Nonlinear EEG biomarker profiles for autism and absence epilepsy

Computer-assisted analysis of routine EEG to identify hidden biomarkers of epilepsy: A systematic review

Background

Computational analysis of routine electroencephalogram (rEEG) could improve the accuracy of epilepsy diagnosis. We aim to systematically assess the diagnostic performances of computed biomarkers for epilepsy in individuals undergoing rEEG.

Methods

We searched MEDLINE, EMBASE, EBM reviews, IEEE Explore and the grey literature for studies published between January 1961 and December 2022. We included studies reporting a computational method to diagnose epilepsy based on rEEG without relying on the identification of interictal epileptiform discharges or seizures. Diagnosis of epilepsy as per a treating physician was the reference standard. We assessed the risk of bias using an adapted QUADAS-2 tool.

Results

We screened 10 166 studies, and 37 were included. The sample size ranged from 8 to 192 (mean=54). The computed biomarkers were based on linear (43%), non-linear (27%), connectivity (38%), and convolutional neural networks (10%) models. The risk of bias was high or unclear in all studies, more commonly from spectrum effect and data leakage. Diagnostic accuracy ranged between 64% and 100%. We observed high methodological heterogeneity, preventing pooling of accuracy measures.

Conclusion

The current literature provides insufficient evidence to reliably assess the diagnostic yield of computational analysis of rEEG.

Significance

We provide guidelines regarding patient selection, reference standard, algorithms, and performance validation.

Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by diverse clinical features. EEG biomarkers such as spectral power and functional connectivity have emerged as potential tools for enhancing early diagnosis and understanding of the neural processes underlying ASD. However, existing studies yield conflicting results, necessitating a comprehensive, data-driven analysis. We conducted a retrospective cross-sectional study involving 246 children with ASD and 42 control children. EEG was collected, and diverse EEG features, including spectral power and spectral coherence were extracted. Statistical inference methods, coupled with machine learning models, were employed to identify differences in EEG features between ASD and control groups and develop classification models for diagnostic purposes. Our analysis revealed statistically significant differences in spectral coherence, particularly in gamma and beta frequency bands, indicating elevated long range functional connectivity between frontal and parietal regions in the ASD group. Machine learning models achieved modest classification performance of ROC-AUC at 0.65. While machine learning approaches offer some discriminative power classifying individuals with ASD from controls, they also indicate the need for further refinement.

Measuring Real-Time Medication Effects From Electroencephalography

PURPOSE

Evaluating the effects of antiseizure medication (ASM) on patients with epilepsy remains a slow and challenging process. Quantifiable noninvasive markers that are measurable in real-time and provide objective and useful information could guide clinical decision-making. We examined whether the effect of ASM on patients with epilepsy can be quantitatively measured in real-time from EEGs.

METHODS

This retrospective analysis was conducted on 67 patients in the long-term monitoring unit at Boston Children's Hospital. Two 30-second EEG segments were selected from each patient premedication and postmedication weaning for analysis. Nonlinear measures including entropy and recurrence quantitative analysis values were computed for each segment and compared before and after medication weaning.

RESULTS

Our study found that ASM effects on the brain were measurable by nonlinear recurrence quantitative analysis on EEGs. Highly significant differences ( P < 1e-11) were found in several nonlinear measures within the seizure zone in response to antiseizure medication. Moreover, the size of the medication effect correlated with a patient's seizure frequency, seizure localization, number of medications, and reported seizure frequency reduction on medication.

CONCLUSIONS

Our findings show the promise of digital biomarkers to measure medication effects and epileptogenicity.

Linear and Non-linear Analyses of EEG in a Group of ASD Children During Resting State Condition

This study analyses the spontaneous electroencephalogram (EEG) brain activity of 14 children diagnosed with Autism Spectrum Disorder (ASD) compared to 18 children with normal development, aged 5-11 years. (i) Power Spectral Density (PSD), (ii) variability across trials (coefficient of variation: CV), and (iii) complexity (multiscale entropy: MSE) of the brain signal analysis were computed on the resting state EEG. PSD (0.5-45 Hz) and CV were averaged over different frequency bands (low-delta, delta, theta, alpha, low-beta, high-beta and gamma). MSE were calculated with a coarse-grained procedure on 67 time scales and divided into fine, medium and coarse scales. In addition, significant neurophysiological variables were correlated with behavioral performance data (Kaufman Brief Intelligence Test (KBIT) and Autism Spectrum Quotient (AQ)). Results show increased PSD fast frequency bands (high-beta and gamma), higher variability (CV) and lower complexity (MSE) in children with ASD when compared to typically developed children. These results suggest a more variable, less complex and, probably, less adaptive neural networks with less capacity to generate optimal responses in ASD children.

Region-Wise Brain Response Classification of ASD Children Using EEG and BiLSTM RNN

AbstractAutism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by impairment in sensory modulation. These sensory modulation deficits would ultimately lead them to difficulties in adaptive behavior and intellectual functioning. The purpose of this study was to observe changes in the nervous system with responses to auditory/visual and only audio stimuli in children with autism and typically developing (TD) through electroencephalography (EEG). In this study, 20 children with ASD and 20 children with TD were considered to investigate the difference in the neural dynamics. The neural dynamics could be understood by non-linear analysis of the EEG signal. In this research to reveal the underlying nonlinear EEG dynamics, recurrence quantification analysis (RQA) is applied. RQA measures were analyzed using various parameter changes in RQA computations. In this research, the cosine distance metric was considered due to its capability of information retrieval and the other distance metrics parameters are compared for identifying the best biomarker. Each computational combination of the RQA measure and the responding channel was analyzed and discussed. To classify ASD and TD, the resulting features from RQA were fed to the designed BiLSTM (bi-long short-term memory) network. The classification accuracy was tested channel-wise for each combination. T3 and T5 channels with neighborhood selection as FAN (fixed amount of nearest neighbors) and distance metric as cosine is considered as the best-suited combination to discriminate between ASD and TD with the classification accuracy of 91.86%, respectively.

