Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from ...healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects.
Display omitted
Epilepsy represents the third most common neurological disorders in the elderly after cerebrovascular disorders and dementias. The incidence of new-onset epilepsy peaks in this age ...group. The most peculiar aetiologies of late-onset epilepsy are stroke, dementia, and brain tumours. However, aetiology remains unknown in about half of the patients. Diagnosis of epilepsy may be challenging due to the frequent absence of ocular witnesses and the high prevalence of seizure-mimics (i.e. transient ischemic attacks, syncope, transient global amnesia or vertigo) in the elderly. The diagnostic difficulties are even greater when patients have cognitive impairment or cardiac diseases. The management of late-onset epilepsy deserves special considerations. The elderly can reach seizure control with low antiepileptic drugs (AEDs) doses, and seizure-freedom is possible in the vast majority of patients. Pharmacological management should take into account pharmacokinetics and pharmacodynamics of AEDs and the frequent occurrence of comorbidities and polytherapy in this age group. Evidences from double-blind and open-label studies indicate lamotrigine, levetiracetam and controlled-release carbamazepine as first line treatment in late-onset epilepsy.
To prospectively assess sensitivity and specificity of magnetic resonance (MR) imaging measurements of midbrain, pons, middle cerebellar peduncles (MCPs), and superior cerebellar peduncles (SCPs) for ...differentiating progressive supranuclear palsy (PSP) from Parkinson disease (PD) and Parkinson variant of multiple system atrophy (MSA-P), with established consensus criteria as reference standard.
All study participants provided informed consent; study was approved by the institutional review board. Pons area, midbrain area, MCP width, and SCP width were measured in 33 consecutive patients with PSP (16 possible, 17 probable), 108 consecutive patients with PD, 19 consecutive patients with MSA-P, and 50 healthy control participants on T1-weighted MR images. The pons area-midbrain area ratio (P/M) and MCP width-SCP width ratio (MCP/SCP) were also used, and an index termed MR parkinsonism index was calculated (P/M).(MCP/SCP). Differences in MR imaging measurements among groups were evaluated with Kruskal-Wallis test, Mann-Whitney U test, and Bonferroni correction.
Midbrain area and SCP width in patients with PSP (23 men, 10 women; mean age, 69.3 years) were significantly (P < .001) smaller than in patients with PD (62 men, 46 women; mean age, 65.8 years), patients with MSA-P (five men, 14 women; mean age, 64.0 years), and control participants (25 men, 25 women; mean age, 66.6 years). P/M and MCP/SCP were significantly larger in patients with PSP than in patients in other groups and control participants. All measurements showed some overlap of values between patients with PSP and patients from other groups and control participants. MR parkinsonism index value was significantly larger in patients with PSP (median, 19.42) than in patients with PD (median, 9.40; P < .001), patients with MSA-P (median, 6.53; P < .001), and control participants (median, 9.21; P < .001), without overlap of values among groups. No patient with PSP received a misdiagnosis when the index was used (sensitivity and specificity, 100%).
The MR parkinsonism index can help distinguish patients with PSP from those with PD and MSA-P on an individual basis.
