Autism Spectrum Disorder Classification Research Articles

Classification of Autism Spectrum Disorder using Resting State-Functional Magnetic Resonance Imaging and Artificial Neural Network

Autism Spectrum Disorder (ASD) represents a growing challenge in public health, characterized by irreversible neurodevelopmental abnormalities. Despite a rising prevalence, the underlying aetiology and neural substrates of ASD remain incompletely understood. Resting state-functional Magnetic Resonance Imaging (rs-fMRI) has emerged as a valuable non-invasive tool for probing the organization and cognitive functions of the brain by capturing hemodynamic changes. This study explores the relationship between Functional Connectivity (FC) alterations, measured by rs-fMRI, and the manifestation of ASD-related brain disorders. In this paper, we propose a hybrid approach employing an InfoMax Independent Component Analysis (ICA) algorithm and Artificial Neural Network to distinguish between the ASD subjects and Healthy Controls (HCs). Initially, rs-fMRI datasets are preprocessed using Statistical Parametric Mapping (SPM). Further, these datasets are processed using InfoMax ICA to extract the distinct features such as fractional Amplitude of Low-Frequency Fluctuations (fALFF) and Dynamic Range and visualize the FC alterations by region mapping. In addition to this, the number of activated voxels for each brain regions are estimated to observe the neural abnormalities. Finally, the extracted features are fed as input to train, test and validate the ANN classifier. The efficacy of the proposed network is evaluated using the Autism Brain Imaging Data Exchange (ABIDE) dataset and an accuracy of 75.3 percentage is achieved.

Artificial gannet optimization enabled deep convolutional neural network for autism spectrum disorders classification using MRI image

Artificial gannet optimization enabled deep convolutional neural network for autism spectrum disorders classification using MRI image

Diagnostic classification of autism spectrum disorder using sMRI improves with the morphological distance-related features compared to morphological features

Diagnostic classification of autism spectrum disorder using sMRI improves with the morphological distance-related features compared to morphological features

Classifying autism in a clinical population based on motion synchrony: a proof-of-concept study using real-life diagnostic interviews

Predictive modeling strategies are increasingly studied as a means to overcome clinical bottlenecks in the diagnostic classification of autism spectrum disorder. However, while some findings are promising in the light of diagnostic marker research, many of these approaches lack the scalability for adequate and effective translation to everyday clinical practice. In this study, our aim was to explore the use of objective computer vision video analysis of real-world autism diagnostic interviews in a clinical sample of children and young individuals in the transition to adulthood to predict diagnosis. Specifically, we trained a support vector machine learning model on interpersonal synchrony data recorded in Autism Diagnostic Observation Schedule (ADOS-2) interviews of patient-clinician dyads. Our model was able to classify dyads involving an autistic patient (n = 56) with a balanced accuracy of 63.4% against dyads including a patient with other psychiatric diagnoses (n = 38). Further analyses revealed no significant associations between our classification metrics with clinical ratings. We argue that, given the above-chance performance of our classifier in a highly heterogeneous sample both in age and diagnosis, with few adjustments this highly scalable approach presents a viable route for future diagnostic marker research in autism.

Using Machine Learning for Motion Analysis to Early Detect Autism Spectrum Disorder: A Systematic Review

AbstractDiagnosis of autism spectrum disorder (ASD) is typically performed using traditional tools based on behavioral observations. However, these diagnosis methods are time-consuming and can be misleading. Integrating machine learning algorithms with technological screening tools within the typical behavioral observations can possibly enhance the traditional assessment and diagnostic process. In the last two decades, to improve the accuracy and reliability of autism detection, many clinicians and researchers began to develop new screening methods by means of advanced technology like machine learning (ML). These methods include artificial neural networks (ANN), support vector machines (SVM), a priori algorithms, and decision trees (DT). Mostly, these methods have been applied to pre-existing datasets, derived from the standard diagnostic and assessment tools, to implement and test predictive models. On the other hand, the detection of new objective behavioral measures such as biomarkers could lead to a significant strengthening of existing screening tools. In the present study, we carried out a critical review of the literature about the latest findings in this field. The aim was to shed light about the effectiveness of using ML systems for motion analysis to enhance both clinical assessment and diagnostic processes. Specifically, we discussed the contribution of ML systems in promoting early diagnosis of ASD. The literature review showed that motion patterns ML analysis predicts ASD classification as accurately as that of classical gold standard tools. However, the application of these methods is still challenging, as discussed in this review.