Machine-learning for the prediction of one-year seizure recurrence based on routine electroencephalography

Predicting seizure recurrence risk is critical to the diagnosis and management of epilepsy. Routine electroencephalography (EEG) is a cornerstone of the estimation of seizure recurrence risk. However, EEG interpretation relies on the visual identification of interictal epileptiform discharges (IEDs) by neurologists, with limited sensitivity. Automated processing of EEG could increase its diagnostic yield and accessibility. The main objective was to develop a prediction model based on automated EEG processing to predict one-year seizure recurrence in patients undergoing routine EEG. We retrospectively selected a consecutive cohort of 517 patients undergoing routine EEG at our institution (training set) and a separate, temporally shifted cohort of 261 patients (testing set). We developed an automated processing pipeline to extract linear and non-linear features from the EEGs. We trained machine learning algorithms on multichannel EEG segments to predict one-year seizure recurrence. We evaluated the impact of IEDs and clinical confounders on performances and validated the performances on the testing set. The receiver operating characteristic area-under-the-curve for seizure recurrence after EEG in the testing set was 0.63 (95% CI 0.55-0.71). Predictions were still significantly above chance in EEGs with no IEDs. Our findings suggest that there are changes other than IEDs in the EEG signal embodying seizure propensity.

Multiscale entropy of ADHD children during resting state condition

This present study aims to investigate neural mechanisms underlying ADHD compared to healthy children through the analysis of the complexity and the variability of the EEG brain signal using multiscale entropy (MSE), EEG signal standard deviation (SDs), as well as the mean, standard deviation (SDp) and coefficient of variation (CV) of absolute spectral power (PSD). For this purpose, a sample of children diagnosed with attention-deficit/hyperactivity disorder (ADHD) between 6 and 17 years old were selected based on the number of trials and diagnostic agreement, 32 for the open-eyes (OE) experimental condition and 25 children for the close-eyes (CE) experimental condition. Healthy control subjects were age- and gender-matched with the ADHD group. The MSE and SDs of resting-state EEG activity were calculated on 34 time scales using a coarse-grained procedure. In addition, the PSD was averaged in delta, theta, alpha, and beta frequency bands, and its mean, SDp, and CV were calculated. The results show that the MSE changes with age during development, increases as the number of scales increases and has a higher amplitude in controls than in ADHD. The absolute PSD results show CV differences between subjects in low and beta frequency bands, with higher variability values in the ADHD group. All these results suggest an increased EEG variability and reduced complexity in ADHD compared to controls.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09869-0.

A biomarker discovery framework for childhood anxiety

Introduction

Anxiety is the most common manifestation of psychopathology in youth, negatively affecting academic, social, and adaptive functioning and increasing risk for mental health problems into adulthood. Anxiety disorders are diagnosed only after clinical symptoms emerge, potentially missing opportunities to intervene during critical early prodromal periods. In this study, we used a new empirical approach to extracting nonlinear features of the electroencephalogram (EEG), with the goal of discovering differences in brain electrodynamics that distinguish children with anxiety disorders from healthy children. Additionally, we examined whether this approach could distinguish children with externalizing disorders from healthy children and children with anxiety.

Methods

We used a novel supervised tensor factorization method to extract latent factors from repeated multifrequency nonlinear EEG measures in a longitudinal sample of children assessed in infancy and at ages 3, 5, and 7 years of age. We first examined the validity of this method by showing that calendar age is highly correlated with latent EEG complexity factors (r = 0.77). We then computed latent factors separately for distinguishing children with anxiety disorders from healthy controls using a 5-fold cross validation scheme and similarly for distinguishing children with externalizing disorders from healthy controls.

Results

We found that latent factors derived from EEG recordings at age 7 years were required to distinguish children with an anxiety disorder from healthy controls; recordings from infancy, 3 years, or 5 years alone were insufficient. However, recordings from two (5, 7 years) or three (3, 5, 7 years) recordings gave much better results than 7 year recordings alone. Externalizing disorders could be detected using 3- and 5 years EEG data, also giving better results with two or three recordings than any single snapshot. Further, sex assigned at birth was an important covariate that improved accuracy for both disorder groups, and birthweight as a covariate modestly improved accuracy for externalizing disorders. Recordings from infant EEG did not contribute to the classification accuracy for either anxiety or externalizing disorders.

Conclusion

This study suggests that latent factors extracted from EEG recordings in childhood are promising candidate biomarkers for anxiety and for externalizing disorders if chosen at appropriate ages.

Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review

There are growing application of machine learning models to study the intricacies of non-linear and non-stationary characteristics of electroencephalography (EEG) and magnetoencephalography (MEG) data in neurobiologically complex and heterogeneous conditions such as autism spectrum disorder (ASD). Such tools have potential diagnostic applications, and given the highly heterogeneous presentation of ASD, might prove fruitful in early detection and therefore could facilitate very early intervention. We conducted a systematic review (PROSPERO ID#CRD42021257438) by searching PubMed, EMBASE, and PsychINFO for machine learning approaches for EEG and MEG analyses in ASD. Thirty-nine studies were identified, of which the majority (18) used support vector machines for classification; other successful methods included deep learning. Thirty-seven studies were found to employ EEG and two were found to employ MEG. This systematic review indicate that machine learning methods can be used to classify ASD, predict ASD diagnosis in high-risk infants as early as 3 months of age, predict ASD symptom severity, and classify states of cognition in ASD with high accuracy. Replication studies testing validity, reproducibility and generalizability in tandem with randomized controlled trials in ASD populations will likely benefit the field.

