Classification and automatic scoring of arousal intensity during sleep stages using machine learning.

Arousal during sleep can result in sleep fragmentation and various physiological effects, impairing cognitive function and raising blood pressure and heart rate. However, the current definition of arousal has limitations in assessing both amplitude and duration, making it challenging to measure sleep fragmentation accurately. Moreover, there is inconsistency among inter-raters in arousal scoring, which renders it susceptible to subjective variability. Therefore, this study aims to identify a highly accurate classifier for each sleep stage by employing optimized feature selection and machine learning models. According to electroencephalography (EEG) signals during the arousal phase, the intensity level was categorized into four levels. For control, the non-arousal cases were used as level 0 and referred as sham arousal, resulting in five arousal intensity levels. Wavelet transform was applied to analyze sleep arousal to extract features from EEG. Based on these features, we classified arousal intensity levels through machine learning algorithms. Due to the different characteristics of EEG in each sleep stage, the classification model was optimized for the four sleep stages. Excluding sham arousals, a total of 13,532 arousal events were used. The lowest intensity in the entire data, level 1, was computed to be 3107, level 2 was 3384, level 3 was 3472, and the highest intensity of level 4 was 3,569. The optimized classification model for each sleep stage achieved an average sensitivity of 82.68%, specificity of 95.68%, and AUROC of 96.30%. The sensitivity of the control, arousal intensity level 0, was 83.07%, a 1.25% increase over the unoptimized model and a 14.22% increase over previous research. This study used machine learning techniques to develop classifiers for each sleep stage, improving the accuracy of arousal intensity classification. The classifiers showed high sensitivity and specificity and revealed the unique characteristics of arousal intensity during different sleep stages. These findings represent a novel approach to arousal research and have implications for developing more accurate predictive models in sleep research.

Surgical outcome and prognostic factors in epilepsy patients with MR-negative focal cortical dysplasia.

OBJECTIVE: Focal cortical dysplasia (FCD) represents a heterogeneous group of disorders of the cortical formation and is one of the most common causes of epilepsy. Magnetic resonance imaging (MRI) is the modality of choice for detecting structural lesions, and the surgical prognosis in patients with MR lesions is favorable. However, the surgical prognosis of patients with MR-negative FCD is unknown. We aimed to evaluate the long-term surgical outcomes and prognostic factors in MR-negative FCD patients through comprehensive presurgical data. METHODS: We retrospectively reviewed data from 719 drug-resistant epilepsy patients who underwent resective surgery and selected cases in which surgical specimens were pathologically confirmed as FCD Type I or II. If the epileptogenic focus and surgical specimens were obtained from brain areas with a normal MRI appearance, they were classified as MR-negative FCD. Surgical outcomes were evaluated at 2 and 5 years, and clinical, neurophysiological, and neuroimaging data of MR-negative FCD were compared to those of MR-positive FCD. RESULTS: Finally, 47 MR-negative and 34 MR-positive FCD patients were enrolled in the study. The seizure-free rate after surgery (Engel classification I) at postoperative 2 year was 59.5% and 64.7% in the MR-negative and positive FCD groups, respectively (p = 0.81). This rate decreased to 57.5% and 44.4% in the MR-negative and positive FCD groups (p = 0.43) at postoperative 5 years. MR-negative FCD showed a higher proportion of FCD type I (87.2% vs. 50.0%, p = 0.001) than MR-positive FCD. Unilobar cerebral perfusion distribution (odds ratio, OR 5.41) and concordance of interictal epileptiform discharges (OR 5.10) were significantly associated with good surgical outcomes in MR-negative FCD. CONCLUSION: In this study, MR-negative and positive FCD patients had a comparable surgical prognosis, suggesting that comprehensive presurgical evaluations, including multimodal neuroimaging studies, are crucial for obtaining excellent surgical outcomes even in epilepsy patients with MR-negative FCD.

Correlations between interictal extratemporal spikes and clinical features, imaging characteristics, and surgical outcomes in patients with mesial temporal lobe epilepsy.

PURPOSE: The significance of interictal epileptiform discharges (IEDs) observed in the extratemporal lobe has not been fully evaluated in patients with mesial temporal lobe epilepsy (MTLE). This study aimed to evaluate the surgical outcomes, clinical features, and functional neuroimaging characteristics of patients in relation to the presence or absence of extratemporal IED in MTLE with hippocampal sclerosis (HS). METHODS: A total of 165 patients with HS-induced MTLE who had undergone anterior temporal lobectomy were enrolled and stratified into the extratemporal interictal epileptiform discharges (ETD) and the temporal lobe discharges (TD) groups. We analyzed the differentiating features of pre- and postsurgical evaluation data between the two groups. For outcome assessment, only patients with a follow-up of at least 2 years were enrolled, and the outcomes were classified based on Engel classification. RESULTS: The ETD group showed extensive glucose hypometabolism involving the temporal lobe and extratemporal regions (p < 0.001), and IEDs were observed bilaterally or contralateral to the ictal focus (p = 0.02). However, there was no difference in the surgical outcomes between the two groups. On multivariate analysis, statistically significant variables related to ETD occurrence including seizure onset age were not identified nevertheless. CONCLUSION: Our results indicate that ETD had a surgical outcome comparable to that of TD. Therefore, a surgical intervention need not be delayed even if extratemporal IED may be found in presurgical long-term scalp EEG monitoring.