Biosignal comparison for autism assessment using machine learning models and virtual reality

Clinical assessment procedures encounter challenges in terms of objectivity because they rely on subjective data. Computational psychiatry proposes overcoming this limitation by introducing biosignal-based assessments able to detect clinical biomarkers, while virtual reality (VR) can offer ecological settings for measurement. Autism spectrum disorder (ASD) is a neurodevelopmental disorder where many biosignals have been tested to improve assessment procedures. However, in ASD research there is a lack of studies systematically comparing biosignals for the automatic classification of ASD when recorded simultaneously in ecological settings, and comparisons among previous studies are challenging due to methodological inconsistencies. In this study, we examined a VR screening tool consisting of four virtual scenes, and we compared machine learning models based on implicit (motor skills and eye movements) and explicit (behavioral responses) biosignals. Machine learning models were developed for each biosignal within the virtual scenes and then combined into a final model per biosignal. A linear support vector classifier with recursive feature elimination was used and tested using nested cross-validation. The final model based on motor skills exhibited the highest robustness in identifying ASD, achieving an AUC of 0.89 (SD = 0.08). The best behavioral model showed an AUC of 0.80, while further research is needed for the eye-movement models due to limitations with the eye-tracking glasses. These findings highlight the potential of motor skills in enhancing objectivity and reliability in the early assessment of ASD compared to other biosignals.

Using visual attention estimation on videos for automated prediction of autism spectrum disorder and symptom severity in preschool children.

Atypical visual attention in individuals with autism spectrum disorders (ASD) has been utilised as a unique diagnosis criterion in previous research. This paper presents a novel approach to the automatic and quantitative screening of ASD as well as symptom severity prediction in preschool children. We develop a novel computational pipeline that extracts learned features from a dynamic visual stimulus to classify ASD children and predict the level of ASD-related symptoms. Experimental results demonstrate promising performance that is superior to using handcrafted features and machine learning algorithms, in terms of evaluation metrics used in diagnostic tests. Using a leave-one-out cross-validation approach, we obtained an accuracy of 94.59%, a sensitivity of 100%, a specificity of 76.47% and an area under the receiver operating characteristic curve (AUC) of 96% for ASD classification. In addition, we obtained an accuracy of 94.74%, a sensitivity of 87.50%, a specificity of 100% and an AUC of 99% for ASD symptom severity prediction.

Design and Implementation of Mobile Application for CNN-Based EEG Identification of Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a disorder of the nervous system from birth and during infancy. This disorder affects children's development, making it difficult for nerve function to develop, and causes the child concerned to have difficulty in fostering social relationships. Early detection of children with ASD is needed so that treatment is fast and on target. Currently, facilities and research on early diagnosis of ASD patients through EEG signals are still very few, requiring much cost and more effort to analyze EEG signals in examinations related to ASD detection cases. This study proposes a mobile phone application that can distinguish people living with ASD and normal data signals based on asynchronous EEG brain signals. This research also produces a preprocessing algorithm and BCI2000 EEG data signal so that it can be automated using Python. This research also produces an output model, namely the Deep Learning Convolutional Neural Network, which is deployed using Python-Flask so that the diagnosis of EEG signals with ASD and normal patients can be used on various platforms through restAPI. This research is also expected to help the community and support the diagnosis of ASD sufferers so that they can be handled appropriately. Data for ASD sufferers and normal data were correctly classified into the appropriate class. Handling this disease requires close and integrated cooperation, so this ASD classification will be very helpful for patients and can make a diagnosis in a faster time, enabling patients to receive targeted treatment and therapy.

Machine learning classification of autism spectrum disorder based on reciprocity in naturalistic social interactions

Autism spectrum disorder is characterized by impaired social communication and interaction. As a neurodevelopmental disorder typically diagnosed during childhood, diagnosis in adulthood is preceded by a resource-heavy clinical assessment period. The ongoing developments in digital phenotyping give rise to novel opportunities within the screening and diagnostic process. Our aim was to quantify multiple non-verbal social interaction characteristics in autism and build diagnostic classification models independent of clinical ratings. We analyzed videos of naturalistic social interactions in a sample including 28 autistic and 60 non-autistic adults paired in dyads and engaging in two conversational tasks. We used existing open-source computer vision algorithms for objective annotation to extract information based on the synchrony of movement and facial expression. These were subsequently used as features in a support vector machine learning model to predict whether an individual was part of an autistic or non-autistic interaction dyad. The two prediction models based on reciprocal adaptation in facial movements, as well as individual amounts of head and body motion and facial expressiveness showed the highest precision (balanced accuracies: 79.5% and 68.8%, respectively), followed by models based on reciprocal coordination of head (balanced accuracy: 62.1%) and body (balanced accuracy: 56.7%) motion, as well as intrapersonal coordination processes (balanced accuracy: 44.2%). Combinations of these models did not increase overall predictive performance. Our work highlights the distinctive nature of non-verbal behavior in autism and its utility for digital phenotyping-based classification. Future research needs to both explore the performance of different prediction algorithms to reveal underlying mechanisms and interactions, as well as investigate the prospective generalizability and robustness of these algorithms in routine clinical care.