The Future of Neurodiagnostics and Emergence of a New Science

Electroencepholography (EEG) is the oldest and original brain measurement technology. Since EEG was first used in clinical settings, the role of neurodiagnostic professionals has focused on two principal tasks that require specialized training. These include collecting the EEG recording, performed primarily by EEG Technologists, and interpreting the recording, generally done by physicians with proper specialization. Emerging technology appears to enable non-specialists to contribute to these tasks. Neurotechnologists may feel vulnerable to being displaced by new technology. A similar shift occurred in the last century when human "computers," employed to perform repetitive calculations needed to solve complex mathematics for the Manhattan and Apollo Projects, were displaced by new electronic computing machines. Many human "computers" seized on the opportunity created by the new computing technology to become the first computer programmers and create the new field of computer science. That transition offers insights for the future of neurodiagnostics. From its inception, neurodiagnostics has been an information processing discipline. Advances in dynamical systems theory, cognitive neuroscience, and biomedical informatics have created an opportunity for neurodiagnostic professionals to help create a new science of functional brain monitoring. A new generation of advanced neurodiagnostic professionals that bring together knowledge and skills in clinical neuroscience and biomedical informatics will benefit psychiatry, neurology, and precision healthcare, lead to preventive brain health through the lifespan, and lead the establishment of a new science of clinical neuroinformatics.

Identifying autism spectrum disorder in resting-state fNIRS signals based on multiscale entropy and a two-branch deep learning network

BACKGROUND

The demand for early and precise identification of autism spectrum disorder (ASD) presented a challenge to the prediction of ASD with a non-invasive neuroimaging method.

NEW METHOD

A deep learning model was proposed to identify children with ASD using the resting-state functional near-infrared spectroscopy (fNIRS) signals. In this model, the input was the pattern of brain complexity represented by multiscale entropy of fNIRS time-series signals, with the purpose to solve the problem of deep learning analysis when the raw signals were limited by length and the number of subjects. The model consisted of a two-branch deep learning network, where one branch was a convolution neural network and the other was a long short-term memory neural network based on an attention mechanism.

RESULTS

Our model could achieve an identification accuracy of 94%. Further analysis used the SHapley Additive exPlanations (SHAP) method to balance the accuracy and the number of optical channels, thus reducing the complexity of fNIRS experiment. COMPARISON WITH PREVIOUSLY USED METHOD(S): in identification accuracy, our model was about 14% higher than previously used deep learning models with the same input and 4% higher than the same model but directly using fNIRS signals as input. We could obtain a discriminative accuracy of 90% with nearly half of the measurement channels by the SHAP method.

CONCLUSIONS

Using the pattern of brain complexity as input was effective in the deep learning model when the fNIRS signals were insufficient. With the SHAP method, it was possible to reduce the number of optical channels, while maintaining high accuracy in ASD identification.

Complexity analysis of heartbeat-related signals in brain MRI time series as a potential biomarker for ageing and cognitive performance

Getting older affects both the structure of the brain and some cognitive capabilities. Until now, magnetic resonance imaging (MRI) approaches have been unable to give a coherent reflection of the cognitive declines. It shows the limitation of the contrast mechanisms used in most MRI investigations, which are indirect measures of brain activities depending on multiple physiological and cognitive variables. However, MRI signals may contain information of brain activity beyond these commonly used signals caused by the neurovascular response. Here, we apply a zero-spin echo (ZSE) weighted MRI sequence, which can detect heartbeat-evoked signals (HES). Remarkably, these MRI signals have properties only known from electrophysiology. We investigated the complexity of the HES arising from this sequence in two age groups; young (18-29 years) and old (over 65 years). While comparing young and old participants, we show that the complexity of the HES decreases with age, where the stability and chaoticity of these HES are particularly sensitive to age. However, we also found individual differences which were independent of age. Complexity measures were related to scores from different cognitive batteries and showed that higher complexity may be related to better cognitive performance. These findings underpin the affinity of the HES to electrophysiological signals. The profound sensitivity of these changes in complexity shows the potential of HES for understanding brain dynamics that need to be tested in more extensive and diverse populations with clinical relevance for all neurovascular diseases.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1140/epjs/s11734-022-00696-2.

The automated preprocessing pipe-line for the estimation of scale-wise entropy from EEG data (APPLESEED): Development and validation for use in pediatric populations

It is increasingly understood that moment-to-moment brain signal variability - traditionally modeled out of analyses as mere "noise" - serves a valuable functional role related to development, cognitive processing, and psychopathology. Multiscale entropy (MSE) - a measure of signal irregularity across temporal scales - is an increasingly popular analytic technique in human neuroscience calculated from time series such as electroencephalography (EEG) signals. MSE provides insight into the time-structure and (non)linearity of fluctuations in neural activity and network dynamics, capturing the brain's moment-to-moment complexity as it operates on multiple time scales. MSE is emerging as a powerful predictor of developmental processes and outcomes. However, differences in data preprocessing and MSE computation make it challenging to compare results across studies. Here, we (1) provide an introduction to MSE for developmental researchers, (2) demonstrate the effect of preprocessing procedures on scale-wise entropy estimates, and (3) establish a standardized EEG preprocessing and entropy estimation pipeline that adapts a critical modification to the original MSE algorithm, and generates reliable scale-wise entropy estimates capable of differentiating developmental stages and cognitive states. This novel pipeline - the Automated Preprocessing Pipe-Line for the Estimation of Scale-wise Entropy from EEG Data (APPLESEED) is fully automated, customizable, and freely available for download from https://github.com/mhpuglia/APPLESEED.

Early Warning Signals in Phase Space: Geometric Resilience Loss Indicators From Multiplex Cumulative Recurrence Networks

The detection of Early Warning Signals (EWS) of imminent phase transitions, such as sudden changes in symptom severity could be an important innovation in the treatment or prevention of disease or psychopathology. Recurrence-based analyses are known for their ability to detect differences in behavioral modes and order transitions in extremely noisy data. As a proof of principle, the present paper provides an example of a recurrence network based analysis strategy which can be implemented in a clinical setting in which data from an individual is continuously monitored for the purpose of making decisions about diagnosis and intervention. Specifically, it is demonstrated that measures based on the geometry of the phase space can serve as Early Warning Signals of imminent phase transitions. A publicly available multivariate time series is analyzed using so-called cumulative Recurrence Networks (cRN), which are recurrence networks with edges weighted by recurrence time and directed towards previously observed data points. The results are compared to previous analyses of the same data set, benefits, limitations and future directions of the analysis approach are discussed.

