Nonlinear EEG biomarker profiles for autism and absence epilepsy

Abstract

Background: Although autism and epilepsy are considered to be different disorders, epileptiform EEG activity is common in people with autism even when overt seizures are not present. The relatively high comorbidity between autism and all epilepsy syndromes suggests the possibility of common underlying neurophysiological mechanisms. Although many different epilepsies may be comorbid with autism, absence epilepsy is a generalized epilepsy syndrome with seizures that appear as staring spells, with no motor signs and no focal lesions, making it more difficult to diagnose. Application of nonlinear methods for EEG signal analysis may enable characterization of brain activity that can help to delineate neurophysiological commonalities and differences between autism and epilepsy. Multiscale entropy and recurrence quantitative analysis (RQA) were computed from EEG signals derived from children with autism or absence epilepsy and compared with the goal of finding significant and potentially clinically useful biomarkers neurophysiological differences between these two childhood disorders. Methods: Multiscale entropy and a multiscale version of RQA were computed from EEG data obtained from 92 children were collected in two different settings at Boston Children's Hospital. Short segments of alert resting state EEG were selected for analysis. A complexity index derived from entropy and RQA methods was computed from each of 19 standard EEG channels for all subjects using publicly available software. Statistical comparisons were made between the groups. Machine learning classifiers were also used to determine which derived features were most significantly different among the groups, and to determine classification specificity and sensitivity. Results: Significant differences were found between absence, autism, and control groups in a number of different scalp locations and the values of complexity index. Autism values appeared to be intermediate between epilepsy and control in many locations, and differences between controls and absence patients were more widely distributed across scalp locations. Classification algorithms were able to distinguish absence epilepsy and autism cases from controls with high (>95%) accuracy. Importantly, two independent control groups, although they were derived from different settings and with different equipment were statistically indistinguishable.

The Potential Application of Multiscale Entropy Analysis of Electroencephalography in Children with Neurological and Neuropsychiatric Disorders

“…The changes in EEG complexity were also correlated with the improvement of catatonic symptoms and an increase of serum brain-derived neurotropic factor [12]. Although most studies showed decreased EEG complexity in individuals with ASD, an increased EEG complexity at rest has been noted in a study of older individuals with ASD [15], which showed that the EEG complexity of ASD was in between that of the control and individuals with absence seizures.…”

“…A recent study showed that the inter-ictal EEG complexity in children with CAE was significantly higher than the control over the frontal, occipital, temporal, and parietal areas [15]. In contrast, the reduction of EEG complexity in all channels during the seizure was noted in children with CAE [21].…”

“…Various modifications of MSE have been applied in previous studies [9,14,15,20]. For example, one modification is to use modified sample entropy (mSamEn) by substituting the strict cut-off used to define the similarity of two segments of time series with a sigmoidal function, which improves the relative consistency of parameter selection and the robustness to noise [37].…”

Machine learning in mental health: A systematic scoping review of methods and applications

“…[18][19][20]; and (ii) differentiating between mental health conditions with similar symptomatology, e.g. [21,22]. The majority of studies considered neuroimaging data (e.g., magnetic resonance imaging (MRI), electroencephalography (EEG), and positron emission tomography (PET)).…”

“…Further, MRI data was used to diagnose patients with Alzheimer's disease and cognitive impairment, achieving reasonable accuracy [20]. In addition, ML has also been applied to the diagnosis of mental health conditions with similar symptomatology, for example differentiation of autism spectrum disorders and epilepsy using EEG data [21]. Research has also investigated the application of ML techniques to sensor, speech and video data to improve diagnosis of Alzheimer's disease [23], schizophrenia [24], and suicide ideation [25], achieving high accuracy.…”