Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence.

Introduction: Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment. Methods: In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects). Results: At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h. Discussion: These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Rare encounter: Adult-onset temporal lobe schizencephaly with septo-optic dysplasia - a case report on comprehensive diagnosis and management.

This case report presents a 21-year-old male with recurrent seizures attributed to isolated temporal lobe closed-lip schizencephaly coexisting with septo-optic dysplasia. Despite adult-onset seizures, the patient lacked motor deficits, maintaining normal developmental milestones. Comprehensive diagnostic modalities, including MRI revealing temporal lobe atrophy and associated abnormalities, contributed to the unique identification of schizencephaly. The classic triad of septo-optic dysplasia further complicated the clinical spectrum. Financial limitations influenced the predominantly conservative management, highlighting healthcare challenges. This case enhances our understanding of the rare congenital disorder, emphasizing the importance of tailored diagnostics and management strategies for diverse presentations of schizencephaly, particularly in the context of associated congenital anomalies.

The effect of the coronavirus vaccinations on seizures in patients with epilepsy.

Purpose: Information on COVID-19 vaccine tolerance and complications in patients with epilepsy is not yet sufficient to provide a recommendation for vaccination guidelines. The aim of this study was to investigate the effect of two types of COVID vaccines currently used in Turkey (mRNA vaccine from Pfizer/BioNTech and inactivated vaccine from Sinovac) on epileptic seizures. Methods: We included 318 patients with epilepsy who were admitted to our epilepsy outpatient clinic. Clinical characteristics such as age, gender, age at seizure onset and the duration of epilepsy were noted. Types and the numbers of the anti-seizure drugs were recorded. Patients were evaluated either by face-to-face or by teleconference interviews. The seizure frequency in the first thirty days after any dose of vaccination was questioned. Results: A total of 318 patients (149 females, 46.8%) with a confirmed diagnosis of epilepsy were enrolled in the study. An increase in seizure frequency was reported after the COVID-19 vaccine in 19 patients. Of these 19 patients, 2 were vaccinated with Sinovac, while 17 were vaccinated with BioNTech/Pfizer mRNA vaccine. There was no significant relationship between age, age at seizure onset, duration of epilepsy, type of seizures, seizure frequency or seizure induction. Status epilepticus was not reported in any of the participants. Conclusion: Physicians need strong scientific evidence to advocate the importance of vaccine for COVID-19, that's why accumulation of knowledge related to this issue is important not only from medical but also from medico-legal point of interest. We aimed to contribute the current literature with our study to strengthen the physicians' hand while recommending COVID vaccines to PWE. Our results show that there is no significant increase in the risk of triggering seizures with COVID-19 vaccines. These data show that vaccination against COVID-19 with both vaccine types in patients with epilepsy is safe and well tolerated.

The influence of concomitant antidepressant and antipsychotic medication on antidepressant effect and seizure duration of electroconvulsive therapy.

Background: A significant proportion of patients with a depressive disorder show resistance to pharmacological and psychotherapeutic antidepressant treatments. Electroconvulsive therapy (ECT) is still one of the most effective treatment methods, especially in the acute phase. In everyday clinical practice, this usually accompanies pharmacological treatment. It has been shown that pharmacological treatment following acute ECT treatment reduces the rate of relapses. However, the effect of various antidepressants (ADs) and antipsychotics (APs) on the effect during the course of ECT has rarely been investigated. Methods: In this retrospective chart review study, the data of 104 depressive patients treated with ECT were examined. We analyzed the influence of concomitant administration of AD and AP or no psychotropic medication on the effect of ECT using the Montgomery-Åsberg Depression Rating Scale (MADRS). We further analyzed the influence of the ADs Bupropion, Venlafaxine, and Sertraline or no AD and the influence of augmentation with Aripiprazole or Quetiapine or Olanzapine. Results/discussion: Psychotropic medication did not have an impact on antidepressant efficacy of ECT as measured with the MADRS scores. In addition, the comparison between the antidepressant or antipsychotic medications themselves did not show any significant difference. However, we found a significantly different seizure duration depending on the antidepressant substance that patients received during ECT (p = .008). ECT treatment itself led to a highly significant reduction of 13.3 points in the MADRS (p <.001). Conclusion: Taken together, our study underlines that concomitant psychotropic medication while doing electroconvulsive therapy does not bare the risk of prolonged seizure duration or does it reduce the effectiveness of ECT. To the best of our knowledge, this study is the first to examine the effect of treatment with antidepressants in combination with antipsychotics while doing ECT. In light of our results, this combination therapy is safe and effective. Bearing in mind the delay in onset of antidepressant action of medication and the importance of antidepressant medication for relapse prevention, this study further supports the recommendation that psychotropic medication should be given in adjunction to ECT.