Evaluation of Feature Selection Methods for Classification of Epileptic Seizure EEG Signals

Epilepsy is a disease that decreases the quality of life of patients; it is also among the most common neurological diseases. Several studies have approached the classification and prediction of seizures by using electroencephalographic data and machine learning techniques. A large diversity of features has been extracted from electroencephalograms to perform classification tasks; therefore, it is important to use feature selection methods to select those that leverage pattern recognition. In this study, the performance of a set of feature selection methods was compared across different classification models; the classification task consisted of the detection of ictal activity from the CHB-MIT and Siena Scalp EEG databases. The comparison was implemented for different feature sets and the number of features. Furthermore, the similarity between selected feature subsets across classification models was evaluated. The best F1-score (0.90) was reported by the K-nearest neighbor along with the CHB-MIT dataset. Results showed that none of the feature selection methods clearly outperformed the rest of the methods, as the performance was notably affected by the classifier, dataset, and feature set. Two of the combinations (classifier/feature selection method) reporting the best results were K-nearest neighbor/support vector machine and random forest/embedded random forest.

EMD-based analysis of complexity with dissociated EEG amplitude and frequency information: a data-driven robust tool -for Autism diagnosis- compared to multi-scale entropy approach

OBJECTIVE

Autism spectrum disorder (ASD) is usually characterised by altered social skills, repetitive behaviours, and difficulties in verbal/nonverbal communication. It has been reported that electroencephalograms (EEGs) in ASD are characterised by atypical complexity. The most commonly applied method in studies of ASD EEG complexity is multiscale entropy (MSE), where the sample entropy is evaluated across several scales. However, the accuracy of MSE-based classifications between ASD and neurotypical EEG activities is poor owing to several shortcomings in scale extraction and length, the overlap between amplitude and frequency information, and sensitivity to frequency. The present study proposes a novel, nonlinear, non-stationary, adaptive, data-driven, and accurate method for the classification of ASD and neurotypical groups based on EEG complexity and entropy without the shortcomings of MSE.

APPROACH

The proposed method is as follows: (a) each ASD and neurotypical EEG (122 subjects × 64 channels) is decomposed using empirical mode decomposition (EMD) to obtain the intrinsic components (intrinsic mode functions). (b) The extracted components are normalised through the direct quadrature procedure. (c) The Hilbert transforms of the components are computed. (d) The analytic counterparts of components (and normalised components) are found. (e) The instantaneous frequency function of each analytic normalised component is calculated. (f) The instantaneous amplitude function of each analytic component is calculated. (g) The Shannon entropy values of the instantaneous frequency and amplitude vectors are computed. (h) The entropy values are classified using a neural network (NN). (i) The achieved accuracy is compared to that obtained with MSE-based classification. (j) The consistency of the results of entropy 3D mapping with clinical data is assessed.

MAIN RESULTS

The results demonstrate that the proposed method outperforms MSE (accuracy: 66.4%), with an accuracy of 93.5%. Moreover, the entropy 3D mapping results are more consistent with the available clinical data regarding brain topography in ASD.

SIGNIFICANCE

This study presents a more robust alternative to MSE, which can be used for accurate classification of ASD/neurotypical as well as for the examination of EEG entropy across brain zones in ASD.

A Review of Network and Computer Analysis of Epileptiform Discharge Free EEG to Characterize and Detect Epilepsy

Objectives. There is emerging evidence that network/computer analysis of epileptiform discharge free electroencephalograms (EEGs) can be used to detect epilepsy, improve diagnosis and resource use. Such methods are automated and can be performed on shorter recordings of EEG. We assess the evidence and its strength in the area of seizure detection from network/computer analysis of epileptiform discharge free EEG. Methods. A scoping review using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidance was conducted with a literature search of Embase, Medline and PsychINFO. Predesigned inclusion/exclusion criteria were applied to selected articles. Results. The initial search found 3398 articles. After duplicate removal and screening, 591 abstracts were reviewed, 64 articles were selected and read leading to 20 articles meeting the requisite inclusion/exclusion criteria. These were 9 reports and 2 cross-sectional studies using network analysis to compare and/or classify EEG. One review of 17 reports and 10 cross-sectional studies only aimed to classify the EEGs. One cross-sectional study discussed EEG abnormalities associated with autism. Conclusions. Epileptiform discharge free EEG features derived from network/computer analysis differ significantly between people with and without epilepsy. Diagnostic algorithms report high accuracies and could be clinically useful. There is a lack of such research within the intellectual disability (ID) and/or autism populations, where epilepsy is more prevalent and there are additional diagnostic challenges.

Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months

BACKGROUND

Early identification of autism spectrum disorder (ASD) provides an opportunity for early intervention and improved developmental outcomes. The use of electroencephalography (EEG) in infancy has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Given the high co-morbidity with language impairment, we and others have speculated that infants who are later diagnosed with ASD have altered language learning, including phoneme discrimination. Phoneme learning occurs rapidly in infancy, so altered neural substrates during the first year of life may serve as early, accurate indicators of later autism diagnosis.

METHODS

Using EEG data collected at two different ages during a passive phoneme task in infants with high familial risk for ASD, we compared the predictive accuracy of a combination of feature selection and machine learning models at 6 months (during native phoneme learning) and 12 months (after native phoneme learning), and we identified a single model with strong predictive accuracy (100%) for both ages. Samples at both ages were matched in size and diagnoses (n = 14 with later ASD; n = 40 without ASD). Features included a combination of power and nonlinear measures across the 10‑20 montage electrodes and 6 frequency bands. Predictive features at each age were compared both by feature characteristics and EEG scalp location. Additional prediction analyses were performed on all EEGs collected at 12 months; this larger sample included 67 HR infants (27 HR-ASD, 40 HR-noASD).

