The early prediction of epileptic seizures is important to provide appropriate treatment because it can notify clinicians in advance. Various EEG-based machine learning techniques have been used for automatic seizure classification based on subject-specific paradigms. However, because subject-specific models tend to perform poorly on new patient data, a generalized model with a cross-patient paradigm is necessary for building a robust seizure diagnosis system. In this study, we proposed a generalized model that combines one-dimensional convolutional layers (1D CNN), gated recurrent unit (GRU) layers, and attention mechanisms to classify preictal and interictal phases. When we trained this model with ten minutes of preictal data, the average accuracy over eight patients was 82.86%, with 80% sensitivity and 85.5% precision, outperforming other state-of-the-art models. In addition, we proposed a novel application of attention mechanisms for channel selection. The personalized model using three channels with the highest attention score from the generalized model performed better than when using the smallest attention score. Based on these results, we proposed a model for generalized seizure predictors and a seizure-monitoring system with a minimized number of EEG channels.

Background: The aim of this study was to describe the application of whole exome sequencing (WES) in the accurate genetic diagnosis and personalized treatment of extremely rare neurogenetic disorders. Methods: From 2017 to 2019, children with neurodevelopmental symptoms were evaluated using WES in the pediatric neurology clinic and medical genetics center. The clinical presentation, laboratory findings including the genetic results from WES, and diagnosis-based treatment and outcomes of the four patients are discussed. Results: A total of 376 children with neurodevelopmental symptom were evaluated by WES, and four patients (1.1%) were diagnosed with treatable neurologic disorders. Patient 1 (Pt 1) showed global muscle hypotonia, dysmorphic facial features, and multiple anomalies beginning in the perinatal period. Pt 1 was diagnosed with congenital myasthenic syndrome 22 of PREPL deficiency. Pt 2 presented with hypotonia and developmental arrest and was diagnosed with autosomal recessive dopa-responsive dystonia due to TH deficiency. Pt 3, who suffered from intractable epilepsy and progressive cognitive decline, was diagnosed with epileptic encephalopathy 47 with a heterozygous FGF12 mutation. Pt 4 presented with motor delay and episodic ataxia and was diagnosed with episodic ataxia type II (heterozygous CACNA1A mutation). The patients’ major neurologic symptoms were remarkably relieved with pyridostigmine (Pt 1), levodopa (Pt 2), sodium channel blocker (Pt 3), and acetazolamide (Pt 4), and most patients regained developmental milestones in the follow-up period (0.4 to 3 years). Conclusions: The early application of WES helps in the identification of extremely rare genetic diseases, for which effective treatment modalities exist. Ultimately, WES resulted in optimal clinical outcomes of affected patients.

Shin SH, et al. Yonsei Med J. 2022 Nov;63(11):1035-1042. https://doi.org/10.3349/ymj.2022.0274

We investigated the prognostic value of standard electroencephalography, a 30-min recording using 21 electrodes on the scalp, during the early post-cardiac arrest period, and evaluated the performance of electroencephalography findings combined with other clinical features for predicting favourable outcomes in comatose out-of-hospital cardiac arrest (OHCA) survivors treated with targeted temperature management (TTM). This observational registry-based study was conducted at a tertiary care hospital in Korea using the data of all consecutive adult non-traumatic comatose OHCA survivors who underwent standard electroencephalography during TTM between 2010 and 2018. The primary outcome was a 6-month favourable neurological outcome (Cerebral Performance Category score of 1 or 2). Among 170 comatose OHCA survivors with median electroencephalography time of 22 h, a 6-month favourable neurologic outcome was observed in 34.1% (58/170). After adjusting other clinical characteristics, an electroencephalography background with dominant alpha and theta waves had the highest odds ratio of 13.03 (95% confidence interval, 4.69–36.22) in multivariable logistic analysis. A combination of other clinical features (age < 65 years, initial shockable rhythm, resuscitation duration < 20 min) with an electroencephalography background with dominant alpha and theta waves increased predictive performance for favourable neurologic outcomes with a high specificity of up to 100%. A background with dominant alpha and theta waves in standard electroencephalography during TTM could be a simple and early favourable prognostic finding in comatose OHCA survivors.

Lee YJ, et al. J Korean Med Sci. 2017 Mar;32(3):457-464. https://doi.org/10.3346/jkms.2017.32.3.457

Purpose: To determine the prognostic indicators for hematopoietic stem cell transplantation (HSCT)-associated neurological complications, the clinical characteristics and brain magnetic resonance imaging (MRI) lesions in pediatric HSCT recipients were reviewed. Methods: This retrospective study included 51 patients who had underwent a brain MRI due to newly developed neurological symptoms or infection signs during chemotherapy or HSCT. We reviewed the demographics, received treatments, treatment-related morbidities, laboratory findings and brain MRI findings, which were compared between good and poor neurologic outcome groups. Results: Thirty-seven patients (72.5%) fully recovered from the neurologic deficits and fourteen (27.5%) persisted or aggravated. The children with an underlying malignant disease had significantly poorer neurological outcomes (p = 0.015). The neurologic complications associated with infection were more frequent in the poor outcome group (p = 0.038). In the neuroimaging findings, the extent of the white matter lesions was significantly higher in the poor outcome group, as was that of abnormal enhancement, ventriculomegaly, cortical change, deep gray matter abnormalities and cerebellar abnormalities. Conclusion: Most children with neurologic complications and neuroimaging abnormalities during HSCT had recovered. However, children with neurologic complications associated with infectious causes, malignant disease or severe brain MRI abnormalities should be more carefully monitored during HSCT.