Predictors of Seizure Recurrence in Women With Idiopathic Generalized Epilepsy Who Switch From Valproate to Another Medication.

BACKGROUND AND OBJECTIVES: To investigate the predictors of seizure recurrence in women of childbearing age with idiopathic generalized epilepsy (IGE) who switched from valproate (VPA) to alternative antiseizure medications (ASMs) and compare the effectiveness of levetiracetam (LEV) and lamotrigine (LTG) as VPA alternatives after switch. METHODS: This multicenter retrospective study included women of childbearing age diagnosed with IGE from 16 epilepsy centers. Study outcomes included worsening or recurrence of generalized tonic-clonic seizure (GTCS) at 12 months and 24 months after the switch from VPA to an alternative ASM. The comparative effectiveness of LEV and LTG as alternative ASM following VPA discontinuation was assessed through inverse probability treatment-weighted (IPTW) Cox regression analysis. RESULTS: We included 426 women with IGE, with a median (interquartile range) age at VPA switch of 24 (19-30) years and a median VPA dosage of 750 (500-1,000) mg/d. The most common reason for VPA switch was teratogenicity concern in 249 women (58.6%), and the most common ASM used in place of VPA was LEV in 197 (46.2%) cases, followed by LTG in 140 (32.9%). GTCS worsening/recurrence occurred in 105 (24.6%) and 139 (32.6%) women at 12 and 24 months, respectively. Catamenial worsening of seizures, higher VPA dosage during switch, multiple seizure types, and shorter duration of GTCS freedom before switch were independent predictors of GTCS recurrence or worsening at 12 months according to mixed multivariable logistic regression analysis. After internal-external validation through 16 independent cohorts, the model showed an area under the curve of 0.71 (95% CI 0.64-0.77). In the subgroup of 337 women who switched to LEV or LTG, IPTW Cox regression analysis showed that LEV was associated with a reduced risk of GTCS worsening or recurrence compared with LTG (adjusted hazard ratio 0.59, 95% CI 0.40-0.87, p = 0.008) during the 24-month follow-up. DISCUSSION: Our findings can have practical implications for optimizing counselling and treatment choices in women of childbearing age with IGE and may help clinicians in making informed treatment decisions in this special population of patients. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that for women with IGE switching from VPA, LEV was associated with a reduced risk of GTCS worsening or recurrence compared with LTG.

Brivaracetam use in clinical practice: a Delphi consensus on its role as first add-on therapy in focal epilepsy and beyond.

BACKGROUND: Antiseizure medications remain the cornerstone of treatment for epilepsy, although a proportion of individuals with the condition will continue to experience seizures despite appropriate therapy. Treatment choices for epilepsy are based on variables related to both the individual patient and the available medications. Brivaracetam is a third-generation agent antiseizure medication. METHODS: We carried out a Delphi consensus exercise to define the role of brivaracetam in clinical practice and to provide guidance about its use as first add-on ASM and in selected clinical scenarios. A total of 15 consensus statements were drafted by an expert panel following review of the literature and all were approved in the first round of voting by panelists. The consensus indicated different clinical scenarios for which brivaracetam can be a good candidate for treatment, including first add-on use. RESULTS: Overall, brivaracetam was considered to have many advantageous characteristics that render it a suitable option for patients with focal epilepsy, including a fast onset of action, favorable pharmacokinetic profile with few drug-drug interactions, broad-spectrum activity, and being well tolerated across a range of doses. Brivaracetam is also associated with sustained clinical response and good tolerability in the long term. CONCLUSIONS: These characteristics also make it suitable as an early add-on for the elderly and for patients with post-stroke epilepsy or status epilepticus as highlighted by the present Delphi consensus.

Conversion to Brivaracetam Monotherapy in Clinical Practice: A Retrospective Study.

