Accurate prediction of neurologic changes in critically ill infants using pose AI.

Infant alertness and neurologic changes can reflect life-threatening pathology but are assessed by exam, which can be intermittent and subjective. Reliable, continuous methods are needed. We hypothesized that our computer vision method to track movement, pose AI, could predict neurologic changes in the neonatal intensive care unit (NICU). We collected 4,705 hours of video linked to electroencephalograms (EEG) from 115 infants. We trained a deep learning pose algorithm that accurately predicted anatomic landmarks in three evaluation sets (ROC-AUCs 0.83-0.94), showing feasibility of applying pose AI in an ICU. We then trained classifiers on landmarks from pose AI and observed high performance for sedation (ROC-AUCs 0.87-0.91) and cerebral dysfunction (ROC-AUCs 0.76-0.91), demonstrating that an EEG diagnosis can be predicted from video data alone. Taken together, deep learning with pose AI may offer a scalable, minimally invasive method for neuro-telemetry in the NICU.

Case report: A novel biallelic FTO variant causing multisystem anomalies with severe epilepsy, widening the spectrum of FTO syndrome.

The fat mass and obesity-associated gene (FTO) codes for a DNA/RNA demethylase. Pathological variants in this gene are rare, with only three reports in the literature, all with mutations in the catalytic domain. We report the first biallelic human variant in fat mass and obesity-associated gene (c.287G>C, p.Arg96Pro/R96P) outside the catalytic site, causing numerous abnormalities across multiple organ systems, affecting respiratory, cardiovascular, and neurological function. Biochemical assays of cells with the patient's variant were performed to further quantify the effect of the variant on function. Loss-of-function resulting from the patient's R96P missense variant was demonstrated with in vitro biochemical characterization of demethylase activity, resulting in a 90% reduction in function of the fat mass and obesity-associated protein compared to wild-type. Our findings demonstrate a novel fat mass and obesity-associated gene non-catalytic site variant with a unique patient phenotype of bilateral multifocal epilepsy and multisystem congenital anomalies.

Centromedian thalamic responsive neurostimulation for Lennox-Gastaut epilepsy and autism.

The RNS System is not approved in patients under 18, although a critical need for novel treatment modalities in this vulnerable population persist. We present two pediatric patients with drug-resistant epilepsy secondary to Lennox-Gastaut Syndrome (LGS) and autism spectrum disorder (ASD) treated with the RNS System. Both patients have experienced 75-99% clinical seizure reductions in >1 year of follow-up. We illustrate that children with diffuse onset, multifocal epilepsy, including frontal and thalamic circuits thought to exist in the generation of LGS seizures, can be treated with responsive neurostimulation safely and effectively, targeting thalamic networks, and avoiding palliative disconnections and resections.

Safety of responsive neurostimulation in pediatric patients with medically refractory epilepsy.

OBJECTIVE: Approximately 75% of pediatric patients who suffer from epilepsy are successfully treated with antiepileptic drugs, while the disease is drug resistant in the remaining patients, who continue to have seizures. Patients with drug-resistant epilepsy (DRE) may have options to undergo invasive treatment such as resection, laser ablation of the epileptogenic focus, or vagus nerve stimulation. To date, treatment with responsive neurostimulation (RNS) has not been sufficiently studied in the pediatric population because the FDA has not approved the RNS device for patients younger than 18 years of age. Here, the authors sought to investigate the safety of RNS in pediatric patients. METHODS: The authors performed a retrospective single-center study of consecutive patients with DRE who had undergone RNS system implantation from September 2015 to December 2019. Patients were followed up postoperatively to evaluate seizure freedom and complications. RESULTS: Of the 27 patients studied, 3 developed infections and were treated with antibiotics. Of these 3 patients, one required partial removal and salvaging of a functioning system, and one required complete removal of the RNS device. No other complications, such as intracranial hemorrhage, stroke, or device malfunction, were seen. The average follow-up period was 22 months. All patients showed improvement in seizure frequency. CONCLUSIONS: The authors demonstrated the safety and efficacy of RNS in pediatric patients, with infections being the main complication. ABBREVIATIONS: DBS = deep brain stimulation; DRE = drug-resistant epilepsy; MDC = multidisciplinary conference; MER = microelectrode recording; MSHS = Mount Sinai Health System; RNS = responsive neurostimulation; SEEG = stereo-EEG; VNS = vagus nerve stimulation.