Association between dietary carbohydrate intake percentage and epilepsy prevalence in the NHANES 2013-2018: a cross-sectional study.

BACKGROUND: Epilepsy is a neurological disorder characterized by recurrent seizures. We aimed to investigate the association between the percentage of dietary carbohydrate intake (DCI) and epilepsy prevalence among American adults. METHODS: We analyzed the data from 9,584 adults aged 20-80 years who participated in the National Health and Nutrition Examination Survey from 2013 to 2018. Logistic regression was applied to explore the association between the percentage of DCI and epilepsy prevalence. RESULTS: A total of 146 (1.5%) individuals with epilepsy were enrolled in this study. The average age of the participants was 56.4 years, and 5,454 (56.9%) individuals were female. A high DCI was associated with an increased prevalence of epilepsy (odds ratio [OR], 4.56; 95% confidence interval [CI], 1.11-18.69; P = 0.035) after adjusting for age, sex, marital status, race/ethnicity, educational level, family income, body mass index, smoking status, drinking status, hypertension, diabetes, and cardiovascular disease. Stratified analyses indicated a positive correlation between DCI and epilepsy prevalence in adults with different characteristics. Compared with individuals in quartile 1 of DCI (<40.5%), those in quartile 4 (>55.4%) had an adjusted OR for epilepsy of 1.72 (95% CI, 1.09-2.73, P = 0.02, P for trend = 0.012). CONCLUSIONS: A high percentage of DCI was associated with an increased prevalence of epilepsy. The risk of epilepsy increased 3.5-fold with a 1% increase in DCI. These results suggest an important role of DCI in the dietary management of epilepsy.

Ictal kissing: Review of literature and report of 5 cases.

Ictal kissing (IK) is a rare type of automatism observed during epileptic seizures. Despite its uncommon occurrence, understanding the underlying mechanisms, the role of emotions, and the level of consciousness during seizures with IK is essential in providing a comprehensive understanding of epilepsy. We describe five cases (.13%) of IK after performing a retrospective analysis of 3794 long-term, ictal video-EEGs from an epilepsy monitoring unit in Mumbai, India. Our patients with drug-resistant epilepsy showed IK had a wide epileptogenic zone. We discuss the current hypotheses on the mechanisms behind IK, the involvement of temporal lobe structures, and the implications of awareness during seizures. The review concludes by suggesting future directions for research to elucidate the complex phenomenon of IK further.

Contemporary Insights into Intractable Epilepsy in Children.

While most children with epilepsy find their seizures manageable through medication, some continue to experience seizures despite trying multiple drugs. Failure of medical treatment often becomes apparent early on, and for these cases, it is advisable to seek further treatment options at a specialized epilepsy center. Such centers offer additional treatments like epilepsy surgery, vagus nerve stimulation, and ketogenic diets. There is no universal definition for what constitutes "medically intractable" epilepsy. A proposal by a task force from the International League Against Epilepsy suggests that drug-resistant epilepsy could be defined as the inability to control seizures even after two adequate treatment attempts with well-chosen and tolerated medications, either alone or in combination. In this review, the authors discussed the management of intractable epilepsy in children.

Congenital continuous retrograde basilar flow suggests type B interrupted aortic arch in a neonate: A case report.