INTRODUCTION: The study aimed to evaluate the effectiveness and safety of brivaracetam (BRV) as conversion monotherapy in adults with focal epilepsy treated in the context of real-world clinical practice. METHODS: This was a retrospective, observational, non-interventional study in adults with focal epilepsy who converted to BRV monotherapy following the withdrawal of background antiseizure medications (ASMs). Primary effectiveness outcome was the retention rate of BRV as single ASM at 6 and 12 months. Secondary outcomes included the 6- and 12-month rates of seizure freedom. Safety and tolerability outcomes included the frequency and type of adverse events (AEs) and the occurrence of treatment discontinuation due to AEs. RESULTS: A total of 44 participants with a median age of 63.5 (interquartile range 44-73.5) years were included; 17 subjects were seizure free at baseline, and 9 of them switched from levetiracetam because of lack of tolerability. The retention rate of BRV monotherapy was 88.6% (39/44) at 6 months and 83.9% (26/31) at 12 months. The rates of seizure freedom were 72.7% (32/44) in subjects with 6-month follow-up and 58.1% (18/31) in subjects with 12-month follow-up. The median maintenance dosage of BRV monotherapy was 150 (100-200) mg/day at 6 months and 125 (100-200) mg/day in subjects with 12-month follow-up. Adverse events were recorded in 6/44 (13.6%) participants and led to BRV discontinuation in 2/44 (4.5%) cases. The reported AEs were somnolence (n = 3), fatigue (n = 2), and irritability (n = 1); no serious AEs were experienced. In 21/44 (47.7%) participants, BRV monotherapy resulted from the direct switch from levetiracetam. The rates of treatment retention and seizure freedom at 6 and 12 months were higher among people who switched from levetiracetam to BRV monotherapy. CONCLUSION: Brivaracetam may be a valuable treatment of focal seizures in people who converted to monotherapy in a real-life setting.

Myoclonus: Differential diagnosis and current management.

Myoclonus classically presents as a brief (10-50 ms duration), non-rhythmic jerk movement. The etiology could vary considerably ranging from self-limited to chronic or even progressive disorders, the latter falling into encephalopathic pictures that need a prompt diagnosis. Beyond the etiological classification, others evaluate myoclonus' body distribution (i.e., clinical classification) or the location of the generator (i.e., neurophysiological classification); particularly, knowing the anatomical source of myoclonus gives inputs on the observable clinical patterns, such as EMG bursts duration or EEG correlate, and guides the therapeutic choices. Among all the chronic disorders, myoclonus often presents itself as a manifestation of epilepsy. In this context, myoclonus has many facets. Myoclonus occurs as one, or the only, seizure manifestation while it can also present as a peculiar type of movement disorder; moreover, its electroclinical features within specific genetically determined epileptic syndromes have seldom been investigated. In this review, following a meeting of recognized experts, we provide an up-to-date overview of the neurophysiology and nosology surrounding myoclonus. Through the dedicated exploration of epileptic syndromes, coupled with pragmatic guidance, we aim to furnish clinicians and researchers alike with practical advice for heightened diagnostic management and refined treatment strategies. PLAIN LANGUAGE SUMMARY: In this work, we described myoclonus, a movement characterized by brief, shock-like jerks. Myoclonus could be present in different diseases and its correct diagnosis helps treatment.

Topiramate ban in women of childbearing potential with idiopathic generalized epilepsy: Does effectiveness offset the teratogenic risks?

Regulatory agencies have recently discouraged the prescription of topiramate (TPM) to women of childbearing potential with epilepsy due to growing evidence of the teratogenic and neurodevelopmental risks associated with its use during pregnancy. It remains, however, unclear whether the use of TPM in this population can be supported to some extent by its high effectiveness. In this multicenter, retrospective, cohort study performed at 22 epilepsy centers, we investigated the comparative effectiveness of TPM and levetiracetam (LEV) given as first-line antiseizure medication in a cohort of women of childbearing potential with idiopathic generalized epilepsy (IGE). A total of 336 participants were included, of whom 24 (7.1%) received TPM and 312 (92.9%) LEV. Women treated with TPM had significantly higher risks of treatment failure and treatment withdrawal and were less likely to achieve seizure freedom at 12 months compared to women treated with LEV. In conclusion, this study highlighted a low tendency among clinicians to use TPM in women of childbearing potential with IGE, anticipating the recently released restrictions on its use. Furthermore, the available data on effectiveness do not appear to support the use of TPM in this population.

Effect of drug treatment changes and seizure outcomes on depression and suicidality in adults with drug-resistant focal epilepsy.

