Mikati, Mohamad A

Artificial intelligence, machine learning, and deep learning are increasingly being used in all medical fields including for epilepsy research and clinical care. Already there have been resultant cutting-edge applications in both the clinical and research arenas of epileptology. Because there is a need to disseminate knowledge about these approaches, how to use them, their advantages, and their potential limitations, the goal of the 2023 Merritt-Putnam Symposium and of this synopsis review of that symposium has been to present the background and state of the art and then to draw conclusions on current and future applications of these approaches through the following: (1) Initially provide an explanation of the fundamental principles of artificial intelligence, machine learning, and deep learning. These are presented in the first section of this review by Dr Wesley Kerr. (2) Provide insights into their cutting-edge applications in screening for medications in neural organoids, in general, and for epilepsy in particular. These are presented by Dr Sandra Acosta. (3) Provide insights into how artificial intelligence approaches can predict clinical response to medication treatments. These are presented by Dr Patrick Kwan. (4) Finally, provide insights into the expanding applications to the detection and analysis of EEG signals in intensive care, epilepsy monitoring unit, and intracranial monitoring situations, as presented below by Dr Gregory Worrell. The expectation is that, in the coming decade and beyond, the increasing use of the above approaches will transform epilepsy research and care and supplement, but not replace, the diligent work of epilepsy clinicians and researchers.

With more than 6000 attendees between in-person and virtual offerings, the American Epilepsy Society Meeting 2022 in Nashville, felt as busy as in prepandemic times. An ever-growing number of physicians, scientists, and allied health professionals gathered to learn a variety of topics about epilepsy. The program was carefully tailored to meet the needs of professionals with different interests and career stages. This article summarizes the different symposia presented at the meeting. Basic science lectures addressed the primary elements of seizure generation and pathophysiology of epilepsy in different disease states. Scientists congregated to learn about anti-seizure medications, mechanisms of action, and new tools to treat epilepsy including surgery and neurostimulation. Some symposia were also dedicated to discuss epilepsy comorbidities and practical issues regarding epilepsy care. An increasing number of patient advocates discussing their stories were intertwined within scientific activities. Many smaller group sessions targeted more specific topics to encourage member participation, including Special Interest Groups, Investigator, and Skills Workshops. Special lectures included the renown Hoyer and Lombroso, an ILAE/IBE joint session, a spotlight on the impact of Dobbs v. Jackson on reproductive health in epilepsy, and a joint session with the NAEC on coding and reimbursement policies. The hot topics symposium was focused on traumatic brain injury and post-traumatic epilepsy. A balanced collaboration with the industry allowed presentations of the latest pharmaceutical and engineering advances in satellite symposia.

Abstract Objective This study was undertaken to evaluate benzodiazepine (BZD) administration patterns before transitioning to non‐BZD antiseizure medication (ASM) in pediatric patients with refractory convulsive status epilepticus (rSE). Methods This retrospective multicenter study in the United States and Canada used prospectively collected observational data from children admitted with rSE between 2011 and 2020. Outcome variables were the number of BZDs given before the first non‐BZD ASM, and the number of BZDs administered after 30 and 45 min from seizure onset and before escalating to non‐BZD ASM. Results We included 293 patients with a median (interquartile range) age of 3.8 (1.3–9.3) years. Thirty‐six percent received more than two BZDs before escalating, and the later the treatment initiation was after seizure onset, the less likely patients were to receive multiple BZD doses before transitioning (incidence rate ratio [IRR] = .998, 95% confidence interval [CI] = .997–.999 per minute, p = .01). Patients received BZDs beyond 30 and 45 min in 57.3% and 44.0% of cases, respectively. Patients with out‐of‐hospital seizure onset were more likely to receive more doses of BZDs beyond 30 min (IRR = 2.43, 95% CI = 1.73–3.46, p < .0001) and beyond 45 min (IRR = 3.75, 95% CI = 2.40–6.03, p < .0001) compared to patients with in‐hospital seizure onset. Intermittent SE was a risk factor for more BZDs administered beyond 45 min compared to continuous SE (IRR = 1.44, 95% CI = 1.01–2.06, p = .04). Forty‐seven percent of patients ( n = 94) with out‐of‐hospital onset did not receive treatment before hospital arrival. Among patients with out‐of‐hospital onset who received at least two BZDs before hospital arrival ( n = 54), 48.1% received additional BZDs at hospital arrival. Significance Failure to escalate from BZDs to non‐BZD ASMs occurs mainly in out‐of‐hospital rSE onset. Delays in the implementation of medical guidelines may be reduced by initiating treatment before hospital arrival and facilitating a transition to non‐BZD ASMs after two BZD doses during handoffs between prehospital and in‐hospital settings.