Reversed flow in the basilar artery can be acquired or congenital. Acquired reversed flow in the basilar artery can result from acute thrombosis of the basilar artery or retrograde vertebral artery flow. Congenital continuous retrograde basilar artery flow has not been described. We report a 2-day-old male presenting with hypocalcemic seizures which led us to obtain a Duplex echoencephalogram. An echocardiogram was subsequently ordered. In the coronal plane through the anterior fontanelle, retrograde flow was seen in the basilar artery and the right vertebral artery. In the axial plane through the temporal window, the flow was anteroposterior in both posterior communicating arteries. In the posterior cerebral arteries, the flow was retrograde in the P1 segment and anterograde in the P2 and P3 segments. An interrupted aortic arch was suspected. The echocardiogram showed a large perimembranous ventricular septal defect with bidirectional shunting, a hypoplastic and bicuspid aortic valve, an aortic arch interrupted between the left common carotid artery and the left subclavian artery (type B interrupted aortic arch), and a 5 mm patent ductus arteriosus with predominant right to left flow. Because of the patency of the large patent ductus arteriosus, our patient showed no sign of posterior circulation insufficiency. Prostaglandin E1 therapy was initiated immediately. Diagnosis of DiGeorge syndrome was proven. The infant underwent interrupted aortic arch repair and anterograde flow was established in the basilar artery. We conclude that congenital asymptomatic continuous retrograde flow in the basilar artery and left vertebral artery is a medical emergency as it implies the presence of type B interrupted aortic arch with large patent ductus arteriosus in a neonate.

Orthogonal extended infomax algorithm.

Objective.The extended infomax algorithm for independent component analysis (ICA) can separate sub- and super-Gaussian signals but converges slowly as it uses stochastic gradient optimization. In this paper, an improved extended infomax algorithm is presented that converges much faster.Approach.Accelerated convergence is achieved by replacing the natural gradient learning rule of extended infomax by a fully-multiplicative orthogonal-group based update scheme of the ICA unmixing matrix, leading to an orthogonal extended infomax algorithm (OgExtInf). The computational performance of OgExtInf was compared with original extended infomax and with two fast ICA algorithms: the popular FastICA and Picard, a preconditioned limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm belonging to the family of quasi-Newton methods.Main results.OgExtInf converges much faster than original extended infomax. For small-size electroencephalogram (EEG) data segments, as used for example in online EEG processing, OgExtInf is also faster than FastICA and Picard.Significance.OgExtInf may be useful for fast and reliable ICA, e.g. in online systems for epileptic spike and seizure detection or brain-computer interfaces.

Perifocal edema is a risk factor for preoperative seizures in patients with meningioma WHO grade 2 and 3.

BACKGROUND: Patients with intracranial meningiomas frequently suffer from tumor-related seizures prior to resection, impacting patients' quality of life. We aimed to elaborate on incidence and predictors for seizures in a patient cohort with meningiomas WHO grade 2 and 3. METHODS: We retrospectively searched for patients with meningioma WHO grade 2 and 3 according to the 2021 WHO classification undergoing tumor resection. Clinical, histopathological and imaging findings were collected and correlated with preoperative seizure development. Tumor and edema volumes were quantified. RESULTS: Ninety-five patients with a mean age of 59.5 ± 16.0 years were included. Most tumors (86/95, 90.5%) were classified as atypical meningioma WHO grade 2. Nine of 95 tumors (9.5%) corresponded to anaplastic meningiomas WHO grade 3, including six patients harboring TERT promoter mutations. Meningiomas were most frequently located at the convexity in 38/95 patients (40.0%). Twenty-eight of 95 patients (29.5%) experienced preoperative seizures. Peritumoral edema was detected in 62/95 patients (65.3%) with a median volume of 9 cm3 (IR: 0-54 cm3). Presence of peritumoral edema but not age, tumor localization, TERT promoter mutation, brain invasion or WHO grading was associated with incidence of preoperative seizures, as confirmed in multivariate analysis (OR: 6.61, 95% CI: 1.18, 58.12, p = *0.049). Postoperative freedom of seizures was achieved in 91/95 patients (95.8%). CONCLUSIONS: Preoperative seizures were frequently encountered in about every third patient with meningioma WHO grade 2 or 3. Patients presenting with peritumoral edema on preoperative imaging are at particular risk for developing tumor-related seizures. Tumor resection was highly effective in achieving seizure freedom.

Giant frontal sinus mucocele mimicked a primary brain tumor: A case report.

INTRODUCTION: Frontal sinus mucoceles commonly manifest with orbital complications. Intracranial complications, though rare, are significant in the differential diagnosis. Tumefactive and giant mucoceles can resemble intracranial tumors. CASE PRESENTATION: We present the case of a 24-year-old male patient who initially presented to our institution after experiencing a single generalized tonic-clonic seizure. Initial imaging revealed large masses in both frontal lobes. Surgical intervention revealed mucoceles originating from the frontal and paranasal sinuses. DISCUSSION: Mucoceles are often misdiagnosed due to the wide variety of symptoms they can present. In particular, the tumefactive type of mucoceles can present brain tumors both clinically and radiologically. CONCLUSION: Mucoceles can manifest as tumefactive lesions, mimicking intracranial masses, and may present as perplexing neurological conditions.