OBJECTIVE: To investigate changes in depressive and suicidality status and their relationship with seizure outcomes after the addition or substitution of another antiseizure medication (ASM) in adults with drug-resistant focal epilepsy. METHODS: Seven hundred seventy consecutively enrolled patients were assessed and followed prospectively for seizure outcome and depressive status over a 6-month period after starting treatment with a newly introduced ASM. The Neurological Disorders Depression Inventory for Epilepsy (NDDIE) was used to screen for depression and suicidality. Correlations of NDDIE results with clinical and treatment-related variables were assessed by using a stepwise logistic regression model. RESULTS: At baseline, 50% of patients had a positive screening test result for depression and 13% had a positive screening test result for suicidal ideation. A psychiatric comorbidity at baseline was associated with a 2.3 times increased risk of an initially negative NDDIE screening result becoming positive at re-assessment after 6 months. In addition, the number of ASMs taken at baseline correlated with an increased risk of a change in depression screening test results from negative to positive during follow-up, whereas no association was identified with sociodemographic and epilepsy-related variables, including seizure outcomes. Approximately 6% of patients who were initially negative at screening for suicidal ideation became positive at the 6-month re-assessment. The risk of switch from a negative to a positive screening test result for suicidal ideation was increased more than two-fold in individuals who screened positive for depression at baseline, and was unrelated to the type of ASM introduced, sociodemographic variables, or seizure outcomes. SIGNIFICANCE: Almost 1 in 5 adults with drug-resistant focal epilepsy who screen negative for depression become positive when re-assessed 6 months after a treatment change. At re-assessment 6 months later, 6.1% who screen initially negative for passive suicidal ideation become positive. These changes in screening status are independent of type of ASM introduced or seizure outcomes but correlate with psychiatric status at baseline.

Dissecting genetics of spectrum of epilepsies with eyelid myoclonia by exome sequencing.

OBJECTIVE: Epilepsy with eyelid myoclonia (EEM) spectrum is a generalized form of epilepsy characterized by eyelid myoclonia with or without absences, eye closure-induced seizures with electroencephalographic paroxysms, and photosensitivity. Based on the specific clinical features, age at onset, and familial occurrence, a genetic cause has been postulated. Pathogenic variants in CHD2, SYNGAP1, NEXMIF, RORB, and GABRA1 have been reported in individuals with photosensitivity and eyelid myoclonia, but whether other genes are also involved, or a single gene is uniquely linked with EEM, or its subtypes, is not yet known. We aimed to dissect the genetic etiology of EEM. METHODS: We studied a cohort of 105 individuals by using whole exome sequencing. Individuals were divided into two groups: EEM- (isolated EEM) and EEM+ (EEM accompanied by intellectual disability [ID] or any other neurodevelopmental/psychiatric disorder). RESULTS: We identified nine variants classified as pathogenic/likely pathogenic in the entire cohort (8.57%); among these, eight (five in CHD2, one in NEXMIF, one in SYNGAP1, and one in TRIM8) were found in the EEM+ subcohort (28.57%). Only one variant (IFIH1) was found in the EEM- subcohort (1.29%); however, because the phenotype of the proband did not fit with published data, additional evidence is needed before considering IFIH1 variants and EEM- an established association. Burden analysis did not identify any single burdened gene or gene set. SIGNIFICANCE: Our results suggest that for EEM, as for many other epilepsies, the identification of a genetic cause is more likely with comorbid ID and/or other neurodevelopmental disorders. Pathogenic variants were mostly found in CHD2, and the association of CHD2 with EEM+ can now be considered a reasonable gene-disease association. We provide further evidence to strengthen the association of EEM+ with NEXMIF and SYNGAP1. Possible new associations between EEM+ and TRIM8, and EEM- and IFIH1, are also reported. Although we provide robust evidence for gene variants associated with EEM+, the core genetic etiology of EEM- remains to be elucidated.

A real-world comparison among third-generation antiseizure medications: Results from the COMPARE study.