The diagnosis of psychogenic nonepileptic seizures (PNES) by means of electroencephalography (EEG) is not a trivial task during clinical practice for neurologists. No clear PNES electrophysiological ...biomarker has yet been found, and the only tool available for diagnosis is video EEG monitoring with recording of a typical episode and clinical history of the subject. In this paper, a data-driven machine learning (ML) pipeline for classifying EEG segments (i.e., epochs) of PNES and healthy controls (CNT) is introduced. This software pipeline consists of a semiautomatic signal processing technique and a supervised ML classifier to aid clinical discriminative diagnosis of PNES by means of an EEG time series. In our ML pipeline, statistical features like the mean, standard deviation, kurtosis, and skewness are extracted in a power spectral density (PSD) map split up in five conventional EEG rhythms (delta, theta, alpha, beta, and the whole band, i.e., 1-32 Hz). Then, the feature vector is fed into three different supervised ML algorithms, namely, the support vector machine (SVM), linear discriminant analysis (LDA), and Bayesian network (BN), to perform EEG segment classification tasks for CNT vs. PNES. The performance of the pipeline algorithm was evaluated on a dataset of 20 EEG signals (10 PNES and 10 CNT) that was recorded in eyes-closed resting condition at the Regional Epilepsy Centre, Great Metropolitan Hospital of Reggio Calabria, University of Catanzaro, Italy. The experimental results showed that PNES vs. CNT discrimination tasks performed via the ML algorithm and validated with random split (RS) achieved an average accuracy of 0.97 ± 0.013 (RS-SVM), 0.99 ± 0.02 (RS-LDA), and 0.82 ± 0.109 (RS-BN). Meanwhile, with leave-one-out (LOO) validation, an average accuracy of 0.98 ± 0.0233 (LOO-SVM), 0.98 ± 0.124 (LOO-LDA), and 0.81 ± 0.109 (LOO-BN) was achieved. Our findings showed that BN was outperformed by SVM and LDA. The promising results of the proposed software pipeline suggest that it may be a valuable tool to support existing clinical diagnosis.
A novel technique of quantitative EEG for differentiating patients with early-stage Creutzfeldt-Jakob disease (CJD) from other forms of rapidly progressive dementia (RPD) is proposed. The ...discrimination is based on the extraction of suitable features from the time-frequency representation of the EEG signals through continuous wavelet transform (CWT). An average measure of complexity of the EEG signal obtained by permutation entropy (PE) is also included. The dimensionality of the feature space is reduced through a multilayer processing system based on the recently emerged deep learning (DL) concept. The DL processor includes a stacked auto-encoder, trained by unsupervised learning techniques, and a classifier whose parameters are determined in a supervised way by associating the known category labels to the reduced vector of high-level features generated by the previous processing blocks. The supervised learning step is carried out by using either support vector machines (SVM) or multilayer neural networks (MLP-NN). A subset of EEG from patients suffering from Alzheimer's Disease (AD) and healthy controls (HC) is considered for differentiating CJD patients. When fine-tuning the parameters of the global processing system by a supervised learning procedure, the proposed system is able to achieve an average accuracy of 89%, an average sensitivity of 92%, and an average specificity of 89% in differentiating CJD from RPD. Similar results are obtained for CJD versus AD and CJD versus HC.
Introduction
Angelman syndrome (AS) is a neurodevelopmental disorder characterized by cognitive disability, speech impairment, hyperactivity and seizures. Movement disorders have been reported in ...almost all AS subjects and they are described as “tremulous movements of limbs, unsteadiness, clumsiness or quick, jerky motions”. The presence of dystonia has barely been mentioned in subjects with AS and has never been studied in detail. The purpose of this study is to evaluate the prevalence, clinical features and severity of dystonia in a series of adolescents and adults with AS.
Methods
Whole body video recordings of patients with genetically confirmed AS were evaluated. Dystonia was evaluated by mean of the movement subscale of Burke–Fahn–Marsden Dystonia Rating Scale (BFM).
Results
Forty-four subjects with AS were evaluated. Fourteen recordings were excluded due to poor cooperation. We finally analyzed data of 30 subjects (15 F) with a median age of 28 years (range 15–51). Dystonia was present in 28/30 (93.3%) subjects. Among these, dystonia involved the upper limbs in 28/28 (100%), lower limbs in 8/28 (28.5%), mouth in 7/28 (25%), neck in 3/28 (10.7%), trunk in 1/28 (3.6%). Severity of dystonia ranged from slight to moderate. There was a linear correlation between severity of dystonia and increasing age. There was no difference in terms of severity of dystonia among genetic subgroups.
Conclusions
Dystonia is a common and previously underrecognized clinical feature of adults and adolescents with AS.
Summary
Objective
Temporal and extratemporal white matter abnormalities have been identified frequently in patients with refractory mesial temporal lobe epilepsy (rMTLE). However, the identification ...of potential water diffusion abnormalities in patients with drug‐responsive, benign MTLE (bMTLE) is still missing. The aim of this study was to identify markers of refractoriness in MTLE.
