Autism Spectrum Disorder Diagnostic System Using HOS Bispectrum with EEG Signals

Conduction velocity, G-ratio, and extracellular water as microstructural characteristics of autism spectrum disorder

The neuronal differences contributing to the etiology of autism spectrum disorder (ASD) are still not well defined. Previous studies have suggested that myelin and axons are disrupted during development in ASD. By combining structural and diffusion MRI techniques, myelin and axons can be assessed using extracellular water, aggregate g-ratio, and a new approach to calculating axonal conduction velocity termed aggregate conduction velocity, which is related to the capacity of the axon to carry information. In this study, several innovative cellular microstructural methods, as measured from magnetic resonance imaging (MRI), are combined to characterize differences between ASD and typically developing adolescent participants in a large cohort. We first examine the relationship between each metric, including microstructural measurements of axonal and intracellular diffusion and the T1w/T2w ratio. We then demonstrate the sensitivity of these metrics by characterizing differences between ASD and neurotypical participants, finding widespread increases in extracellular water in the cortex and decreases in aggregate g-ratio and aggregate conduction velocity throughout the cortex, subcortex, and white matter skeleton. We finally provide evidence that these microstructural differences are associated with higher scores on the Social Communication Questionnaire (SCQ) a commonly used diagnostic tool to assess ASD. This study is the first to reveal that ASD involves MRI-measurable in vivo differences of myelin and axonal development with implications for neuronal and behavioral function. We also introduce a novel formulation for calculating aggregate conduction velocity, that is highly sensitive to these changes. We conclude that ASD may be characterized by otherwise intact structural connectivity but that functional connectivity may be attenuated by network properties affecting neural transmission speed. This effect may explain the putative reliance on local connectivity in contrast to more distal connectivity observed in ASD.

Teachers and educators' experiences and perceptions of artificial-powered interventions for autism groups

BACKGROUND

Artificial intelligence-powered interventions have emerged as promising tools to support autistic individuals. However, more research must examine how teachers and educators perceive and experience these AI systems when implemented.

OBJECTIVES

The first objective was to investigate informants' perceptions and experiences of AI-empowered interventions for children with autism. Mainly, it explores the informants' perceived benefits and challenges of using AI-empowered interventions and their recommendations for avoiding the perceived challenges.

METHODOLOGY

A qualitative phenomenological approach was used. Twenty educators and parents with experience implementing AI interventions for autism were recruited through purposive sampling. Semi-structured and focus group interviews conducted, transcribed verbatim, and analyzed using thematic analysis.

FINDINGS

The analysis identified four major themes: perceived benefits of AI interventions, implementation challenges, needed support, and recommendations for improvement. Benefits included increased engagement and personalized learning. Challenges included technology issues, training needs, and data privacy concerns.

CONCLUSIONS

AI-powered interventions show potential to improve autism support, but significant challenges must be addressed to ensure effective implementation from an educator's perspective. The benefits of personalized learning and student engagement demonstrate the potential value of these technologies. However, with adequate training, technical support, and measures to ensure data privacy, many educators will likely find integrating AI systems into their daily practices easier.

IMPLICATIONS

To realize the full benefits of AI for autism, developers must work closely with educators to understand their needs, optimize implementation, and build trust through transparent privacy policies and procedures. With proper support, AI interventions can transform how autistic individuals are educated by tailoring instruction to each student's unique profile and needs.

Conduction Velocity, G-ratio, and Extracellular Water as Microstructural Characteristics of Autism Spectrum Disorder

The neuronal differences contributing to the etiology of autism spectrum disorder (ASD) are still not well defined. Previous studies have suggested that myelin and axons are disrupted during development in ASD. By combining structural and diffusion MRI techniques, myelin and axons can be assessed using extracellular water, aggregate g-ratio, and a novel metric termed aggregate conduction velocity, which is related to the capacity of the axon to carry information. In this study, several innovative cellular microstructural methods, as measured from magnetic resonance imaging (MRI), are combined to characterize differences between ASD and typically developing adolescent participants in a large cohort. We first examine the relationship between each metric, including microstructural measurements of axonal and intracellular diffusion and the T1w/T2w ratio. We then demonstrate the sensitivity of these metrics by characterizing differences between ASD and neurotypical participants, finding widespread increases in extracellular water in the cortex and decreases in aggregate g-ratio and aggregate conduction velocity throughout the cortex, subcortex, and white matter skeleton. We finally provide evidence that these microstructural differences are associated with higher scores on the Social Communication Questionnaire (SCQ) a commonly used diagnostic tool to assess ASD. This study is the first to reveal that ASD involves MRI-measurable in vivo differences of myelin and axonal development with implications for neuronal and behavioral function. We also introduce a novel neuroimaging metric, aggregate conduction velocity, that is highly sensitive to these changes. We conclude that ASD may be characterized by otherwise intact structural connectivity but that functional connectivity may be attenuated by network properties affecting neural transmission speed. This effect may explain the putative reliance on local connectivity in contrast to more distal connectivity observed in ASD.