Seizures as presentation of shunt malfunction: tertiary paediatric neurosurgery experience.

AIM: Patients with a background of cerebrospinal fluid (CSF)-diverting shunts are frequently investigated for shunt malfunction when presenting with seizures. However, there is very limited evidence in the literature regarding the association of seizures and shunt malfunction. We sought to determine the incidence of shunt malfunction in our cohort of shunted paediatric patients presenting with seizures, and the utility of seizures as a marker of shunt malfunction. METHODS: We retrospectively identified all shunted patients presenting with seizures, as well as all patients undergoing shunt revision following a presentation with seizures from our hospital database over a 14-year period from 2009 to 2023. Data gathered included demographics, de novo seizures or change in pattern of seizures, the aetiology of hydrocephalus and the segment of shunt requiring revision. Exclusion criteria included infected cases requiring shunt externalisation. A literature review of all papers discussing seizures as a presentation of shunt malfunction was also carried out. RESULTS: Overall, over a 14-year period of study, 338 shunted patients presented with seizures and were referred as suspected shunt malfunction with 10 having confirmed shunt malfunction requiring revision (2.9%). This group represented 6.2% of 161 cases of shunt revision carried out during the 14-year period of study. Post-haemorrhagic hydrocephalus secondary to prematurity was the commonest aetiology of shunted hydrocephalus presenting with seizures. Out of 10 patients presenting with seizures with shunt malfunction, 4 presented with de novo seizures, while 6 presented with a change in seizure pattern or frequency in already known epileptic patients. Shunt revision surgeries included 5 distal catheter, 2 proximal catheter, 1 proximal catheter-valve, 1 valve only and 1 case of whole shunt change. CONCLUSION: Our data supports that seizures are rare manifestation of shunt malfunction and can present either de novo or with a change in seizure frequency in already-known epileptic patients.

Spatial and temporal properties of intra-operatively recorded spikes and high frequency oscillations in focal cortical dysplasia.

OBJECTIVE: Focal cortical dysplasias (FCD) are characterized by distinct interictal spike patterns and high frequency oscillations (HFOs; ripples: 80-250 Hz; fast ripples: 250-500 Hz) in the intra-operative electrocorticogram (ioECoG). We studied the temporal relation between intra-operative spikes and HFOs and their relation to resected tissue in people with FCD with a favorable outcome. METHODS: We included patients who underwent ioECoG-tailored epilepsy surgery with pathology confirmed FCD and long-term Engel 1A outcome. Spikes and HFOs were automatically detected and visually checked in 1-minute pre-resection-ioECoG. Channels covering resected and non-resected tissue were compared using a logistic mixed model, assessing event numbers, co-occurrence ratios, and time-based properties. RESULTS: We found pre-resection spikes, ripples in respectively 21 and 20 out of 22 patients. Channels covering resected tissue showed high numbers of spikes and HFOs, and high ratios of co-occurring events. Spikes, especially with ripples, have a relatively sharp rising flank with a long descending flank and early ripple onset over resected tissue. CONCLUSIONS: A combined analysis of event numbers, ratios, and temporal relationships between spikes and HFOs may aid identifying epileptic tissue in epilepsy surgery. SIGNIFICANCE: This study shows a promising method for clinically relevant properties of events, closely associated with FCD.

Assessment of knowledge towards first aid skills of epilepsy among undergraduate health students in Riyadh province of Saudi Arabia: A cross-sectional study.

