use of the minimally-invasive CE-marked subcutaneous unilateral electroencephalography (EEG) recording system, which has been shown to accurately detect ipsilateral focal seizures.</p><p><strong>Methods: </strong>We implanted the subcutaneous EEG system in nine patients with refractory idiopathic generalized epilepsy (IGE), following initial characterization of their inter-ictal and ictal EEG abnormalities, with in-patient video-EEG monitoring as gold standard comparison. We compared the in-patient video-EEG findings to the abnormalities detected on the long-term subcutaneous system in seven of the nine patients. We compared EEG signal characteristics for convulsive seizures, and for spike and wave discharges of duration of <3 s, between 3 to 10 s, and greater than 10 s.</p><p><strong>Results: </strong>Three generalized convulsive seizures were recorded in total during video-EEG monitoring, and all were easily detected by the long-term subcutaneous EEG system. Ninety percent of significant spike and wave discharges lasting >3 s were identified using the subcutaneous EEG device. There were minimal adverse effects from use of the device; the patients were satisfied that the device was easy to use and were likely to recommend the use of the device to other patients with epilepsy, as measured by Likert scales. The device implantation was judged to be easy by our epilepsy neurosurgeons.</p><p><strong>Significance: </strong>This study demonstrates that ultra long-term monitoring with unilateral subcutaneous EEG can reliably detect all convulsive and most non-convulsive generalized seizures in patients with refractory IGE. The device is well tolerated and easy to insert, and it can be used as a useful adjunctive seizure monitoring system in select patients. Furthermore, it may guide therapy to optimize seizure control, and it may confer cost savings by avoiding the need for in-patient video monitoring in appropriate patients.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surfaced-based detection of focal cortical dysplasia using magnetic resonance fingerprinting and machine learning.","authors":"Ting-Yu Su, Siyuan Hu, Xiaofeng Wang, Sophie Adler, Konrad Wagstyl, Zheng Ding, Joon Yul Choi, Ken Sakaie, Ingmar Blümcke, Hiroatsu Murakami, Andreas V Alexopoulos, Stephen E Jones, Imad Najm, Dan Ma, Zhong Irene Wang","doi":"10.1111/epi.18667","DOIUrl":"https://doi.org/10.1111/epi.18667","url":null,"abstract":"<p><strong>Objective: </strong>This study was undertaken to develop a framework for focal cortical dysplasia (FCD) detection using surface-based morphometric (SBM) analysis and machine learning (ML) applied to three-dimensional (3D) magnetic resonance fingerprinting (MRF).</p><p><strong>Methods: </strong>We included 114 subjects (44 patients with medically intractable focal epilepsy and FCD, 70 healthy controls [HCs]). All subjects underwent high-resolution 3-T MRF scans generating T1 and T2 maps. All patients had clinical T1-weighted (T1w) images; 35 also had 3D fluid-attenuated inversion recovery (FLAIR). A 3D region of interest (ROI) was manually created for each lesion. All maps/images and lesion ROIs were registered to T1w images. Surface-based features were extracted following the Multi-center Epilepsy Lesion Detection pipeline. Features were normalized using intrasubject, interhemispheric, and intersubject z-scoring. A two-stage ML approach was applied: a vertexwise neural network classifier for lesional versus normal vertices using T1w/MRF/FLAIR features, followed by a clusterwise Random Undersampling Boosting classifier to suppress false positives (FPs) based on cluster size, prediction probabilities, and feature statistics. Leave-one-out cross-validation was performed at both stages.</p><p><strong>Results: </strong>Using T1w features, sensitivity was 70.4% with 11.6 FP clusters/patient and 4.1 in HCs. Adding MRF reduced FPs to 6.6 clusters/patient and 1.5 in HCs, with 68.2% sensitivity. Combining T1w, MRF, and FLAIR achieved 71.4% sensitivity, with 4.7 FPs/patient and 1.1 in HCs. Detection probabilities were significantly higher for true positive clusters than FPs (p < .001). Type II showed higher detection rates than non-type II. Magnetic resonance imaging (MRI)-positive patients showed higher detection rates and fewer FPs than MRI-negative patients. Seizure-free patients demonstrated higher detection rates than non-seizure-free patients. Subtyping accuracy was 80.8% for non-type II versus type II, and 68.4% for IIa versus IIb, although limited by small sample size. The transmantle sign was present in 61.5% of IIb and 40% of IIa cases.</p><p><strong>Significance: </strong>We developed an ML framework for FCD detection integrating SBM with clinical MRI and MRF. Advances include improved FP control and enhanced subtyping; selected model outputs may provide indicators of detection confidence and seizure outcome.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seizure detection using ultra-long-term subcutaneous electroencephalography: A deep learning CNN-BiLSTM approach.","authors":"Sihyeong Park, Jordan S Clark, Pedro F Viana, Jie Cui, Jonas Duun-Henriksen, Jay Mandrekar, Nicholas Gregg, Vaclav Kremen, Gregory A Worrell, Mark P Richardson, Benjamin H Brinkmann","doi":"10.1111/epi.18652","DOIUrl":"https://doi.org/10.1111/epi.18652","url":null,"abstract":"<p><strong>Objective: </strong>This study reports development and validation of a deep learning seizure detection algorithm for two-channel subscalp electroencephalographic (EEG) recordings. Ultra-long-term monitoring of people with epilepsy may produce new insights into the timing and pattern of their seizures and may pave the way for novel therapeutic options. Although EEG is the accepted standard for epilepsy monitoring, ultra-long-term EEG recordings generate a massive quantity of data and are not reasonably reviewable in full by human readers.</p><p><strong>Methods: </strong>The convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) hybrid algorithm uses nine layers, operating on channel spectrograms 5 min in length with 50% overlap. Retrospective subscalp EEG data from 16 patients recorded at three centers were available for algorithm development and testing. EEG was recorded for a median of 63 days (range = 9-508), and a median of 17 seizures (range = 0-96) were recorded. Training data were augmented with scalp EEG seizures, and performance was benchmarked against a conventional spectral power classifier algorithm. We also evaluated an intrapatient training-testing approach where the algorithm was trained on the first 45% of data.</p><p><strong>Results: </strong>The CNN-BiLSTM trained on scalp EEG and subscalp EEG achieved an area under the receiver operating characteristic curve (AUROC) of .98 and an area under the precision-recall curve (AUPRC) of .50, which correspond to 94% sensitivity with 1.11 false detections per day. The same model trained on iEEG achieved only AUROC = .94 and AUPRC = .36. The conventional spectral band power detector achieved AUROC = .93 and AUPRC = .38. The CNN-BiLSTM detector trained on the earliest half of the subscalp EEG data achieved AUROC = .93 and AUPRC = .37, corresponding to 87% sensitivity and 5.9 false detections per day.</p><p><strong>Significance: </strong>High sensitivity and specificity are possible in automated seizure detection in two-channel subscalp EEG data using a CNN-BiLSTM framework. Performance of the detector is superior using subcutaneous EEG data for training rather than intracranial EEG, but addition of scalp EEG seizures for training was helpful.</p>","PeriodicalId":11768,"journal":{"name":"Epilepsia","volume":" ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145243877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}