RESULTS

Using a combination of Pearson correlation feature selection and support vector machine classifier, 100% predictive diagnostic accuracy was observed at both 6 and 12 months. Predictive features differed between the models trained on 6- versus 12-month data. At 6 months, predictive features were biased to measures from central electrodes, power measures, and frequencies in the alpha range. At 12 months, predictive features were more distributed between power and nonlinear measures, and biased toward frequencies in the beta range. However, diagnosis prediction accuracy substantially decreased in the larger, more behaviorally heterogeneous 12-month sample.

CONCLUSIONS

These results demonstrate that speech processing EEG measures can facilitate earlier identification of ASD but emphasize the need for age-specific predictive models with large sample sizes to develop clinically relevant classification algorithms.

Integrating Optimized Multiscale Entropy Model with Machine Learning for the Localization of Epileptogenic Hemisphere in Temporal Lobe Epilepsy Using Resting-State fMRI

The bottleneck associated with the validation of the parameters of the entropy model has limited the application of this model to modern functional imaging technologies such as the resting-state functional magnetic resonance imaging (rfMRI). In this study, an optimization algorithm that could choose the parameters of the multiscale entropy (MSE) model was developed, while the optimized effectiveness for localizing the epileptogenic hemisphere was validated through the classification rate with a supervised machine learning method. The rfMRI data of 20 mesial temporal lobe epilepsy patients with positive indicators (the indicators of epileptogenic hemisphere in clinic) in the hippocampal formation on either left or right hemisphere (equally divided into two groups) on the structural MRI were collected and preprocessed. Then, three parameters in the MSE model were statistically optimized by both receiver operating characteristic (ROC) curve and the area under the ROC curve value in the sensitivity analysis, and the intergroup significance of optimized entropy values was utilized to confirm the biomarked brain areas sensitive to the epileptogenic hemisphere. Finally, the optimized entropy values of these biomarked brain areas were regarded as the feature vectors input for a support vector machine to classify the epileptogenic hemisphere, and the classification effectiveness was cross-validated. Nine biomarked brain areas were confirmed by the optimized entropy values, including medial superior frontal gyrus and superior parietal gyrus (p < .01). The mean classification accuracy was greater than 90%. It can be concluded that combination of the optimized MSE model with the machine learning model can accurately confirm the epileptogenic hemisphere by rfMRI. With the powerful information interaction capabilities of 5G communication, the epilepsy side-fixing algorithm that requires computing power can be integrated into a cloud platform. The demand side only needs to upload patient data to the service platform to realize the preoperative assessment of epilepsy.

Complexity analysis of the brain activity in Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) due to cognitive loads/demands induced by Aristotle's type of syllogism/reasoning. A Power Spectral Density and multiscale entropy (MSE) analysis

OBJECTIVE

We aim to investigate whether EEG dynamics differ in adults with ASD (Autism Spectrum Disorders), ADHD (attention-deficit/hyperactivity disorder), compared with healthy subjects during the performance of an innovative cognitive task: Aristotle's valid and invalid syllogisms. We follow the Neuroanatomical differences type of criterion in assessing the results of our study in supporting or not the dual-process theory of Kahneman, 2011) (Systems I & II of thinking).

METHOD

We recorded EEGs from 14 scalp electrodes in 30 adults with ADHD, 30 with ASD and 24 healthy, normal subjects. The subjects were exposed in a set of innovative cognitive tasks (inducing varying cognitive loads), the Aristotle's four types of syllogism mentioned above. The multiscale entropy (MSE), a nonlinear information-theoretic measure or tool was computed to extract features that quantify the complexity of the EEG.

RESULTS

The dynamics of the curves of the grand average of MSE values of the ADHD and ASD participants was significantly in higher levels for the majority of time scales, than the healthy subjects over a number of brain regions (electrodes locations), during the performance of both valid and invalid types of syllogism. This result is seemingly not in accordance of the broadly accepted 'theory' of complexity loss in 'pathological' subjects, but actually this is not the case as explained in the text. ADHD subjects are engaged in System II of thinking, for both Valid and Invalid syllogism, ASD and Control in System I for valid and invalid syllogism, respectively. A surprising and 'provocative' result of this paper, as shown in the next sections, is that the Complexity-variability of ASD and ADHD subjects, when they face Aristotle's types of syllogisms, is higher than that of the control subjects. An explanation is suggested as described in the text. Also, in the case of invalid type of Aristotelian syllogisms, the linguistic and visuo-spatial systems are both engaged ONLY in the temporal and occipital regions of the brain, respectively, of ADHD subjects. In the case of valid type, both above systems are engaged in the temporal and occipital regions of the brain, respectively, of both ASD and ADHD subjects, while in the control subjects only the visuo-spatial type is engaged (Goel et al., 2000; Knauff, 2007).

CONCLUSION

Based on the results of the analysis described in this work, the differences in the EEG complexity between the three groups of participants lead to the conclusion that cortical information processing is changed in ASD and ADHD adults, therefore their level of cortical activation may be insufficient to meet the peculiar cognitive demand of Aristotle's reasoning.

SIGNIFICANCE

The present paper suggest that MSE, is a powerful and efficient nonlinear measure in detecting neural dysfunctions in adults with ASD and ADHD characteristics, when they are called on to perform in a very demanding as well as innovative set of cognitive tasks, that can be considered as a new diagnostic 'benchmark' in helping detecting more effectively such type of disorders. A linear measure alone, as the typical PSD, is not capable in making such a distinction. The work contributes in shedding light on the neural mechanisms of syllogism/reasoning of Aristotelian type, as well as toward understanding how humans reason logically and why 'pathological' subjects deviate from the norms of formal logic.

Machine learning with neuroimaging data to identify autism spectrum disorder: a systematic review and meta-analysis

PURPOSE

Autism Spectrum Disorder (ASD) is diagnosed through observation or interview assessments, which is time-consuming, subjective, and with questionable validity and reliability. Thus, we aimed to evaluate the role of machine learning (ML) with neuroimaging data to provide a reliable classification of ASD.