BACKGROUND: Applying proper first-aid measures to patients with seizure episodes plays a vital role in preventing the adverse consequences of seizures. Most previous data focused on teachers, healthcare providers and the general public. This study aimed to assess the knowledge of seizure first-aid measures among undergraduate health students. METHODS: This descriptive, cross-sectional study was conducted between May 16 and 31, 2023, with 493 undergraduate health students of Riyadh Province who answered online surveys. The data were collected using the descriptive information form. The chi-square (χ2) test was employed to compare knowledge of seizure first aid between demographic variables. The relationship between knowledge score and independent variables was evaluated using multiple linear regression technique. RESULTS: Only 1.6 % of participants demonstrated good knowledge scores toward seizure first-aid measures. The skill most frequently reported was to remove all harmful objects from their vicinity and loosen the tight clothes around the neck during a seizure; 68.7 % of the participants correctly answered with agreed. Conversely, the skill that received the lowest knowledge score among participants was putting a piece object such as a cloth, wallet, or spoon between the teeth to prevent tongue biting during a seizure; only 37.3 % of the participants correctly answered with disagree. Moreover, participants in the advanced age group, medicine and fifth-year, were found to be significant predictors of knowledge and exhibited better knowledge scores toward seizure first aid measures than their peers (p < 0.001). Furthermore, lectures and books were identified (69.6 %) as the most common source of information about seizure first aid. CONCLUSION: The study concluded that most undergraduate health students demonstrated poor knowledge scores in delivering seizure first aid. This finding suggests that introducing epilepsy education from the first year in all health-related courses is crucial to improving overall awareness and skills in providing seizure first aid.

Dravet syndrome seizure frequency and clustering: Placebo-treated patients in clinical trials.

OBJECTIVE: Dravet syndrome is a rare developmental epilepsy syndrome associated with severe, treatment-resistant seizures. Since seizures and seizure clusters are linked to morbidity, reduced quality of life, and premature mortality, a greater understanding of these outcomes could improve trial designs. This analysis explored seizure types, seizure clusters, and factors affecting seizure cluster variability in Dravet syndrome patients. METHODS: Pooled post-hoc analyses were performed on data from placebo-treated patients in GWPCARE 1B and GWPCARE 2 randomized controlled phase III trials comparing cannabidiol and placebo in Dravet syndrome patients aged 2-18 years. Multivariate stepwise analysis of covariance of log-transformed convulsive seizure cluster frequency was performed, body weight and body mass index z-scores were calculated, and incidence of adverse events was assessed. Data were summarized in three age groups. RESULTS: We analyzed 124 placebo-treated patients across both studies (2-5 years: n = 35; 6-12 years: n = 52; 13-18 years: n = 37). Generalized tonic-clonic seizures followed by myoclonic seizures were the most frequent seizure types. Mean and median convulsive seizure cluster frequency overall decreased between baseline and maintenance period but did not change significantly during the latter; variation in convulsive seizure cluster frequency was observed across age groups. Multivariate analysis suggested correlations between convulsive seizure cluster frequency and age (positive), and body mass index (BMI) (negative). INTERPRETATION: Post-hoc analyses suggested that potential relationships could exist between BMI, age and convulsive seizure cluster variation. Results suggested that seizure cluster frequency may be a valuable outcome in future trials. Further research is needed to confirm our findings.

Detection of seizure onset in childhood absence epilepsy.

OBJECTIVE: This study aims to detect the seizure onset, in childhood absence epilepsy, as early as possible. Indeed, interfering with absence seizures with sensory simulation has been shown to be possible on the condition that the stimulation occurs soon enough after the seizure onset. METHODS: We present four variations (two supervised, two unsupervised) of an algorithm designed to detect the onset of absence seizures from 4 scalp electrodes, and compare their performance with that of a state-of-the-art algorithm. We exploit the characteristic shape of spike-wave discharges to detect the seizure onset. Their performance is assessed on clinical electroencephalograms from 63 patients with confirmed childhood absence epilepsy. RESULTS: The proposed approaches succeed in early detection of the seizure onset, contrary to the classical detection algorithm. Indeed, the results clearly show the superiority of the proposed methods for small delays of detection, under 750 ms from the onset. CONCLUSION: The performance of the proposed unsupervised methods is equivalent to that of the supervised ones. The use of only four electrodes makes the pipeline suitable to be embedded in a wearable device. SIGNIFICANCE: The proposed pipelines perform early detection of absence seizures, which constitutes a prerequisite for a closed-loop system.

Anticipatory anxiety of seizures in epilepsy: A common, complex, and underrecognized phenomenon?