Hybrid deep transfer learning-based early diagnosis of autism spectrum disorder using scalogram representation of electroencephalography signals

Early diagnosis of autism spectrum disorder (ASD) plays an important role in the rehabilitation of the patient. This goal necessitates higher-level pattern representation and a strong modeling approach. The proposed approach applies scalogram images of electroencephalography signals for the first purpose and a two-level deep learning architecture for better classification. Scalogram images embed both the temporal and spectral information of the signal. On the other hand, the hybrid deep learning hierarchy of convolutional neural network followed by long short-term memory models both spatial and temporal information of the scalogram image. The approach is evaluated on a dataset of 34 ASD samples and 11 normal cases in without-voice and with-voice conditions. To validate the early diagnosis hypothesis, signals from children older than 5 years are used as the training set, and signals from younger subjects are used as the validation set. The proposed method achieves excellent performance of 99.50% and 98.43% for automatically detecting ASD with and without voice, respectively. This classification performance is higher than most recent reported approaches, and the results show the effectiveness of the approach in early diagnosis of ASD and demonstrate the auditory impact on the diagnosis of autism.

ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework

Autism Spectrum Disorder (ASD) treatment requires accurate diagnosis and effective rehabilitation. Artificial intelligence (AI) techniques in medical diagnosis and rehabilitation can aid doctors in detecting a wide range of diseases more effectively. Nevertheless, due to its highly heterogeneous symptoms and complicated nature, ASD diagnostics continues to be a challenge for researchers. This study introduces an intelligent system based on the Artificial Gorilla Troops Optimizer (GTO) metaheuristic optimizer to detect ASD using Deep Learning and Machine Learning. Kaggle and UCI ML Repository are the data sources used in this study. The first dataset is the Autistic Children Data Set, which contains 3,374 facial images of children divided into Autistic and Non-Autistic categories. The second dataset is a compilation of data from three numerical repositories: (1) Autism Screening Adults, (2) Autistic Spectrum Disorder Screening Data for Adolescents, and (3) Autistic Spectrum Disorder Screening Data for Children. When it comes to image dataset experiments, the most notable results are (1) a TF learning ratio greater than or equal to 50 is recommended, (2) all models recommend data augmentation, and (3) the DenseNet169 model reports the lowest loss value of 0.512. Concerning the numeric dataset, five experiments recommend standardization and the final five attributes are optional in the classification process. The performance metrics demonstrate the worthiness of the proposed feature selection technique using GTO more than counterparts in the literature review.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Role of Artificial Intelligence for Autism Diagnosis Using DTI and fMRI: A Survey

Autism spectrum disorder (ASD) is a wide range of diseases characterized by difficulties with social skills, repetitive activities, speech, and nonverbal communication. The Centers for Disease Control (CDC) estimates that 1 in 44 American children currently suffer from ASD. The current gold standard for ASD diagnosis is based on behavior observational tests by clinicians, which suffer from being subjective and time-consuming and afford only late detection (a child must have a mental age of at least two to apply for an observation report). Alternatively, brain imaging-more specifically, magnetic resonance imaging (MRI)-has proven its ability to assist in fast, objective, and early ASD diagnosis and detection. With the recent advances in artificial intelligence (AI) and machine learning (ML) techniques, sufficient tools have been developed for both automated ASD diagnosis and early detection. More recently, the development of deep learning (DL), a young subfield of AI based on artificial neural networks (ANNs), has successfully enabled the processing of brain MRI data with improved ASD diagnostic abilities. This survey focuses on the role of AI in autism diagnostics and detection based on two basic MRI modalities: diffusion tensor imaging (DTI) and functional MRI (fMRI). In addition, the survey outlines the basic findings of DTI and fMRI in autism. Furthermore, recent techniques for ASD detection using DTI and fMRI are summarized and discussed. Finally, emerging tendencies are described. The results of this study show how useful AI is for early, subjective ASD detection and diagnosis. More AI solutions that have the potential to be used in healthcare settings will be introduced in the future.