METHODS

A systematic search of PubMed, Scopus, and Embase was conducted to identify relevant publications. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to assess the studies' quality. A bivariate random-effects model meta-analysis was employed to evaluate the pooled sensitivity, the pooled specificity, and the diagnostic performance through the hierarchical summary receiver operating characteristic (HSROC) curve of ML with neuroimaging data in classifying ASD. Meta-regression was also performed.

RESULTS

Forty-four studies (5697 ASD and 6013 typically developing individuals [TD] in total) were included in the quantitative analysis. The pooled sensitivity for differentiating ASD from TD individuals was 86.25 95% confidence interval [CI] (81.24, 90.08), while the pooled specificity was 83.31 95% CI (78.12, 87.48) with a combined area under the HSROC (AUC) of 0.889. Higgins I² (> 90%) and Cochran's Q (p < 0.0001) suggest a high degree of heterogeneity. In the bivariate model meta-regression, a higher pooled specificity was observed in studies not using a brain atlas (90.91 95% CI [80.67, 96.00], p = 0.032). In addition, a greater pooled sensitivity was seen in studies recruiting both males and females (89.04 95% CI [83.84, 92.72], p = 0.021), and combining imaging modalities (94.12 95% [85.43, 97.76], p = 0.036).

CONCLUSION

ML with neuroimaging data is an exciting prospect in detecting individuals with ASD but further studies are required to improve its reliability for usage in clinical practice.

Measuring the effects of sleep on epileptogenicity with multifrequency entropy

OBJECTIVE

We demonstrate that multifrequency entropy gives insight into the relationship between epileptogenicity and sleep, and forms the basis for an improved measure of medical assessment of sleep impairment in epilepsy patients.

METHODS

Multifrequency entropy was computed from electroencephalography measurements taken from 31 children with Benign Epilepsy with Centrotemporal Spikes and 31 non-epileptic controls while awake and during sleep. Values were compared in the epileptic zone and away from the epileptic zone in various sleep stages.

RESULTS

We find that (I) in lower frequencies, multifrequency entropy decreases during non-rapid eye movement sleep stages when compared with wakefulness in a general population of pediatric patients, (II) patients with Benign Epilepsy with Centrotemporal Spikes had lower multifrequency entropy across stages of sleep and wakefulness, and (III) the epileptic regions of the brain exhibit lower multifrequency entropy patterns than the rest of the brain in epilepsy patients.

CONCLUSIONS

Our results show that multifrequency entropy decreases during sleep, particularly sleep stage 2, confirming, in a pediatric population, an association between sleep, lower multifrequency entropy, and increased likelihood of seizure.

SIGNIFICANCE

We observed a correlation between lowered multifrequency entropy and increased epileptogenicity that lays preliminary groundwork for the detection of a digital biomarker for epileptogenicity.

Spontaneous neural activity relates to psychiatric traits in 16p11.2 CNV carriers: An analysis of EEG spectral power and multiscale entropy

Copy number variations (CNV) at the 16p11.2 chromosomal region are rare high-risk CNVs associated with various clinical features and psychiatric disorders including intellectual disability, developmental delays, and autism spectrum disorder. No study to date has investigated whether spontaneous neural activity is altered for 16p11.2 CNV carriers and whether this relates to psychiatric traits. The aim of this study is to examine the impact of 16p11.2 deletions (del) and duplications (dup) on spontaneous neural activity and its relationship to psychiatric problems. EEG was previously collected as part of the Simons Searchlight initiative. Using spectral power (delta, theta, alpha, and beta frequency bands), complexity index (CI), and multiscale entropy analysis techniques, we analyzed frontal resting-state EEG data collected from 22 16p11.2 del carriers, 14 dup carriers, and 13 controls. We then examined associations between neural activity and psychiatric traits, measured with the Child Behavior Checklist. Results indicated that EEG entropy was higher for del and dup compared to controls, respectively, at all timescales. CI was also higher for del and dup compared to controls. Theta power of 16p11.2 dup carriers was higher than controls. A strong association was found between entropy at higher timescales and anxiety problems. In addition, a strong correlation was found between theta power and pervasive developmental problems. Atypical spontaneous neural activity is implicated in 16p11.2 CNVs. With higher entropy or theta power, psychiatric traits increase in severity. Our findings provide evidence of the link between genotype, neural activity, and phenotypes in 16p11.2 CNVs.

Nonlinear Analysis of Visually Normal EEGs to Differentiate Benign Childhood Epilepsy with Centrotemporal Spikes (BECTS)

Childhood epilepsy with centrotemporal spikes, previously known as Benign Epilepsy with Centro-temporal Spikes (BECTS) or Rolandic Epilepsy, is one of the most common forms of focal childhood epilepsy. Despite its prevalence, BECTS is often misdiagnosed or missed entirely. This is in part due to the nocturnal and brief nature of the seizures, making it difficult to identify during a routine electroencephalogram (EEG). Detecting brain activity that is highly associated with BECTS on a brief, awake EEG has the potential to improve diagnostic screening for BECTS and predict clinical outcomes. For this study, 31 patients with BECTS were retrospectively selected from the BCH Epilepsy Center database along with a contrast group of 31 patients in the database who had no form of epilepsy and a normal EEG based on a clinical chart review. Nonlinear features, including multiscale entropy and recurrence quantitative analysis, were computed from 30-second segments of awake EEG signals. Differences were found between these multiscale nonlinear measures in the two groups at all sensor locations, while visual EEG inspection by a board-certified child neurologist did not reveal any distinguishing features. Moreover, a quantitative difference in the nonlinear measures (sample entropy, trapping time and the Lyapunov exponents) was found in the centrotemporal region of the brain, the area associated with a greater tendency to have unprovoked seizures, versus the rest of the brain in the BECTS patients. This difference was not present in the contrast group. As a result, the epileptic zone in the BECTS patients appears to exhibit lower complexity, and these nonlinear measures may potentially serve as a clinical screening tool for BECTS, if replicated in a larger study population.