OBJECTIVE: There are few comparative data on the third-generation antiseizure medications (ASMs). We aimed to assess and compare the effectiveness of brivaracetam (BRV), eslicarbazepine acetate (ESL), lacosamide (LCM), and perampanel (PER) in people with epilepsy (PWE). Efficacy and tolerability were compared as secondary objectives. METHODS: This multicenter, retrospective study collected data from 22 Italian neurology/epilepsy centers. All adult PWE who started add-on treatment with one of the studied ASMs between January 2018 and October 2021 were included. Retention rate was established as effectiveness measure and described using Kaplan-Meier curves and the best fitting survival model. The responder status and the occurrence of adverse events (AEs) were used to evaluate efficacy and safety, respectively. The odds of AEs and drug efficacy were estimated by two multilevel logistic models. RESULTS: A total of 960 patients (52.92% females, median age = 43 years) met the inclusion criteria. They mainly suffered from structural epilepsy (52.29%) with monthly (46.2%) focal seizures (69.58%). Compared with LCM, all the studied ASMs had a higher dropout risk, statistically significant in the BRV levetiracetam (LEV)-naïve (hazard ratio [HR] = 1.97, 95% confidence interval [CI] = 1.17-3.29) and PER groups (HR = 1.64, 95% CI = 1.06-2.55). Women were at higher risk of discontinuing ESL (HR = 5.33, 95% CI = 1.71-16.61), as well as PER-treated patients with unknown epilepsy etiology versus those with structural etiology (HR = 1.74, 95% CI = 1.05-2.88). BRV with prior LEV therapy showed lower odds of efficacy (odds ratio [OR] = .08, 95% CI = .01-.48) versus LCM, whereas a higher efficacy was observed in women treated with BRV and LEV-naïve (OR = 10.32, 95% CI = 1.55-68.78) versus men. PER (OR = 6.93, 95% CI = 3.32-14.44) and BRV in LEV-naïve patients (OR = 6.80, 95% CI = 2.64-17.52) had a higher chance of AEs than LCM. SIGNIFICANCE: Comparative evidence from real-world studies may help clinicians to tailor treatments according to patients' demographic and clinical characteristics.

Use, experience and perspectives of high-density EEG among Italian epilepsy centers: a national survey.

INTRODUCTION: High-density EEG (hdEEG) is a validated tool in presurgical evaluation of people with epilepsy. The aim of this national survey is to estimate diffusion and knowledge of hdEEG to develop a network among Italian epilepsy centers. METHODS: A survey of 16 items (and 15 additional items) was distributed nationwide by email to all members of the Italian League Against Epilepsy and the Italian Society of Clinical Neurophysiology. The data obtained were analyzed using descriptive statistics. RESULTS: A total of 104 respondents were collected from 85 centers, 82% from the Centre-North of Italy; 27% of the respondents had a hdEEG. The main applications were for epileptogenic focus characterization in the pre-surgical evaluation (35%), biomarker research (35%) and scientific activity (30%). The greatest obstacles to hdEEG were economic resources (35%), acquisition of dedicated personnel (30%) and finding expertise (17%). Dissemination was limited by difficulties in finding expertise and dedicated personnel (74%) more than buying devices (9%); 43% of the respondents have already published hdEEG data, and 91% of centers were available to participate in multicenter hdEEG studies, helping in both pre-processing and analysis. Eighty-nine percent of respondents would be interested in referring patients to centers with established experience for clinical and research purposes. CONCLUSIONS: In Italy, hdEEG is mainly used in third-level epilepsy centers for research and clinical purposes. HdEEG diffusion is limited not only by costs but also by lack of trained personnel. Italian centers demonstrated a high interest in educational initiatives on hdEEG as well as in clinical and research collaborations.

Adjunctive brivaracetam and sustained seizure frequency reduction in very active focal epilepsy.

OBJECTIVE: This study aimed to explore the effectiveness of brivaracetam (BRV) according to baseline seizure frequency and past treatment history in subjects with focal epilepsy who were included in the Brivaracetam Add-On First Italian Network Study (BRIVAFIRST). METHODS: BRIVAFIRST was a 12-month retrospective, multicenter study including adults prescribed adjunctive BRV. Study outcomes included sustained seizure response (SSR), sustained seizure freedom (SSF), and the rates of treatment discontinuation and adverse events (AEs). Baseline seizure frequency was stratified as <5, 5-20, and >20 seizures per month, and the number of prior antiseizure medications (ASMs) as <5 and ≥6. RESULTS: A total of 994 participants were included. During the 1-year study period, SSR was reached by 45.8%, 39.3%, and 22.6% of subjects with a baseline frequency of <5, 5-20, and >20 seizures per month (p < .001); the corresponding figures for the SSF were 23.4%, 9.8%, and 2.8% (p < .001). SSR was reached by 51.2% and 26.5% participants with a history of 1-5 and ≥6 ASMs (p < .001); the corresponding rates of SSF were 24.7% and 4.5% (p < .001). Treatment discontinuation due to lack of efficacy was more common in participants with >20 seizures compared to those with <5 seizures per month (25.8% vs. 9.3%, p < .001), and in participants with history of ≥6 prior ASMs compared to those with history of 1-5 ASMs (19.6% vs. 12.2%, p = .002). There were no differences in the rates of BRV withdrawal due to AEs and the rates of AEs across the groups of participants defined according to the number of seizures at baseline and the number of prior ASMs. SIGNIFICANCE: The baseline seizure frequency and the number of previous ASMs were predictors of sustained seizure frequency reduction with adjunctive BRV in subjects with focal epilepsy.

