No abstract

Objective: There is substantial variability in reported seizure outcome following pediatric epilepsy surgery, and lack of individualized predictive tools that could evaluate the probability of seizure freedom postsurgery. The aim of this study was to develop and validate a supervised machine learning (ML) model for predicting seizure freedom after pediatric epilepsy surgery.Methods: This is a multicenter retrospective study of children who underwent epilepsy surgery at five pediatric epilepsy centers in North America. Clinical information, diagnostic investigations, and surgical characteristics were collected, and used as features to predict seizure-free outcome 1 year after surgery. The dataset was split randomly into 80% training and 20% testing data. Thirty-five combinations of five feature sets with seven ML classifiers were assessed on the training cohort using 10-fold cross-validation for model development. The performance of the optimal combination of ML classifier and feature set was evaluated in the testing cohort, and compared with logistic regression, a classical statistical approach.Results: Of the 801 patients included, 61.3% were seizure-free 1 year postsurgery.During model development, the best combination was XGBoost ML algorithm with five features from the univariate feature set, including number of antiseizure medications, magnetic resonance imaging lesion, age at seizure onset, videoelectroencephalography concordance, and surgery type, with a mean area under the curve (AUC) of .73 (95% confidence interval [CI] = .69-.77). The combination of XGBoost and univariate feature set was then evaluated on the testing cohort

Background and ObjectivesPurine-rich element-binding protein A (PURA) gene encodes Pur-α, a conserved protein essential for normal postnatal brain development. Recently, a PURA syndrome characterized by intellectual disability, hypotonia, epilepsy, and dysmorphic features was suggested. The aim of this study was to define and expand the phenotypic spectrum of PURA syndrome by collecting data, including EEG, from a large cohort of affected patients.MethodsData on unpublished and published cases were collected through the PURA Syndrome Foundation and the literature. Data on clinical, genetic, neuroimaging, and neurophysiologic features were obtained.ResultsA cohort of 142 patients was included. Characteristics of the PURA syndrome included neonatal hypotonia, feeding difficulties, and respiratory distress. Sixty percent of the patients developed epilepsy with myoclonic, generalized tonic-clonic, focal seizures, and/or epileptic spasms. EEG showed generalized, multifocal, or focal epileptic abnormalities. Lennox-Gastaut was the most common epilepsy syndrome. Drug refractoriness was common: 33.3% achieved seizure freedom. We found 97 pathogenic variants in PURA without any clear genotype-phenotype associations.DiscussionThe PURA syndrome presents with a developmental and epileptic encephalopathy with characteristics recognizable from neonatal age, which should prompt genetic screening. Sixty percent have drug-resistant epilepsy with focal or generalized seizures. We collected more than 90 pathogenic variants without observing overt genotype-phenotype associations.

AISArterial RESULTS Overall, the interval from symptom onset to diagnosis was similar post-protocol compared to pre-protocol (20.3 vs 22.7h; p=0.109), although mild strokes (Pediatric National Institute of Health Stroke Scale [PedNIHSS] 0-4), were diagnosed faster post-protocol (12.1 vs 36.3h; p=0.003). Magnetic resonance imaging (MRI) was the initial diagnostic modality more often post-protocol (25% vs 1.4%; p<0.001). Initial MRI was more accurate for diagnosing stroke than initial CT (100% vs 47%; p<0.001) with similar time-to-diagnosis. The proportion of children receiving antithrombotic medication within 24 hours doubled in the post-protocol period (83% vs 36%; p<0.001).

Aim To determine whether epilepsy surgery improved health‐related quality of life (HRQoL) and whether seizure freedom after surgery mediated the improvement in HRQoL. Method This multicenter cohort study compared HRQoL after epilepsy surgery to pharmacological management in children with drug‐resistant epilepsy (DRE). HRQoL was measured using the Quality of Life in Childhood Epilepsy (QOLCE) questionnaire at baseline and 1‐year follow‐up. The mediator between treatment type and HRQoL was seizure freedom. Results Two hundred and thirty‐seven patients were recruited (surgery group: n=147 [92 males, 45 females]; pharmacological group: n=90 [53 males, 37 females]). Mean age at seizure onset was 6 years (SD 4y 4mo) in the surgical group and 6 years 1 month (SD 4y) in the pharmacological group. The odds ratio of seizure freedom was higher for the surgery versus pharmacological group (β=4.24 [95% confidence interval {CI}: 2.26–7.93], p<0.001). Surgery had no direct effect on total QOLCE score at 1‐year (β=0.24 [95% CI –2.04 to 2.51], p=0.839) compared to pharmacological management, but had an indirect effect on total QOLCE that was mediated by seizure freedom (β=0.92 [95% CI 0.19–1.65], p=0.013), adjusting for baseline total QOLCE score. Surgery had a direct effect on improving social function (p=0.043), and an indirect effect on improving physical function (p=0.016), cognition (p=0.042), social function (p=0.012) and behavior (p=0.032), mediated by seizure freedom. Interpretation Greater seizure freedom achieved through epilepsy surgery mediated the improvement in HRQoL compared to pharmacological management in children with DRE. What this paper adds Seizure freedom is higher after pediatric epilepsy surgery compared to pharmacologically managed epilepsy. Surgery indirectly improves health‐related quality of life (HRQoL) mediated by seizure freedom compared to pharmacological management. Surgery has a direct effect on improving social function relative to pharmacological management. Baseline HRQoL was an important predictor of HRQoL after treatment.