AbstractObjectiveThis study was undertaken to describe long‐term clinical and developmental outcomes in pediatric refractory status epilepticus (RSE) and identify factors associated with new neurological deficits after RSE.MethodsWe performed retrospective analyses of prospectively collected observational data from June 2011 to March 2020 on pediatric patients with RSE. We analyzed clinical outcomes from at least 30 days after RSE and, in a subanalysis, we assessed developmental outcomes and evaluated risk factors in previously normally developed patients.ResultsFollow‐up data on outcomes were available in 276 patients (56.5% males). The median (interquartile range [IQR]) follow‐up duration was 1.6 (.9–2.7) years. The in‐hospital mortality rate was 4% (16/403 patients), and 15 (5.4%) patients had died after hospital discharge. One hundred sixty‐six (62.9%) patients had subsequent unprovoked seizures, and 44 (16.9%) patients had a repeated RSE episode. Among 116 patients with normal development before RSE, 42 of 107 (39.3%) patients with available data had new neurological deficits (cognitive, behavioral, or motor). Patients with new deficits had longer median (IQR) electroclinical RSE duration than patients without new deficits (10.3 [2.1–134.5] h vs. 4 [1.6–16] h, p = .011, adjusted odds ratio = 1.003, 95% confidence interval = 1.0008–1.0069, p = .027). The proportion of patients with an unfavorable functional outcome (Glasgow Outcome Scale‐Extended score ≥ 4) was 22 of 90 (24.4%), and they were more likely to have received a continuous infusion.SignificanceAbout one third of patients without prior epilepsy developed recurrent unprovoked seizures after the RSE episode. In previously normally developing patients, 39% presented with new deficits during follow‐up, with longer electroclinical RSE duration as a predictor.

OBJECTIVES: To characterize the pediatric super-refractory status epilepticus population by describing treatment variability in super-refractory status epilepticus patients and comparing relevant clinical characteristics, including outcomes, between super-refractory status epilepticus, and nonsuper-refractory status epilepticus patients. DESIGN: Retrospective cohort study with prospectively collected data between June 2011 and January 2019. SETTING: Seventeen academic hospitals in the United States. PATIENTS: We included patients 1 month to 21 years old presenting with convulsive refractory status epilepticus. We defined super-refractory status epilepticus as continuous or intermittent seizures lasting greater than or equal to 24 hours following initiation of continuous infusion and divided the cohort into super-refractory status epilepticus and nonsuper-refractory status epilepticus groups. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We identified 281 patients (157 males) with a median age of 4.1 years (1.3–9.5 yr), including 31 super-refractory status epilepticus patients. Compared with nonsuper-refractory status epilepticus group, super-refractory status epilepticus patients had delayed initiation of first nonbenzodiazepine-antiseizure medication (149 min [55–491.5 min] vs 62 min [33.3–120.8 min]; p = 0.030) and of continuous infusion (495 min [177.5–1,255 min] vs 150 min [90–318.5 min]; p = 0.003); prolonged seizure duration (120 hr [58–368 hr] vs 3 hr [1.4–5.9 hr]; p < 0.001) and length of ICU stay (17 d [9.5–40 d] vs [1.8–8.8 d]; p < 0.001); more medical complications (18/31 [58.1%] vs 55/250 [22.2%] patients; p < 0.001); lower return to baseline function (7/31 [22.6%] vs 182/250 [73.4%] patients; p < 0.001); and higher mortality (4/31 [12.9%] vs 5/250 [2%]; p = 0.010). Within the super-refractory status epilepticus group, status epilepticus resolution was attained with a single continuous infusion in 15 of 31 patients (48.4%), two in 10 of 31 (32.3%), and three or more in six of 31 (19.4%). Most super-refractory status epilepticus patients (30/31, 96.8%) received midazolam as first choice. About 17 of 31 patients (54.8%) received additional treatments. CONCLUSIONS: Super-refractory status epilepticus patients had delayed initiation of nonbenzodiazepine antiseizure medication treatment, higher number of medical complications and mortality, and lower return to neurologic baseline than nonsuper-refractory status epilepticus patients, although these associations were not adjusted for potential confounders. Treatment approaches following the first continuous infusion were heterogeneous, reflecting limited information to guide clinical decision-making in super-refractory status epilepticus.