Treatment of medically refractory seizures with responsive neurostimulation: 2 pediatric cases.

The responsive neurostimulation (RNS) system, an adjunctive treatment for pharmacoresistant partial-onset seizures with 1 or 2 foci, has been available to patients aged 18 years or older since the device's FDA approval in 2013. Herein, the authors describe their off-label application of this technology in 2 pediatric patients and the consequent therapeutic benefit without surgical complications or treatment side effects. A 14-year-old nonambulatory, nonverbal male with severe developmental delay was considered for RNS therapy for medically and surgically refractory epilepsy with bilateral seizure onsets in the setting of a normal radiological examination and a known neuropathological diagnosis of type I cortical dysplasia. The RNS system was implanted with strip electrodes placed on the left lateral frontal and right lateral temporal neocortex. At 19 months' follow-up, cortical stimulation resulted in sustained reduction in both seizure frequency-3 seizures per day down from 15 to 30 per day-and seizure severity. The patient subsequently underwent a trial of corticothalamic stimulation with a right temporal cortical strip and a left thalamic depth electrode, which resulted in a further 50% reduction in seizure frequency. In a second case, a 9-year-old right-handed female with radiological evidence of a small watershed infarct on the left and medically refractory seizures was referred for presurgical evaluation. Invasive monitoring revealed an unresectable seizure focus in the eloquent cortex of the left posterior frontal and parietal lobes. The RNS device was implanted with cortical leads placed at the putative seizure focus. At 21 months after surgery, the patient had been seizure free for 4 months, following a 17-month period in which the seizure frequency had decreased from 12 per month to 2 per month, with associated functional and behavioral improvement. The authors' results suggest that RNS may be a palliative option for children with intractable seizures whose condition warrants off-label use of the surgical device. The improved therapeutic effect noted with time and sustained RNS treatment points to a possible neuromodulatory effect.

Epilepsy surgery in patients with autism.

OBJECTIVE The purpose of this study was to report outcomes of epilepsy surgery in 56 consecutive patients with autism spectrum disorder. METHODS Medical records of 56 consecutive patients with autism who underwent epilepsy surgery were reviewed with regard to clinical characteristics, surgical management, postoperative seizure control, and behavioral changes. RESULTS Of the 56 patients with autism, 39 were male, 45 were severely autistic, 27 had a history of clinically significant levels of aggression and other disruptive behaviors, and 30 were considered nonverbal at baseline. Etiology of the epilepsy was known in 32 cases, and included structural lesions, medical history, and developmental and genetic factors. Twenty-nine patients underwent resective treatments (in 8 cases combined with palliative procedures), 24 patients had only palliative treatments, and 3 patients had only subdural electroencephalography. Eighteen of the 56 patients had more than one operation. The mean age at surgery was 11 ± 6.5 years (range 1.5-35 years). At a mean follow-up of 47 ± 30 months (range 2-117 months), seizure outcomes included 20 Engel Class I, 12 Engel Class II, 18 Engel Class III, and 3 Engel Class IV cases. The age and follow-up times are stated as the mean ± SD. Three patients were able to discontinue all antiepileptic drugs (AEDs). Aggression and other aberrant behaviors observed in the clinical setting improved in 24 patients. According to caregivers, most patients also experienced some degree of improvement in daily social and cognitive function. Three patients had no functional or behavioral changes associated with seizure reduction, and 2 patients experienced worsening of seizures and behavioral symptoms. CONCLUSIONS Epilepsy surgery in patients with autism is feasible, with no indication that the comorbidity of autism should preclude a good outcome. Resective and palliative treatments brought seizure freedom or seizure reduction to the majority of patients, although one-third of the patients in this study required more than one procedure to achieve worthwhile improvement in the long term, and few patients were able to discontinue all AEDs. The number of palliative procedures performed, the need for multiple interventions, and continued use of AEDs highlight the complex etiology of epilepsy in patients with autism spectrum disorder. These considerations underscore the need for continued analysis, review, and reporting of surgical outcomes in patients with autism, which may aid in better identification and management of surgical candidates. The reduction in aberrant behaviors observed in this series suggests that some behaviors previously attributed to autism may be associated with intractable epilepsy, and further highlights the need for systematic evaluation of the relationship between the symptoms of autism and refractory seizures.