Cross-Frequency Multilayer Network Analysis with Bispectrum-based Functional Connectivity: A Study of Alzheimer's Disease

Alzheimer's disease (AD) is a neurodegenerative disorder known to affect functional connectivity (FC) across many brain regions. Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals, such as electroencephalography (EEG) recordings, into discrete frequency bands and analysing them in isolation from each other. We address this limitation by quantifying cross-frequency FC in addition to the traditional within-band approach. Cross-bispectrum, a higher-order spectral analysis approach, is used to measure the nonlinear FC and is compared with the cross-spectrum, which only measures the linear FC within bands. This work reports the reconstruction of a cross-frequency FC network where each frequency band is treated as a layer in a multilayer network with both inter- and intra-layer edges. Cross-bispectrum detects cross-frequency differences, mainly increased FC in AD cases in δ-θ coupling. Overall, increased strength of low-frequency coupling and decreased level of high-frequency coupling is observed in AD cases in comparison to healthy controls (HC). We demonstrate that a graph-theoretic analysis of cross-frequency brain networks is crucial to obtain a more detailed insight into their structure and function. Vulnerability analysis reveals that the integration and segregation properties of networks are enabled by different frequency couplings in AD networks compared to HCs. Finally, we use the reconstructed networks for classification. The extra cross-frequency coupling information can improve the classification performance significantly, suggesting an important role of cross-frequency FC. The results highlight the importance of studying nonlinearity and including cross-frequency FC in characterising AD.

Quantitative assessment of cognitive profile and brain asymmetry in the characterization of autism spectrum in children: A task-based EEG study

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by learning, attention, social, communication, and behavioral impairments. Each person with Autism has a different severity and level of brain functioning, ranging from high functioning (HF) to low functioning (LF), depending on their intellectual/developmental abilities. Identifying the level of functionality remains crucial in understanding the cognitive abilities of Autistic children. Assessment of EEG signals acquired during specific cognitive tasks is more appropriate in identifying brain functional and cognitive load variations. The spectral power of EEG sub-band frequency and parameters related to brain asymmetry has the potential to be employed as indices to characterize brain functioning. Thus, the objective of this work is to analyze the cognitive task-based electrophysiological variations in autistic and control groups, using EEG acquired during two well-defined protocols. Theta to Alpha ratio (TAR) and Theta to Beta ratio (TBR) of absolute powers of the respective sub-band frequencies have been estimated to quantify the cognitive load. The variations in interhemispheric cortical power measured by EEG were studied using the brain asymmetry index. For the arithmetic task, the TBR of the LF group was found to be considerably higher than the HF group. The findings reveal that the spectral powers of EEG sub-bands can be a key indicator in the assessment of high and low-functioning ASD to facilitate appropriate training strategies. Instead of depending solely on behavioral tests to diagnose autism, it could be a beneficial approach to use task-based EEG characteristics to differentiate between the LF and HF groups.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Technologies to support the diagnosis and/or treatment of neurodevelopmental disorders: A systematic review

In recent years, there has been a great interest in utilizing technology in mental health research. The rapid technological development has encouraged researchers to apply technology as a part of a diagnostic process or treatment of Neurodevelopmental Disorders (NDDs). With the large number of studies being published comes an urgent need to inform clinicians and researchers about the latest advances in this field. Here, we methodically explore and summarize findings from studies published between August 2019 and February 2022. A search strategy led to the identification of 4108 records from PubMed and APA PsycInfo databases. 221 quantitative studies were included, covering a wide range of technologies used for diagnosis and/or treatment of NDDs, with the biggest focus on Autism Spectrum Disorder (ASD). The most popular technologies included machine learning, functional magnetic resonance imaging, electroencephalogram, magnetic resonance imaging, and neurofeedback. The results of the review indicate that technology-based diagnosis and intervention for NDD population is promising. However, given a high risk of bias of many studies, more high-quality research is needed.

Epilepsy and EEG Abnormalities in Children with Autism Spectrum Disorders

OBJECTIVE

To evaluate the prevalence of epilepsy and  electroencephalographic abnormalities in children with autism spectrum disorders (ASD) and determine their risk factors.

METHODS

This cross-sectional study was conducted over one year in children with ASD aged between 3 and 14 y. Classification of epilepsy and routine electroencephalography (EEG) recordings were done for all the patients. Developmental and cognitive assessments were done using Developmental Profile 3. Children were divided into three groups: ASD with epilepsy, ASD with isolated electroencephalographic abnormalities, and ASD with neither epilepsy nor electroencephalographic abnormalities.