AbstractObjectiveWe aimed to characterize the clinical profile and outcomes of new onset refractory status epilepticus (NORSE) in children, and investigated the relationship between fever onset and status epilepticus (SE).MethodsPatients with refractory SE (RSE) between June 1, 2011 and October 1, 2016 were prospectively enrolled in the pSERG (Pediatric Status Epilepticus Research Group) cohort. Cases meeting the definition of NORSE were classified as "NORSE of known etiology" or "NORSE of unknown etiology." Subgroup analysis of NORSE of unknown etiology was completed based on the presence and time of fever occurrence relative to RSE onset: fever at onset (≤24 h), previous fever (2 weeks–24 h), and without fever.ResultsOf 279 patients with RSE, 46 patients met the criteria for NORSE. The median age was 2.4 years, and 25 (54%) were female. Forty (87%) patients had NORSE of unknown etiology. Nineteen (48%) presented with fever at SE onset, 16 (40%) had a previous fever, and five (12%) had no fever. The patients with preceding fever had more prolonged SE and worse outcomes, and 25% recovered baseline neurological function. The patients with fever at onset were younger and had shorter SE episodes, and 89% recovered baseline function.SignificanceAmong pediatric patients with RSE, 16% met diagnostic criteria for NORSE, including the subcategory of febrile infection‐related epilepsy syndrome (FIRES). Pediatric NORSE cases may also overlap with refractory febrile SE (FSE). FIRES occurs more frequently in older children, the course is usually prolonged, and outcomes are worse, as compared to refractory FSE. Fever occurring more than 24 h before the onset of seizures differentiates a subgroup of NORSE patients with distinctive clinical characteristics and worse outcomes.

Purpose: We aimed to determine whether clinical EEG reports obtained from children in the intensive care unit with refractory status epilepticus could provide data for comparative effectiveness research studies. Methods: We conducted a retrospective descriptive study to assess the documentation of key variables within clinical continuous EEG monitoring reports based on the American Clinical Neurophysiology Society's standardized EEG terminology for children with refractory status epilepticus from 10 academic centers. Two pediatric electroencephalographers reviewed the EEG reports. We compared reports generated using free text or templates. Results: We reviewed 191 EEG reports. Agreement between the electroencephalographers regarding whether a variable was described in the report ranged from fair to very good. The presence of electrographic seizures (ES) was documented in 46% (87/191) of reports, and these reports documented the time of first ES in 64% (56/87), ES duration in 72% (63/85), and ES frequency in 68% (59/87). Reactivity was documented in 16% (31/191) of reports, and it was more often documented in template than in free-text reports (40% vs. 14%, P = 0.006). Other variables were not differentially reported in template versus free-text reports. Conclusions: Many key EEG features are not documented consistently in clinical continuous EEG monitoring reports, including ES characteristics and reactivity assessment. Standardization may be needed for clinical EEG reports to provide informative data for large multicenter observational studies.

Summary Purpose To review the efficacy and tolerability of stiripentol in the treatment of U . S . children with D ravet syndrome. Methods U . S . clinicians who had prescribed stiripentol for two or more children with D ravet syndrome between March 2005 and 2012 were contacted to request participation in this retrospective study. Data collected included overall seizure frequency, frequency of prolonged seizures, and use of rescue medications and emergency room ( ER )/hospital visits in the year preceding stiripentol initiation, and with stiripentol therapy. We separately assessed efficacy in the following treatment groups: g roup A , stiripentol without clobazam or valproate; g roup B , stiripentol with clobazam but without valproate; g roup C , stiripentol with valproate but without clobazam; and g roup D , stiripentol with clobazam and valproate. In addition, adverse effects were recorded. Key Findings Thirteen of 16 clinicians contacted for study participated and provided data on 82 children. Stiripentol was initiated a median of 6.0 years after seizure onset and 1.2 years after diagnosis of D ravet syndrome. Compared to baseline, overall seizure frequency was reduced in 2/6 in g roup A , 28/35 in g roup B , 8/14 in g roup C , and 30/48 in g roup D . All children with prolonged seizure frequency greater than quarterly during the baseline period experienced a reduction in this frequency on the various treatment arms with stiripentol. Similarly, 2/4 patients in g roup A , 25/25 in g roup B , 5/10 in g roup C , and 26/33 in g roup D experienced reduction in frequency of rescue medication use and 1/1 in g roup A , 12/12 in g roup B , 3/5 in g roup C , and 18/19 in group D had reduction in frequency of ER /hospital visits. Adverse effects were reported in 38, most commonly sedation and reduced appetite. Four patients (5%) discontinued stiripentol for adverse effects and two (2%) for lack of efficacy. Significance Stiripentol is an effective and well‐tolerated therapy that markedly reduced frequency of prolonged seizures in D ravet syndrome.