Surgical management of medically refractory epilepsy due to early childhood stroke.

UNLABELLED: OBJECT.: The risk of developing epilepsy after perinatal stroke, hypoxic/ischemic injury, and intracerebral hemorrhage is significant, and seizures may become medically refractory in approximately 25% of these patients. Surgical management can be difficult due to multilobar or bilateral cortical injury, nonfocal or poorly lateralizing video electroencephalography (EEG) findings, and limited functional reserve. In this study the authors describe the surgical approaches, seizure outcomes, and complications in patients with epilepsy due to vascular etiologies in the perinatal period and early infancy. METHODS: The records were analyzed of 19 consecutive children and adults with medically refractory epilepsy and evidence of perinatal arterial branch occlusions, hypoxic/ischemic insult, or hemorrhagic strokes, who underwent surgery at the Comprehensive Epilepsy Center of Beth Israel Medical Center and St. Luke's-Roosevelt Hospital Center. Preoperative findings including MRI, video EEG, functional MRI, and neuropsychological testing were analyzed. The majority of patients underwent staged operations with invasive mapping, and all patients had either extra- or intraoperative functional mapping. RESULTS: In 7 patients with large porencephalic cysts due to major arterial branch occlusions, periinsular functional hemispherotomy was performed in 4 children, and in 3 patients, multilobar resections/disconnections were performed, with 1 patient undergoing additional resections 3 years after initial surgery due to recurrence of seizures. All of these patients have been seizure free (Engel Class IA) after a mean 4.5-year follow-up (range 15-77 months). Another 8 patients had intervascular border-zone ischemic infarcts and encephalomalacia, and in this cohort 2 hemispherotomies, 5 multilobar resections/disconnections, and 1 focal cortical resection were performed. Seven of these patients remain seizure free (Engel Class IA) after a mean 4.5-year follow-up (range 9-94 months), and 1 patient suffered a single seizure after 2.5 years of seizure freedom (Engel Class IB, 33-month follow-up). In the final 4 patients with vascular malformation-associated hemorrhagic or ischemic infarction in the perinatal period, a hemispherotomy was performed in 1 case, multilobar resections in 2 cases, and in 1 patient a partial temporal lobectomy was performed, followed 6 months later by a complete temporal and occipital lobectomy due to ongoing seizures. All of these patients have had seizure freedom (Engel Class IA) with a mean follow-up of 4.5 years (range 10-80 months). Complications included transient monoparesis or hemiparesis in 3 patients, transient mutism in 1 patient, infection in 1 patient, and a single case of permanent distal lower-extremity weakness. Transient mood disorders (depression and anxiety) were observed in 2 patients and required medical/therapeutic intervention. CONCLUSIONS: Epilepsy surgery is effective in controlling medically intractable seizures after perinatal vascular insults. Seizure foci tend to be widespread and rarely limited to the area of injury identified through neuroimaging, with invasive monitoring directing multilobar resections in many cases. Long-term functional outcomes have been good in these patients, with significant improvements in independence, quality of life, cognitive development, and motor skills, despite transient postoperative monoparesis or hemiparesis and occasional mood disorders.

Ketogenic diet in pediatric epilepsy patients with gastrostomy feeding.

Ketogenic diet is effective in the control of intractable seizures. Poor compliance is a major limiting factor. In one study, only 50% of children receiving the oral ketogenic diet remained on the diet after 1 year. Twelve children with static encephalopathy and intractable symptomatic epilepsy were given the ketogenic diet via gastrostomy tube. Mean age was 3 years (range, 7 months to 6.5 years). Mean seizure frequency at baseline was 199/month. Seizure frequency after 12 and 18 months of diet was compared with baseline. After 12 months on the diet, the number of antiepileptic drugs was compared with baseline. Median seizure reduction at 1 year and 18 months was 61% and 66%, respectively (P = 0.02). Individually, six patients had 90% seizure reduction, one had 75% reduction, three had 50% reduction, and two patients did not improve. Mean antiepileptic drugs at baseline was 2.8; at 12 months 1.6 (49% reduction). Three patients had weight loss. Two patients discontinued the diet at 13 months and 21 months, respectively, because of diarrhea and weight loss. Compliance with diet was 100% during treatment. This study suggests that the ketogenic diet via gastrostomy feeding tube is safe and effective in children with intractable seizures and ensures compliance.