Deep Fusion of Multi-Template Using Spatio-Temporal Weighted Multi-Hypergraph Convolutional Networks for Brain Disease Analysis.

Conventional functional connectivity network (FCN) based on resting-state fMRI (rs-fMRI) can only reflect the relationship between pairwise brain regions. Thus, the hyper-connectivity network (HCN) has been widely used to reveal high-order interactions among multiple brain regions. However, existing HCN models are essentially spatial HCN, which reflect the spatial relevance of multiple brain regions, but ignore the temporal correlation among multiple time points. Furthermore, the majority of HCN construction and learning frameworks are limited to using a single template, while the multi-template carries richer information. To address these issues, we first employ multiple templates to parcellate the rs-fMRI into different brain regions. Then, based on the multi-template data, we propose a spatio-temporal weighted HCN (STW-HCN) to capture more comprehensive high-order temporal and spatial properties of brain activity. Next, a novel deep fusion model of multi-template called spatio-temporal weighted multi-hypergraph convolutional network (STW-MHGCN) is proposed to fuse the STW-HCN of multiple templates, which extracts the deep interrelation information between different templates. Finally, we evaluate our method on the ADNI-2 and ABIDE-I datasets for mild cognitive impairment (MCI) and autism spectrum disorder (ASD) analysis. Experimental results demonstrate that the proposed method is superior to the state-of-the-art approaches in MCI and ASD classification, and the abnormal spatio-temporal hyper-edges discovered by our method have significant significance for the brain abnormalities analysis of MCI and ASD.

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.

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders

Background:The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD).Material and methodsWe analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections. We considered 1383 male subjects with age between 5 and 40 years, including 680 subjects with ASD and 703 TD from 35 different acquisition sites. We extracted morphometric and functional brain features from MRI scans with the Freesurfer and the CPAC analysis packages, respectively. Then, due to the multisite nature of the dataset, we implemented a data harmonization protocol. The ASD vs. TD classification was carried out with a multiple-input DL model, consisting in a neural network which generates a fixed-length feature representation of the data of each modality (FR-NN), and a Dense Neural Network for classification (C-NN). Specifically, we implemented a joint fusion approach to multiple source data integration. The main advantage of the latter is that the loss is propagated back to the FR-NN during the training, thus creating informative feature representations for each data modality. Then, a C-NN, with a number of layers and neurons per layer to be optimized during the model training, performs the ASD-TD discrimination. The performance was evaluated by computing the Area under the Receiver Operating Characteristic curve within a nested 10-fold cross-validation. The brain features that drive the DL classification were identified by the SHAP explainability framework.ResultsThe AUC values of 0.66±0.05 and of 0.76±0.04 were obtained in the ASD vs. TD discrimination when only structural or functional features are considered, respectively. The joint fusion approach led to an AUC of 0.78±0.04. The set of structural and functional connectivity features identified as the most important for the two-class discrimination supports the idea that brain changes tend to occur in individuals with ASD in regions belonging to the Default Mode Network and to the Social Brain.ConclusionsOur results demonstrate that the multimodal joint fusion approach outperforms the classification results obtained with data acquired by a single MRI modality as it efficiently exploits the complementarity of structural and functional brain information.

A robust microbiome signature for autism spectrum disorder across different studies using machine learning

Autism spectrum disorder (ASD) is a highly complex neurodevelopmental disorder characterized by deficits in sociability and repetitive behaviour, however there is a great heterogeneity within other comorbidities that accompany ASD. Recently, gut microbiome has been pointed out as a plausible contributing factor for ASD development as individuals diagnosed with ASD often suffer from intestinal problems and show a differentiated intestinal microbial composition. Nevertheless, gut microbiome studies in ASD rarely agree on the specific bacterial taxa involved in this disorder. Regarding the potential role of gut microbiome in ASD pathophysiology, our aim is to investigate whether there is a set of bacterial taxa relevant for ASD classification by using a sibling-controlled dataset. Additionally, we aim to validate these results across two independent cohorts as several confounding factors, such as lifestyle, influence both ASD and gut microbiome studies. A machine learning approach, recursive ensemble feature selection (REFS), was applied to 16S rRNA gene sequencing data from 117 subjects (60 ASD cases and 57 siblings) identifying 26 bacterial taxa that discriminate ASD cases from controls. The average area under the curve (AUC) of this specific set of bacteria in the sibling-controlled dataset was 81.6%. Moreover, we applied the selected bacterial taxa in a tenfold cross-validation scheme using two independent cohorts (a total of 223 samples—125 ASD cases and 98 controls). We obtained average AUCs of 74.8% and 74%, respectively. Analysis of the gut microbiome using REFS identified a set of bacterial taxa that can be used to predict the ASD status of children in three distinct cohorts with AUC over 80% for the best-performing classifiers. Our results indicate that the gut microbiome has a strong association with ASD and should not be disregarded as a potential target for therapeutic interventions. Furthermore, our work can contribute to use the proposed approach for identifying microbiome signatures across other 16S rRNA gene sequencing datasets.