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

BACKGROUND

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

METHODS

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

RESULTS

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

CONCLUSIONS

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Low-Intensity Pulsed Ultrasound Stimulation Modulates the Nonlinear Dynamics of Local Field Potentials in Temporal Lobe Epilepsy

Low-intensity pulsed ultrasound stimulation (LIPUS) can inhibit seizures associated with temporal lobe epilepsy (TLE), which is the most common epileptic syndrome in adults and accounts for more than half of the cases of intractable epilepsy. Electroencephalography (EEG) signal analysis is an important method for studying epilepsy. The nonlinear dynamics of epileptic EEG signals can be used as biomarkers for the prediction and diagnosis of epilepsy. However, how ultrasound modulates the nonlinear dynamic characteristics of EEG signals in TLE is still unclear. Here, we used low-intensity pulsed ultrasound to stimulate the CA3 region of kainite (KA)-induced TLE mice, simultaneously recorded local field potentials (LFP) in the stimulation regions before, during, and after LIPUS. The nonlinear characteristics, including complexity, approximate entropy of different frequency bands, and Lyapunov exponent of the LFP, were calculated. Compared with the control group, the experimental group showed that LIPUS inhibited TLE seizure and the complexity, approximate entropy of the delta (0.5–4 Hz) and theta (4–8 Hz) frequency bands, and Lyapunov exponent of the LFP significantly increased in response to ultrasound stimulation. The values before ultrasound stimulation were higher ∼1.87 (complexity), ∼1.39 (approximate entropy of delta frequency bands), ∼1.13 (approximate entropy of theta frequency bands) and ∼1.46 times (Lyapunov exponent) than that after ultrasound stimulation (p < 0.05). The above results demonstrated that LIPUS can alter nonlinear dynamic characteristics and provide a basis for the application of ultrasound stimulation in the treatment of epilepsy.

A Novel Biomarker of Compensatory Recruitment of Face Emotional Imagery Networks in Autism Spectrum Disorder

Imagery of facial expressions in Autism Spectrum Disorder (ASD) is likely impaired but has been very difficult to capture at a neurophysiological level. We developed an approach that allowed to directly link observation of emotional expressions and imagery in ASD, and to derive biomarkers that are able to classify abnormal imagery in ASD. To provide a handle between perception and action imagery cycles it is important to use visual stimuli exploring the dynamical nature of emotion representation. We conducted a case-control study providing a link between both visualization and mental imagery of dynamic facial expressions and investigated source responses to pure face-expression contrasts. We were able to replicate the same highly group discriminative neural signatures during action observation (dynamical face expressions) and imagery, in the precuneus. Larger activation in regions involved in imagery for the ASD group suggests that this effect is compensatory. We conducted a machine learning procedure to automatically identify these group differences, based on the EEG activity during mental imagery of facial expressions. We compared two classifiers and achieved an accuracy of 81% using 15 features (both linear and non-linear) of the signal from theta, high-beta and gamma bands extracted from right-parietal locations (matching the precuneus region), further confirming the findings regarding standard statistical analysis. This robust classification of signals resulting from imagery of dynamical expressions in ASD is surprising because it far and significantly exceeds the good classification already achieved with observation of neutral face expressions (74%). This novel neural correlate of emotional imagery in autism could potentially serve as a clinical interventional target for studies designed to improve facial expression recognition, or at least as an intervention biomarker.

Recurrence quantification analysis of resting state EEG signals in autism spectrum disorder - a systematic methodological exploration of technical and demographic confounders in the search for biomarkers

BACKGROUND

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with a worldwide prevalence of 1-2%. In low-resource environments, in particular, early identification and diagnosis is a significant challenge. Therefore, there is a great demand for 'language-free, culturally fair' low-cost screening tools for ASD that do not require highly trained professionals. Electroencephalography (EEG) has seen growing interest as an investigational tool for biomarker development in ASD and neurodevelopmental disorders. One of the key challenges is the identification of appropriate multivariate, next-generation analytical methodologies that can characterise the complex, nonlinear dynamics of neural networks in the brain, mindful of technical and demographic confounders that may influence biomarker findings. The aim of this study was to evaluate the robustness of recurrence quantification analysis (RQA) as a potential biomarker for ASD using a systematic methodological exploration of a range of potential technical and demographic confounders.

METHODS

RQA feature extraction was performed on continuous 5-second segments of resting state EEG (rsEEG) data and linear and nonlinear classifiers were tested. Data analysis progressed from a full sample of 16 ASD and 46 typically developing (TD) individuals (age 0-18 years, 4802 EEG segments), to a subsample of 16 ASD and 19 TD children (age 0-6 years, 1874 segments), to an age-matched sample of 7 ASD and 7 TD children (age 2-6 years, 666 segments) to prevent sample bias and to avoid misinterpretation of the classification results attributable to technical and demographic confounders. A clinical scenario of diagnosing an unseen subject was simulated using a leave-one-subject-out classification approach.

RESULTS

In the age-matched sample, leave-one-subject-out classification with a nonlinear support vector machine classifier showed 92.9% accuracy, 100% sensitivity and 85.7% specificity in differentiating ASD from TD. Age, sex, intellectual ability and the number of training and test segments per group were identified as possible demographic and technical confounders. Consistent repeatability, i.e. the correct identification of all segments per subject, was found to be a challenge.

CONCLUSIONS

RQA of rsEEG was an accurate classifier of ASD in an age-matched sample, suggesting the potential of this approach for global screening in ASD. However, this study also showed experimentally how a range of technical challenges and demographic confounders can skew results, and highlights the importance of probing for these in future studies. We recommend validation of this methodology in a large and well-matched sample of infants and children, preferably in a low- and middle-income setting.