Perampanel as only add-on epilepsy treatment in elderly: A subgroup analysis of real-world data from retrospective, multicenter, observational study.

INTRODUCTION: Drug management of epilepsy in the elderly presents unique but data on this population are scarce. This study aimed to assess the effectiveness and tolerability of perampanel (PER) used as only add-on to a background anti-seizure medication (ASM) in the elderly in a real-world setting. METHODS: We performed a subgroup analysis of patients aged ≥65 years included in a previous 12-month multicenter study on adults. Treatment discontinuation, seizure frequency, and adverse events were recorded at 3, 6 and 12 months after PER introduction. Sub-analyses by early (≤1 previous ASM) or late PER add-on were also conducted. RESULTS: The sample included 65 subjects (mean age: 75.7 ± 7.2 years), with mainly focal (73.8%) epilepsy. The mean PER daily dose was ≈4 mg during all follow-up. Retention rates at 3, 6, and 12 months were 90.5%, 89.6%, and 79.4%ly. The baseline median normalized per 28-day seizure number significantly decreased at 3-, 6- and 12-month visits. One year after PER introduction, the responder rate (≥50% reduction in baseline seizure frequency) was 89.7%, with a seizure freedom rate of 72.4%. Adverse events occurred in 22 (34.9%) patients with dizziness and irritability being the most frequent. No major differences between early (41 patients, 63.1%), and late add-on groups were observed. CONCLUSION: Adjunctive PER was effective and well-tolerated when used as only add-on treatment in elderly people with epilepsy in clinical practice, thus representing a suitable therapeutic option in this age category.

Levetiracetam vs Lamotrigine as First-Line Antiseizure Medication in Female Patients With Idiopathic Generalized Epilepsy.

Importance: After the recent limitations to prescribing valproate, many studies have highlighted the challenging management of female patients of reproductive age with idiopathic generalized epilepsy (IGE). However, no study, to the authors' knowledge, has addressed the comparative effectiveness of alternative antiseizure medications (ASMs) in these patients. Objective: To compare the effectiveness and safety of levetiracetam and lamotrigine as initial monotherapy in female patients of childbearing age with IGE. Design, Setting, and Participants: This was a multicenter, retrospective, comparative effectiveness cohort study analyzing data from patients followed up from 1994 to 2022. Patients were recruited from 22 primary, secondary, and tertiary adult and child epilepsy centers from 4 countries. Eligible patients were female individuals of childbearing age, diagnosed with IGE according to International League Against Epilepsy (2022) criteria and who initiated levetiracetam or lamotrigine as initial monotherapy. Patients were excluded due to insufficient follow-up after ASM prescription. Exposures: Levetiracetam or lamotrigine as initial monotherapy. Main Outcomes and Measures: Inverse probability of treatment weighting (IPTW)-adjusted Cox proportional hazards regression was performed to compare treatment failure (TF) among patients who received levetiracetam or lamotrigine as initial monotherapy. Results: A total of 543 patients were included in the study, with a median (IQR) age at ASM prescription of 17 (15-21) years and a median (IQR) follow-up of 60 (24-108) months. Of the study population, 312 patients (57.5%) were prescribed levetiracetam, and 231 (42.5%) were prescribed lamotrigine. An IPTW-adjusted Cox model showed that levetiracetam was associated with a reduced risk of treatment failure after adjustment for all baseline variables (IPTW-adjusted hazard ratio [HR], 0.77; 95% CI, 0.59-0.99; P = .04). However, after stratification according to different IGE syndromes, the higher effectiveness of levetiracetam was confirmed only in patients with juvenile myoclonic epilepsy (JME; IPTW-adjusted HR, 0.47; 95% CI, 0.32-0.68; P < .001), whereas no significant differences were found in other syndromes. Patients treated with levetiracetam experienced adverse effects more frequently compared with those treated with lamotrigine (88 of 312 [28.2%] vs 42 of 231 [18.1%]), whereas the 2 ASMs had similar retention rates during follow-up (IPTW-adjusted HR, 0.91; 95% CI, 0.65-1.23; P = .60). Conclusions and Relevance: Results of this comparative effectiveness research study suggest the use of levetiracetam as initial alternative monotherapy in female patients with JME. Further studies are needed to identify the most effective ASM alternative in other IGE syndromes.