RESULTS

One hundred children with ASD were enrolled. Epilepsy was reported in 23% and subclinical electroencephalographic abnormalities were documented in 8%. The most common seizure types were generalized-onset tonic-clonic (48%), focal-onset with impaired awareness (17%), and focal to bilateral tonic-clonic seizures (17%). In children with subclinical epileptiform discharges, focal abnormalities were most common (75%) and were maximally seen over the temporal region (50%). Subnormal intellect (88.6%) and abnormal global developmental score (82%) were noted in the majority of children. Female gender, abnormal neurological examination, and adverse perinatal events were significantly associated with epilepsy. Of these, female gender and adverse perinatal events were independent predictors of epilepsy. Isolated EEG abnormalities were significantly associated with abnormal neurological examination in comparison with autistic children without epilepsy/EEG abnormalities.

CONCLUSION

Epilepsy is seen in up to one-fourth children with ASD. Female gender and adverse perinatal events are independent risk factors for epilepsy. Subclinical or isolated EEG abnormalities are associated with abnormal neurological examination.

A model for analyzing evolutions of neurons by using EEG waves

It is known that differences between potentials of soma, dendrites and different parts of neural structures may be the origin of electroencephalogram (EEG) waves. These potentials may be produced by some excitatory synapses and currents of charges between neurons and then thereafter may themselves cause the emergence of new synapses and electrical currents. These currents within and between neurons emit some electromagnetic waves which could be absorbed by electrodes on the scalp, and form topographic images. In this research, a model is proposed which formulates EEG topographic parameters in terms of the charge and mass of exchanged particles within neurons, those which move between neurons, the number of neurons and the length of neurons and synapses. In this model, by knowing the densities of the frequencies in different regions of the brain, one can predict the type, charge and velocity of particles which are moving along neurons or are exchanged between neurons.

Triage and priority-based healthcare diagnosis using artificial intelligence for autism spectrum disorder and gene contribution: A systematic review

The exact nature, harmful effects and aetiology of autism spectrum disorder (ASD) have caused widespread confusion. Artificial intelligence (AI) science helps solve challenging diagnostic problems in the medical field through extensive experiments. Disease severity is closely related to triage decisions and prioritisation contexts in medicine because both have been widely used to diagnose various diseases via AI, machine learning and automated decision-making techniques. Recently, taking advantage of high-performance AI algorithms has achieved accessible success in diagnosing and predicting risks from clinical and biological data. In contrast, less progress has been made with ASD because of obscure reasons. According to academic literature, ASD diagnosis works from a specific perspective, and much of the confusion arises from the fact that how AI techniques are currently integrated with the diagnosis of ASD concerning the triage and priority strategies and gene contributions. To this end, this study sought to describe a systematic review of the literature to assess the respective AI methods using the available datasets, highlight the tools and strategies used for diagnosing ASD and investigate how AI trends contribute in distinguishing triage and priority for ASD and gene contributions. Accordingly, this study checked the Science Direct, IEEE Xplore Digital Library, Web of Science (WoS), PubMed, and Scopus databases. A set of 363 articles from 2017 to 2022 is collected to reveal a clear picture and a better understanding of all the academic literature through a final set of 18 articles. The retrieved articles were filtered according to the defined inclusion and exclusion criteria and classified into three categories. The first category includes 'Triage patients based on diagnosis methods' which accounts for 16.66% (n = 3/18). The second category includes 'Prioritisation for Risky Genes' which accounts for 66.6% (n = 12/18) and is classified into two subcategories: 'Mutations observation based', 'Biomarkers and toxic chemical observations'. The third category includes 'E-triage using telehealth' which accounts for 16.66% (n = 3/18). This multidisciplinary systematic review revealed the taxonomy, motivations, recommendations and challenges of ASD research that need synergistic attention. Thus, this systematic review performs a comprehensive science mapping analysis and discusses the open issues that help perform and improve the recommended solution of ASD research direction. In addition, this study critically reviews the literature and attempts to address the current research gaps in knowledge and highlights weaknesses that require further research. Finally, a new developed methodology has been suggested as future work for triaging and prioritising ASD patients according to their severity levels by using decision-making techniques.