Nonlinear analysis of electrodermal activity signals for healthy subjects and patients with chronic obstructive pulmonary disease

It is known that signals recorded from physiological systems represent nonlinear features. Several recent studies report that quantitative information about signal complexity is obtained by using nonlinear analysis algorithms. Chronic obstructive pulmonary disease (COPD) is one of the causes of mortality worldwide with an increasing prevalence. This study aims to investigate nonlinear parameters such as largest Lyapunov exponent (LLE) and correlation dimension of electrodermal activity signals recorded from healthy subjects and patients with COPD. Electrodermal activity signals recorded from 14 healthy subjects and 24 patients with COPD were analysed. Auditory and tactile stimuli were applied at different time intervals during the recording process. Signals were reconstructed in the phase space compatible with theory and LLE and correlation dimension values were calculated. Statistical analysis was performed by using Shapiro-Wilk normality test, one-way analysis of variance (ANOVA) with Bonferroni post-test and Kruskal-Wallis non-parametric test. It was determined that the chaoticity and the complexity of the system increased in the presence of COPD. The systematic auditory stimuli increases chaoticity more than random auditory stimuli. Furthermore it was observed that participants develop habituation to the same auditory stimuli in time. There is no significant difference between COPD groups. Different results were found for the tactile stimuli applied to right or left ear. The results revealed that the nonlinear analysis of physiological data can be used for the development of new strategies for the diagnosis of chronic diseases.

EEG Analytics for Early Detection of Autism Spectrum Disorder: A data-driven approach

Autism spectrum disorder (ASD) is a complex and heterogeneous disorder, diagnosed on the basis of behavioral symptoms during the second year of life or later. Finding scalable biomarkers for early detection is challenging because of the variability in presentation of the disorder and the need for simple measurements that could be implemented routinely during well-baby checkups. EEG is a relatively easy-to-use, low cost brain measurement tool that is being increasingly explored as a potential clinical tool for monitoring atypical brain development. EEG measurements were collected from 99 infants with an older sibling diagnosed with ASD, and 89 low risk controls, beginning at 3 months of age and continuing until 36 months of age. Nonlinear features were computed from EEG signals and used as input to statistical learning methods. Prediction of the clinical diagnostic outcome of ASD or not ASD was highly accurate when using EEG measurements from as early as 3 months of age. Specificity, sensitivity and PPV were high, exceeding 95% at some ages. Prediction of ADOS calibrated severity scores for all infants in the study using only EEG data taken as early as 3 months of age was strongly correlated with the actual measured scores. This suggests that useful digital biomarkers might be extracted from EEG measurements.

Detection of time-, frequency- and direction-resolved communication within brain networks

Electroencephalography (EEG) records fast-changing neuronal signalling and communication and thus can offer a deep understanding of cognitive processes. However, traditional data analyses which employ the Fast-Fourier Transform (FFT) have been of limited use as they do not allow time- and frequency-resolved tracking of brain activity and detection of directional connectivity. Here, we applied advanced qEEG tools using autoregressive (AR) modelling, alongside traditional approaches, to murine data sets from common research scenarios: (a) the effect of age on resting EEG; (b) drug actions on non-rapid eye movement (NREM) sleep EEG (pharmaco-EEG); and (c) dynamic EEG profiles during correct vs incorrect spontaneous alternation responses in the Y-maze. AR analyses of short data strips reliably detected age- and drug-induced spectral EEG changes, while renormalized partial directed coherence (rPDC) reported direction- and time-resolved connectivity dynamics in mice. Our approach allows for the first time inference of behaviour- and stage-dependent data in a time- and frequency-resolved manner, and offers insights into brain networks that underlie working memory processing beyond what can be achieved with traditional methods.

The Emerging Role of Neurodiagnostic Informatics in Integrated Neurological and Mental Health Care

Mental, neurological, and neurodevelopmental (MNN) disorders impose an enormous burden of disease globally. Many MNN disorders follow a developmental trajectory. Thus, defining symptoms of MNN disorders may be conceived as the end product of a long developmental process. Many pharmaceutical therapies are aimed at the end symptoms, essentially attempting to reverse pathological brain function that has developed over a long time. A new paradigm is needed to leverage the developmental trajectory of MNN disorders, based on measuring brain function through the life span. Electroencephalography (EEG) is ideally suited for this task. New developments in several fields, including consumer EEG hardware, ubiquitous access to the Internet and electronic health records, and nonlinear mathematics to extract information from physiological signals have converged to enable new approaches to integrating EEG into routine health care. Research continues to demonstrate that EEG analysis can be used to discover digital biomarkers for a wide range of MNN disorders, including autism, attention-deficit/hyperactivity disorder (ADHD), schizophrenia and dementias, and likely many others. When EEG-derived information about brain function is stored with an electronic health record, clinical decision support software may use these data to detect atypical brain development in the earliest stages, thus opening a potential window for early intervention. These developments create an opportunity for neurodiagnostics to merge with biomedical informatics to create clinical tools for monitoring brain function through the life span. Advanced professionals with neurodiagnostics and biomedical informatics skills and training are needed to lead the way in this emerging field.

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

Electroencephalography (EEG) is frequently used in functional neurological assessment of children with neurological and neuropsychiatric disorders. Multiscale entropy (MSE) can reveal complexity in both short and long time scales and is more feasible in the analysis of EEG. Entropy-based estimation of EEG complexity is a powerful tool in investigating the underlying disturbances of neural networks of the brain. Most neurological and neuropsychiatric disorders in childhood affect the early stage of brain development. The analysis of EEG complexity may show the influences of different neurological and neuropsychiatric disorders on different regions of the brain during development. This article aims to give a brief summary of current concepts of MSE analysis in pediatric neurological and neuropsychiatric disorders. Studies utilizing MSE or its modifications for investigating neurological and neuropsychiatric disorders in children were reviewed. Abnormal EEG complexity was shown in a variety of childhood neurological and neuropsychiatric diseases, including autism, attention deficit/hyperactivity disorder, Tourette syndrome, and epilepsy in infancy and childhood. MSE has been shown to be a powerful method for analyzing the non-linear anomaly of EEG in childhood neurological diseases. Further studies are needed to show its clinical implications on diagnosis, treatment, and outcome prediction.