Methods
The study group included 48 patients with bMTLE (mean age 42.8 + 13.5 years), 38 with rMTLE (mean age 41.7 + 14.1 years) and 54 healthy volunteers. Diffusion tensor imaging (DTI) was performed to measure mean diffusivity (MD) and fractional anisotropy (FA) in a regions‐of‐interest analysis comprising hippocampi and temporal lobe gray and white matter regions. The presence of hippocampal sclerosis (Hs) was assessed using automated magnetic resonance imaging (MRI) evaluation. For statistics we used chi‐square test; two‐tailed, two‐sample t‐test; and stratified linear regression.
Results
The significant demographic differences between the two patient groups were sex (p = 0.003), duration of epilepsy (p = 0.003) and complex febrile convulsions (p = 0.0001). In rMTLE, temporal white matter MD was higher and FA lower, as compared to bMTLE. The analysis of diagnostic accuracy (area under the receiver operator characteristic ROC curve AUC) showed that FA had an AUC for discriminating patients affected from those unaffected by refractory MTLE of 74.0% (p < 0.001), a value that was higher than that of temporal MD (64.0%), hippocampus volume (65.0%), and Hs (66.0%).
Significance
We performed DTI measurements in MTLE and found a significant reduction of FA along the white matter of the temporal lobes in rMTLE, suggesting it as a valuable measure of refractoriness in MTLE.
To evaluate circadian fluctuations and night/day ratio of Heart Rate Variability (HRV) spectral components in patients with obstructive sleep apnea (OSA) in comparison with controls.
This is a ...simultaneous HRV-polysomnographic (PSG) study including 29 patients with OSA and 18 age-sex-matched controls. Four patients with OSA dropped out. All participants underwent PSG and HRV analysis. We measured the 24-hour fluctuations and the night/day ratio of low frequency (LF) and high frequency (HF) spectral components of HRV in all subjects and controls. The LF night/day ratio was termed the cardiac sympathetic index while the HF night/day ratio was termed the cardiac parasympathetic index.
All twenty-five OSA patients were PSG positive (presence of OSA) while 18 controls were PSG negative (absence of OSA). There was no significant difference in LF and HF 24-hour fluctuation values between OSA patients and controls. In OSA patients, LF and HF values were significantly higher during night-time than day time recordings (p<0.001). HF night/day ratio (cardiac parasympathetic index) accurately (100%) differentiated OSA patients from controls without an overlap of individual values. The LF night/day ratio (cardiac sympathetic index) had sensitivity of 84%, specificity of 72.2% and accuracy of 79.1% in distinguishing between groups.
The cardiac parasympathetic index accurately differentiated patients with OSA from controls, on an individual basis.
The differential diagnosis of epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) may be difficult, due to the lack of distinctive clinical features. The interictal ...electroencephalographic (EEG) signal may also be normal in patients with ES. Innovative diagnostic tools that exploit non-linear EEG analysis and deep learning (DL) could provide important support to physicians for clinical diagnosis. In this work, 18 patients with new-onset ES (12 males, 6 females) and 18 patients with video-recorded PNES (2 males, 16 females) with normal interictal EEG at visual inspection were enrolled. None of them was taking psychotropic drugs. A convolutional neural network (CNN) scheme using DL classification was designed to classify the two categories of subjects (ES vs. PNES). The proposed architecture performs an EEG time-frequency transformation and a classification step with a CNN. The CNN was able to classify the EEG recordings of subjects with ES vs. subjects with PNES with 94.4% accuracy. CNN provided high performance in the assigned binary classification when compared to standard learning algorithms (multi-layer perceptron, support vector machine, linear discriminant analysis and quadratic discriminant analysis). In order to interpret how the CNN achieved this performance, information theoretical analysis was carried out. Specifically, the permutation entropy (PE) of the feature maps was evaluated and compared in the two classes. The achieved results, although preliminary, encourage the use of these innovative techniques to support neurologists in early diagnoses.