Brain Network for Exploring the Change of Brain Neurotransmitter 5-Hydroxytryptamine of Autism Children by Resting-State EEG

The study was aimed at understanding the brain network and the change rule of brain neurotransmitter 5-hydroxytryptamine (5-HT) in autism children through resting-state electroencephalogram (EEG). 20 autistic children in hospital were selected and defined as the observation group. Meanwhile, 20 healthy children were defined as the control group. EEG signals were collected for the two groups. Fuzzy C-means (FCM) algorithm was used to extract features of EEG signals, and DTF was applied for the causal association between multichannel EEG signals. The two groups were compared for the average function value and regional efficiency of the brain neurotransmitter 5-HT. The results showed that the classification accuracy of frontal F7 channel, left frontal FP1 channel, and temporal T6 channel was 95.2%, 95.3%, and 91.2%, respectively. The average of high beta frequency band, low beta frequency band, theta frequency band, and alpha frequency band in the control group was significantly higher than that in the observation group under the optimal threshold (P < 0.05). Compared with normal subjects (34.27), the average function of 5-HT in the brain was 20.13 in patients with low function and 45.74 in patients with hyperfunction. In conclusion, FCM algorithm can feature extraction of EEG signals, especially in the frontal F7 channel, the left frontal FP1 channel, and the TEMPORAL T6 channel, which has high classification accuracy and can well express the EEG signals of autistic children. The level of 5-HT in autistic children is lower than that in healthy people, and it is closely related to loneliness and depression.

Accurate detection of autism using Douglas-Peucker algorithm, sparse coding based feature mapping and convolutional neural network techniques with EEG signals

Autism Spectrum Disorders (ASD) is a collection of complicated neurological disorders that first show in early childhood. Electroencephalogram (EEG) signals are widely used to record the electrical activities of the brain. Manual screening is prone to human errors, tedious, and time-consuming. Hence, a novel automated method involving the Douglas-Peucker (DP) algorithm, sparse coding-based feature mapping approach, and deep convolutional neural networks (CNNs) is employed to detect ASD using EEG recordings. Initially, the DP algorithm is used for each channel to reduce the number of samples without degradation of the EEG signal. Then, the EEG rhythms are extracted by using the wavelet transform. The EEG rhythms are coded by using the sparse representation. The matching pursuit algorithm is used for sparse coding of the EEG rhythms. The sparse coded rhythms are segmented into 8 bits length and then converted to decimal numbers. An image is formed by concatenating the histograms of the decimated rhythm signals. Extreme learning machines (ELM)-based autoencoders (AE) are employed at a data augmentation step. After data augmentation, the ASD and healthy EEG signals are classified using pre-trained deep CNN models. Our proposed method yielded an accuracy of 98.88%, the sensitivity of 100% and specificity of 96.4%, and the F1-score of 99.19% in the detection of ASD automatically. Our developed model is ready to be tested with more EEG signals before its clinical application.

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.

Artificial Intelligence Enabled Personalised Assistive Tools to Enhance Education of Children with Neurodevelopmental Disorders-A Review

Mental disorders (MDs) with onset in childhood or adolescence include neurodevelopmental disorders (NDDs) (intellectual disability and specific learning disabilities, such as dyslexia, attention deficit disorder (ADHD), and autism spectrum disorders (ASD)), as well as a broad range of mental health disorders (MHDs), including anxiety, depressive, stress-related and psychotic disorders. There is a high co-morbidity of NDDs and MHDs. Globally, there have been dramatic increases in the diagnosis of childhood-onset mental disorders, with a 2- to 3-fold rise in prevalence for several MHDs in the US over the past 20 years. Depending on the type of MD, children often grapple with social and communication deficits and difficulties adapting to changes in their environment, which can impact their ability to learn effectively. To improve outcomes for children, it is important to provide timely and effective interventions. This review summarises the range and effectiveness of AI-assisted tools, developed using machine learning models, which have been applied to address learning challenges in students with a range of NDDs. Our review summarises the evidence that AI tools can be successfully used to improve social interaction and supportive education. Based on the limitations of existing AI tools, we provide recommendations for the development of future AI tools with a focus on providing personalised learning for individuals with NDDs.

Affective Video Tagging Framework using Human Attention Modelling through EEG Signals

The explosion of multimedia content over the past years is not surprising, thus their efficient management and analysis methods are always in demand. The affectiveness of any multimedia content deals with analyzing human perception and cognition while watching it. Human attention is also one of the important parameters, as it describes the engagement and interestingness of the user while watching that content. Considering this aspect, a video tagging framework is proposed in which the EEG signals of participants are used to analyze human perception while watching videos. A rigorous analysis has been performed on different scalp locations and frequency rhythms of brain signals to formulate significant features corresponding to affective and interesting video content. The analysis presented in this paper shows that the extracted human attention-based features are generating promising results with the accuracy of 93.2% using SVM-based classification model which supports the applicability of the model for various BCI-based applications for automatic classification of multimedia content.