Late-onset fabry disease due to the p.Phe113Leu variant: the first italian cluster of five families.

BACKGROUND: The GLA c.337T > C (p.Phe113Leu) is a known pathogenic variant associated to late-onset Fabry disease phenotype with predominant cardiac manifestations. A founder effect was demonstrated in a large cohort in the Portuguese region of Guimarães. Herein we report an in-depth phenotype description of a cluster of five Southern Italy families. METHODS: Family pedigrees of five index males with the p.Phe113Leu variant were obtained and all at-risk relatives underwent biochemical and genetical screening test. Carriers of GLA p.Phe113Leu variant underwent subsequent multidisciplinary clinical and instrumental evaluation. RESULTS: Thirty-one (16 M, 15 F) individuals with p.Phe113Leu pathogenic variant were identified. Sixteen out of 31 patients (51.6%) had cardiac manifestations. Notably, myocardial fibrosis was found in 7/8 patients, of whom 2 were under 40 years. Stroke occurred in 4 patients. White matter lesions were detected in 12/19 patients and occurred in 2/10 of subjects under 40 years. Seven females complained of acroparesthesias. Renal involvement occurred in 10 patients. Angiokeratomas were evident in 9 subjects. Eyes, ear, gastrointestinal and pulmonary involvement occurred in the minority of subjects. CONCLUSION: This study demonstrates that a cluster of subjects with p.Phe113Leu pathogenic variant is also present in Southern Italy. Disease manifestations are frequent in both sexes and may occur early in life. Cardiac involvement represents the core manifestation, but neurological and renal involvement is also frequent, suggesting that extra-cardiac complications deserve clinical attention.

Epilepsy in Cerebrovascular Diseases: A Narrative Review.

BACKGROUND: Epilepsy is a common comorbidity of cerebrovascular disease and an increasing socioeconomic burden. OBJECTIVE: We aimed to provide an updated comprehensive review on the state of the art about seizures and epilepsy in stroke, cerebral haemorrhage, and leukoaraiosis. METHODS: We selected English-written articles on epilepsy, stroke, and small vessel disease up until December 2021. We reported the most recent data about epidemiology, pathophysiology, prognosis, and management for each disease. RESULTS: The main predictors for both ES and PSE are the severity and extent of stroke, the presence of cortical involvement and hemorrhagic transformation, while PSE is also predicted by younger age at stroke onset. Few data exist on physiopathology and seizure semiology, and no randomized controlled trial has been performed to standardize the therapeutic approach to post-stroke epilepsy. CONCLUSION: Some aspects of ES and PSE have been well explored, particularly epidemiology and risk factors. On the contrary, few data exist on physiopathology, and existing evidence is mainly based on studies on animal models. Little is also known about seizure semiology, which may also be difficult to interpret by non-epileptologists. Moreover, the therapeutic approach needs standardization as regards indications and the choice of specific ASMs. Future research may help to better elucidate these aspects.

Convolutional Neural Network Classification of Rest EEG Signals among People with Epilepsy, Psychogenic Non Epileptic Seizures and Control Subjects.

Identifying subjects with epileptic seizures or psychogenic non-epileptic seizures from healthy subjects via interictal EEG analysis can be a very challenging issue. Indeed, at visual inspection, EEG can be normal in both cases. This paper proposes an automatic diagnosis approach based on deep learning to differentiate three classes: subjects with epileptic seizures (ES), subjects with non-epileptic psychogenic seizures (PNES) and control subjects (CS), analyzed by non-invasive low-density interictal scalp EEG recordings. The EEGs of 42 patients with new-onset ES, 42 patients with PNES video recorded and 19 patients with CS all with normal interictal EEG on visual inspection, were analyzed in the study; none of them was taking psychotropic drugs before registration. The processing pipeline applies empirical mode decomposition (EMD) to 5s EEG segments of 19 channels in order to extract enhanced features learned automatically from the customized convolutional neural network (CNN). The resulting CNN has been shown to perform well during classification, with an accuracy of 85.7%; these results encourage the use of deep processing systems to assist clinicians in difficult clinical settings.