The diagnosis of epilepsy is associated with loss of predictability, which invariably results in the fear of when and if future seizures will occur. For a subset of patients with epilepsy (PWE), there may be a pathological persistent fear of seizure occurrence, resulting in limitations to daily activities through avoidant behaviors. Paradoxically, the research of anticipatory anxiety of seizures (AAS; also referred to as seizure phobia) has been practically nonexistent and, not surprisingly, this condition remains underrecognized by clinicians. The available data are derived from three small case series of patients followed in tertiary epilepsy centers. In this study, we review the available data on the reported clinical manifestations of AAS in PWE, and of the potential role of variables associated with it, such as personal and family psychosocial and psychiatric history and epilepsy-related variables. In addition, we review the need for the creation of screening tools to identify patients at risk of AAS and discuss potential treatment strategies, which could be considered as part of the comprehensive management for PWE.

A systematic review and meta-analysis on efficacy and safety of Ganaxolone in epilepsy.

INTRODUCTION: Ganaxolone has exhibited potential in managing seizures for epilepsy. This systematic review and meta-analysis aim to assess both the safety and efficacy of Ganaxolone for refractory epilepsy. METHODS: A thorough search of electronic databases was conducted to identify relevant randomized controlled trials involving patients with drug-resistant focal epilepsy and CDKL5 deficiency disorder. Efficacy and safety outcomes were extracted from the selected studies. Cochrane Review Manager was utilized for data synthesis and analysis, with risk ratios and mean differences calculated to evaluate the efficacy and safety profile of Ganaxolone. RESULTS: The meta-analysis included a total of five randomized controlled trials. Ganaxolone exhibited significant efficacy in reducing seizure frequency by at least 50% from baseline [RR 0.90 (95% CI: 0.83, 0.98), p = 0.02]. However, the results did not reach significance for reducing 28-day seizure frequency [Mean Difference -1.45 (95% CI: -3.39, 0.49), p = 0.14]. Ganaxolone exhibited a positive safety profile, with no statistically significant occurrence of adverse events [RR 1.30 (95% CI: 0.93, 1.83), p = 0.12] and adverse events leading to discontinuation of the study drug [RR 1.01 (95% CI: 0.42, 2.39), p = 0.99] compared to placebo. CONCLUSION: Ganaxolone presents itself as a viable therapeutic option for refractory epilepsy, showing efficacy in reducing seizure frequency and exhibited a favorable safety profile. PROSPERO REGISTRATION NUMBER: CRD42023434883.

The multifaceted role of Wnt canonical signalling in neurogenesis, neuroinflammation, and hyperexcitability in mesial temporal lobe epilepsy.

Epilepsy is a neurological disorder characterised by unprovoked, repetitive seizures caused by abnormal neuronal firing. The Wnt/ß-Catenin signalling pathway is involved in seizure-induced neurogenesis, aberrant neurogenesis, neuroinflammation, and hyperexcitability associated with epileptic disorder. Wnt/ß-Catenin signalling is crucial for early brain development processes including neuronal patterning, synapse formation, and N-methyl-d-aspartate receptor (NMDAR) regulation. Disruption of molecular networks such as Wnt/ß-catenin signalling in epilepsy could offer encouraging anti-epileptogenic targets. So, with a better understanding of the canonical Wnt/-Catenin pathway, we highlight in this review the important elements of Wnt/-Catenin signalling specifically in Mesial Temporal Lobe Epilepsy (MTLE) for potential therapeutic targets.

Prospective validation of a seizure diary forecasting falls short.

OBJECTIVE: Recently, a deep learning artificial intelligence (AI) model forecasted seizure risk using retrospective seizure diaries with higher accuracy than random forecasts. The present study sought to prospectively evaluate the same algorithm. METHODS: We recruited a prospective cohort of 46 people with epilepsy; 25 completed sufficient data entry for analysis (median = 5 months). We used the same AI method as in our prior study. Group-level and individual-level Brier Skill Scores (BSSs) compared random forecasts and simple moving average forecasts to the AI. RESULTS: The AI had an area under the receiver operating characteristic curve of .82. At the group level, the AI outperformed random forecasting (BSS = .53). At the individual level, AI outperformed random in 28% of cases. At the group and individual level, the moving average outperformed the AI. If pre-enrollment (nonverified) diaries (with presumed underreporting) were included, the AI significantly outperformed both comparators. Surveys showed most did not mind poor-quality LOW-RISK or HIGH-RISK forecasts, yet 91% wanted access to these forecasts. SIGNIFICANCE: The previously developed AI forecasting tool did not outperform a very simple moving average forecasting in this prospective cohort, suggesting that the AI model should be replaced.