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

Deep learning for neuroimaging-based diagnosis and rehabilitation of Autism Spectrum Disorder: A review

Accurate diagnosis of Autism Spectrum Disorder (ASD) followed by effective rehabilitation is essential for the management of this disorder. Artificial intelligence (AI) techniques can aid physicians to apply automatic diagnosis and rehabilitation procedures. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. DL methods for diagnosis of ASD have been focused on neuroimaging-based approaches. Neuroimaging techniques are non-invasive disease markers potentially useful for ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, proposing optimum procedures for ASD diagnosis with neuroimaging data without exploiting powerful AI techniques like DL may be challenging. In this paper, studies conducted with the aid of DL networks to distinguish ASD are investigated. Rehabilitation tools provided for supporting ASD patients utilizing DL networks are also assessed. Finally, we will present important challenges in the automated detection and rehabilitation of ASD and propose some future works.

Detection of an Autism EEG Signature From Only Two EEG Channels Through Features Extraction and Advanced Machine Learning Analysis

BACKGROUND AND OBJECTIVE

In 2 previous studies, we have shown the ability of special machine learning systems applied to standard EEG data in distinguishing children with autism spectrum disorder (ASD) from non-ASD children with an overall accuracy rate of 100% and 98.4%, respectively. Since the equipment routinely available in neonatology units employ few derivations, we were curious to check if just 2 derivations were enough to allow good performance in the same cases of the above-mentioned studies.

METHODS

A continuous segment of artifact-free EEG data lasting 1 minute in ASCCI format from C3 and C4 EEG channels present in 2 previous studies, was used for features extraction and subsequent analyses with advanced machine learning systems. A features extraction software package (Python tsfresh) applied to time-series raw data derived 1588 quantitative features. A special hybrid system called TWIST (Training with Input Selection and Testing), coupling an evolutionary algorithm named Gen-D and a backpropagation neural network, was used to subdivide the data set into training and testing sets as well as to select features yielding the maximum amount of information after a first variable selection performed with linear correlation index threshold.

RESULTS

After this intelligent preprocessing, 12 features were extracted from C3-C4 time-series of study 1 and 36 C3-C4 time-series of study 2 representing the EEG signature. Acting on these features the overall accuracy predictive capability of the best artificial neural network acting as a classifier in deciphering autistic cases from typicals (study 1) and other neuropsychiatric disorders (study 2) resulted in 100 % for study 1 and 94.95 % for study 2.

CONCLUSIONS

The results of this study suggest that also a minor part of EEG contains precious information useful to detect autism if treated with advanced computational algorithms. This could allow in the future to use standard EEG from newborns to check if the ASD signature is already present at birth.

Risk Prediction of Second Primary Endometrial Cancer in Obese Women: A Hospital-Based Cancer Registry Study

Due to the high effectiveness of cancer screening and therapies, the diagnosis of second primary cancers (SPCs) has increased in women with endometrial cancer (EC). However, previous studies providing adequate evidence to support screening for SPCs in endometrial cancer are lacking. This study aimed to develop effective risk prediction models of second primary endometrial cancer (SPEC) in women with obesity (body mass index (BMI) > 25) and included datasets on the incidence of SPEC and the other risks of SPEC in 4480 primary cancer survivors from a hospital-based cancer registry database. We found that obesity plays a key role in SPEC. We used 10 independent variables as predicting variables, which correlated to obesity, and so should be monitored for the early detection of SPEC in endometrial cancer. Our proposed scheme is promising for SPEC prediction and demonstrates the important influence of obesity and clinical data representation in all cases following primary treatments. Our results suggest that obesity is still a crucial risk factor for SPEC in endometrial cancer.

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.