SPECT perfusion changes during ictal automatisms with preserved responsiveness in patients with right temporal lobe epilepsy.

Ictal automatism with preserved responsiveness (APR) has been reported, particularly in nondominant temporal lobe epilepsy (TLE), but its pathophysiology remains poorly understood. This study sought to investigate the relationship between APRs and increased cerebral blood flow (CBF) using ictal single photon emission computed tomography (SPECT) in TLE. Forty-seven subjects with right mesial TLE (15 with and 32 without APR) were enrolled. Patients with APR (APR+) were subdivided into four groups according to degree of responsiveness during seizures. Cerebral blood flow changes during these seizures were semiquantitatively assessed by subtraction ictal SPECT coregistered to MRI (SISCOM). Hyperperfusion in temporal regions did not vary significantly between the APR+ and APR- groups. Cerebral blood flow changes in the frontal area, insula, cingulum, and occipital area were also nonsignificant. However, hyperperfusion in the ipsilateral parietal areas was more frequent in the APR- group than in the APR+ group. Furthermore, hyperperfusion of the contralateral basal ganglia showed an inclination to be more common in the APR- group, but without statistical significance. The study suggested that the involvement of the parietal association cortex during seizure may play an important role in ictal loss of consciousness in TLE. Further studies will be needed to elucidate the pathophysiology of changes in consciousness during temporal lobe seizures.

Effect of continuous positive airway pressure on regional cerebral blood flow in patients with severe obstructive sleep apnea syndrome.

OBJECTIVES: Obstructive sleep apnea (OSA) is commonly associated with neural and cognitive deficits induced by recurrent hypoxemia and sleep fragment. The aims of this study were to use statistical parametric mapping (SPM) to analyze changes in regional cerebral blood flow (rCBF) in untreated patients with severe OSA before and after nasal continuous positive airway pressure (CPAP) treatment, examine the impact of OSA-related variables on rCBF, and assess the therapeutic effect of nasal CPAP treatment. METHODS: Thirty male patients with severe OSA underwent brain single photon emission computed tomography (SPECT) scans twice before and after nasal CPAP treatment for ≥6 months, whereas 26 healthy controls underwent a single SPECT scan. The rCBF differences were compared between two OSA sub-groups (untreated and treated) and the control group, and correlations between rCBF differences and clinical parameters were analyzed. RESULTS: Compared with the controls, the untreated OSA patients showed a significantly lower rCBF in multiple brain areas. After the treatment, partial reversal of the rCBF decreases was observed in the limbic and prefrontal areas. Moreover, complete reversal of the rCBF decreases was observed in the medial orbitofrontal, angular and cerebellar areas. Significant improvements in some clinical and polysomnographic variables (Epworth Sleepiness Scale, apnea-hypopnea index, CPAP duration, and arousal index) paralleled the rCBF changes after the treatment. CONCLUSIONS: Decreased rCBF in severe OSA was significantly reversible by CPAP treatment and correlated with the improvements in the apnea-hypopnea index, arousal index, CPAP duration and Epworth Sleepiness Scale. These results suggest that long-term CPAP treatment improves rCBF in areas responsible for executive, affective, and memory function.

Estrogen receptor independent neurotoxic mechanism of bisphenol A, an environmental estrogen.

Bisphenol A (BPA), a ubiquitous environmental contaminant, has been shown to cause developmental toxicity and carcinogenic effects. BPA may have physiological activity through estrogen receptor (ER) -alpha and -beta, which are expressed in the central nervous system. We previously found that exposure of BPA to immature mice resulted in behavioral alternation, suggesting that overexposure of BPA could be neurotoxic. In this study, we further investigated the molecular neurotoxic mechanisms of BPA. BPA increased vulnerability (decrease of cell viability and differentiation, and increase of apoptotic cell death) of undifferentiated PC12 cells and cortical neuronal cells isolated from gestation 18 day rat embryos in a concentration-dependent manner (more than 50 microM). The ER antagonists, ICI 182,780, and tamoxifen, did not block these effects. The cell vulnerability against BPA was not significantly different in the PC12 cells overexpressing ER-alpha and ER-beta compared with PC12 cells expressing vector alone. In addition, there was no difference observed between BPA and 17-beta estradiol, a well-known agonist of ER receptor in the induction of neurotoxic responses. Further study of the mechanism showed that BPA significantly activated extracellular signal-regulated kinase (ERK) but inhibited anti-apoptotic nuclear factor kappa B (NF-kappaB) activation. In addition, ERK-specific inhibitor, PD 98,059, reversed BPA-induced cell death and restored NF-kappaB activity. This study demonstrated that exposure to BPA can cause neuronal cell death which may eventually be related with behavioral alternation in vivo. However, this neurotoxic effect may not be directly mediated through an ER receptor, as an ERK/NF-kappaB pathway may be more closely involved in BPA-induced neuronal toxicity.