A novel automated autism spectrum disorder detection system

Autism spectrum disorder (ASD) is a neurological and developmental disorder that begins early in childhood and lasts throughout a person’s life. Autism is influenced by both genetic and environmental factors. Lack of social interaction, communication problems, and a limited range of behaviors and interests are possible characteristics of autism in children, alongside other symptoms. Electroencephalograms provide useful information about changes in brain activity and hence are efficaciously used for diagnosis of neurological disease. Eighteen nonlinear features were extracted from EEG signals of 40 children with a diagnosis of autism spectrum disorder and 37 children with no diagnosis of neuro developmental disorder children. Feature selection was performed using Student’s t test, and Marginal Fisher Analysis was employed for data reduction. The features were ranked according to Student’s t test. The three most significant features were used to develop the autism index, while the ranked feature set was input to SVM polynomials 1, 2, and 3 for classification. The SVM polynomial 2 yielded the highest classification accuracy of 98.70% with 20 features. The developed classification system is likely to aid healthcare professionals as a diagnostic tool to detect autism. With more data, in our future work, we intend to employ deep learning models and to explore a cloud-based detection system for the detection of autism. Our study is novel, as we have analyzed all nonlinear features, and we are one of the first groups to have uniquely developed an autism (ASD) index using the extracted features.

Automated ASD detection using hybrid deep lightweight features extracted from EEG signals

BACKGROUND

Autism spectrum disorder is a common group of conditions affecting about one in 54 children. Electroencephalogram (EEG) signals from children with autism have a common morphological pattern which makes them distinguishable from normal EEG. We have used this type of signal to design and implement an automated autism detection model.

MATERIALS AND METHOD

We propose a hybrid lightweight deep feature extractor to obtain high classification performance. The system was designed and tested with a big EEG dataset that contained signals from autism patients and normal controls. (i) A new signal to image conversion model is presented in this paper. In this work, features are extracted from EEG signal using one-dimensional local binary pattern (1D_LBP) and the generated features are utilized as input of the short time Fourier transform (STFT) to generate spectrogram images. (ii) The deep features of the generated spectrogram images are extracted using a combination of pre-trained MobileNetV2, ShuffleNet, and SqueezeNet models. This method is named hybrid deep lightweight feature generator. (iii) A two-layered ReliefF algorithm is used for feature ranking and feature selection. (iv) The most discriminative features are fed to various shallow classifiers, developed using a 10-fold cross-validation strategy for automated autism detection.

RESULTS

A support vector machine (SVM) classifier reached 96.44% accuracy based on features from the proposed model.

CONCLUSIONS

The results strongly indicate that the proposed hybrid deep lightweight feature extractor is suitable for autism detection using EEG signals. The model is ready to serve as part of an adjunct tool that aids neurologists during autism diagnosis in medical centers.

Epileptic Seizures Detection Using Deep Learning Techniques: A Review

A variety of screening approaches have been proposed to diagnose epileptic seizures, using electroencephalography (EEG) and magnetic resonance imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning (DL). Before the rise of DL, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in DL, the extraction of features and classification are entirely automated. The advent of these techniques in many areas of medicine, such as in the diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented. Various methods proposed to diagnose epileptic seizures automatically using EEG and MRI modalities are described. In addition, rehabilitation systems developed for epileptic seizures using DL have been analyzed, and a summary is provided. The rehabilitation tools include cloud computing techniques and hardware required for implementation of DL algorithms. The important challenges in accurate detection of automated epileptic seizures using DL with EEG and MRI modalities are discussed. The advantages and limitations in employing DL-based techniques for epileptic seizures diagnosis are presented. Finally, the most promising DL models proposed and possible future works on automated epileptic seizure detection are delineated.

Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991-2020)

Understanding the data and reaching accurate conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have been widely used for this purpose in various fields. One critically important yet less explored aspect is capturing and analyzing uncertainties in the data and model. Proper quantification of uncertainty helps to provide valuable information to obtain accurate diagnosis. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, various novel deep learning techniques have been proposed to deal with such uncertainties and improve the performance in decision making.

Virulence factor-related gut microbiota genes and immunoglobulin A levels as novel markers for machine learning-based classification of autism spectrum disorder

Autism spectrum disorder (ASD) is a neurodevelopmental condition for which early identification and intervention is crucial for optimum prognosis. Our previous work showed gut Immunoglobulin A (IgA) to be significantly elevated in the gut lumen of children with ASD compared to typically developing (TD) children. Gut microbiota variations have been reported in ASD, yet not much is known about virulence factor-related gut microbiota (VFGM) genes. Upon determining the VFGM genes distinguishing ASD from TD, this study is the first to utilize VFGM genes and IgA levels for a machine learning-based classification of ASD. Sequence comparisons were performed of metagenome datasets from children with ASD (n = 43) and TD children (n = 31) against genes in the virulence factor database. VFGM gene composition was associated with ASD phenotype. VFGM gene diversity was higher in children with ASD and positively correlated with IgA content. As Group B streptococcus (GBS) genes account for the highest proportion of 24 different VFGMs between ASD and TD and positively correlate with gut IgA, GBS genes were used in combination with IgA and VFGMs diversity to distinguish ASD from TD. Given that VFGM diversity, increases in IgA, and ASD-enriched VFGM genes were independent of sex and gastrointestinal symptoms, a classification method utilizing them will not pertain only to a specific subgroup of ASD. By introducing the classification value of VFGM genes and considering that VFs can be isolated in pregnant women and newborns, these findings provide a novel machine learning-based early risk identification method for ASD.

Automated Detection of Sleep Stages Using Deep Learning Techniques: A Systematic Review of the Last Decade (2010–2020)

Sleep is vital for one’s general well-being, but it is often neglected, which has led to an increase in sleep disorders worldwide. Indicators of sleep disorders, such as sleep interruptions, extreme daytime drowsiness, or snoring, can be detected with sleep analysis. However, sleep analysis relies on visuals conducted by experts, and is susceptible to inter- and intra-observer variabilities. One way to overcome these limitations is to support experts with a programmed diagnostic tool (PDT) based on artificial intelligence for timely detection of sleep disturbances. Artificial intelligence technology, such as deep learning (DL), ensures that data are fully utilized with low to no information loss during training. This paper provides a comprehensive review of 36 studies, published between March 2013 and August 2020, which employed DL models to analyze overnight polysomnogram (PSG) recordings for the classification of sleep stages. Our analysis shows that more than half of the studies employed convolutional neural networks (CNNs) on electroencephalography (EEG) recordings for sleep stage classification and achieved high performance. Our study also underscores that CNN models, particularly one-dimensional CNN models, are advantageous in yielding higher accuracies for classification. More importantly, we noticed that EEG alone is not sufficient to achieve robust classification results. Future automated detection systems should consider other PSG recordings, such as electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals, along with input from human experts, to achieve the required sleep stage classification robustness. Hence, for DL methods to be fully realized as a practical PDT for sleep stage scoring in clinical applications, inclusion of other PSG recordings, besides EEG recordings, is necessary. In this respect, our report includes methods published in the last decade, underscoring the use of DL models with other PSG recordings, for scoring of sleep stages.

Profiling of pornography addiction among children using EEG signals: A systematic literature review

Nowadays human behavior has been affected with the advent of new digital technologies. Due to the rampant use of the Internet by children, many have been addicted to pornography. This addiction has negatively affected the behaviors of children including increased impulsiveness, learning ability to attention, poor decision-making, memory problems, and deficit in emotion regulation. The children with porn addiction can be identified by parents and medical practitioners as third-party observers. This systematic literature review (SLR) is conducted to increase the understanding of porn addiction using electroencephalogram (EEG) signals. We have searched five different databases namely IEEE, ACM, Science Direct, Springer and National Center for Biotechnology Information (NCBI) using addiction, porn, and EEG as keywords along with 'OR 'operation in between the expressions. We have selected 46 studies in this work by screening 815,554 papers from five databases. Our results show that it is possible to identify children with porn addiction using EEG signals.

Risk Prediction for Early Chronic Kidney Disease: Results from an Adult Health Examination Program of 19,270 Individuals

Developing effective risk prediction models is a cost-effective approach to predicting complications of chronic kidney disease (CKD) and mortality rates; however, there is inadequate evidence to support screening for CKD. In this study, four data mining algorithms, including a classification and regression tree, a C4.5 decision tree, a linear discriminant analysis, and an extreme learning machine, are used to predict early CKD. The study includes datasets from 19,270 patients, provided by an adult health examination program from 32 chain clinics and three special physical examination centers, between 2015 and 2019. There were 11 independent variables, and the glomerular filtration rate (GFR) was used as the predictive variable. The C4.5 decision tree algorithm outperformed the three comparison models for predicting early CKD based on accuracy, sensitivity, specificity, and area under the curve metrics. It is, therefore, a promising method for early CKD prediction. The experimental results showed that Urine protein and creatinine ratio (UPCR), Proteinuria (PRO), Red blood cells (RBC), Glucose Fasting (GLU), Triglycerides (TG), Total Cholesterol (T-CHO), age, and gender are important risk factors. CKD care is closely related to primary care level and is recognized as a healthcare priority in national strategy. The proposed risk prediction models can support the important influence of personality and health examination representations in predicting early CKD.