Serum brain-derived neurotrophic factor concentration is different between autism spectrum disorders and intellectual disability children and adolescents

PurposeRecent studies showed that mature brain-derived neurotrophic factor (mBDNF) and its precursor proBDNF are associated with autism spectrum disorders (ASD). Whether their levels are different between ASD and intellectual disability (ID) subjects is not clear. The aim of this study is to compare the serum mBDNF and proBDNF concentration, and mBNDF/proBDNF ratio in ASD and ID volunteers. MethodsChildren and adolescents with ASD or ID between the ages of 4 and 22 were recruited in Tianjin, China. Serum mBDNF and proBDNF level were tested and Wechsler Preschool and Primary Scale of Intelligence (WPPSI), Wechsler Intelligence Scale for Children (WISC), and Childhood Autism Rating Scale (CARS) evaluations were conducted. ResultsSerum mBDNF concentration and the ratio of mBDNF to proBDNF was higher in ASD subjects than that in ID subjects (P = 0.035 and P < 0.001, respectively), while serum proBDNF of ASD participants was lower compared to that of ID participants (P < 0.001). CARS score was positively correlated with serum mBDNF level (r = 0.33, P = 0.004) and m/p ratio (r = 0.39, P < 0.001), and negatively correlated with serum proBDNF level (r = −0.39, <0.001) after adjusting for age and IQ. The AUC of mBDNF, proBDNF, and m/p ratio were 0.741, 0.790, and 0.854, respectively, after adjusted for age and IQ. ConclusionSerum mBDNF, proBDNF and m/p ratio were different between ASD and ID group. The three biomarkers displayed good diagnostic values for classification of ASD and ID subjects.

An Auto-encoded Warm Equilibrium Automated Learning (AE2L) Model for Automatic Recognition and Classification of Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurological condition characterized by difficulties with communication and socializing, and repetitive activities. If the underlying reason is hereditary, early detection is still important, and machine learning offers a fascinating way to identify the condition more rapidly and economically. However, the unique issues of higher computational costs, longer execution times, and lower effectiveness affect the traditional methods. The proposed project aims to create an automated artificial intelligence tool for ASD identification that combines several state-of-the-art mining techniques to deliver the best possible level of disease prediction accuracy. For accurate and effective ASD identification, this research suggests an automated and lightweight method dubbed the auto-encoded warm equilibrium automated learner. To speed up the handicap detection process, a unique warm optimized feature selection methodology is applied to minimize the dimensionality of attributes. In addition, auto-encoded term memory equilibrium learning, a powerful deep learning technique, is designed to accurately and less frequently detect ASD from the given data. Moreover, the classifier performs better when hyperparameters are tuned using the equilibrium optimization model. The results of the proposed AE2L model have been tested and validated using a variety of parameters utilizing the well-known ASD dataset that was taken from the UCI repository.

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

Transfer Learning and Hybrid Deep Convolutional Neural Networks Models for Autism Spectrum Disorder Classification From EEG Signals

Adam teaching learning optimization enabled LeNet for autism spectrum disorder detection using brain MRI

The autism spectrum disorder (ASD) is a complicated, lifetime, neuro-developmental circumstance of highly unknown causes. It is greatly more ordinary than formerly believed, frequency only to mental retardation amongst serious developmental disorders. Even though, a heritable element is demonstrated in the etiology of ASD, reputed risk genes are still to be detected. Therefore, Adam Teaching Learning Optimization-LeNet (ATLO-LeNet) is introduced for the detection of ASD utilizing brain Magnetic Resonance Imaging (MRI). Here, input considered is provided for the image pre-processing, wherein extraction of Region of Interest (ROI) is performed and median filter is used to eradicate noises. Then, extraction of the pivotal region is completed by the devised ATLO and hence, output-1 is obtained. On the other side, features are mined from an input MRI image. The extracted features include statistical features as well as texture features. From extracted features, output-2 is attained. By considering the output-1 and output-2, ASD classification is completed by LeNet. The LeNet is trained by ATLO, which is the amalgamation of the Adam algorithm and Teaching–Learning-Based Optimization (TLBO). Moreover, ATLO-LeNet acquired a maximum accuracy of 0.916, Negative Predictive Value (NPV) of 0.916and Positive Predictive Value (PPV) of 0.917 whereas it attained a minimum False Positive Rate (FPR) of 0.132 and False Negative Rate (FNR) of 0.152.

Modified Meta Heuristic BAT with ML Classifiers for Detection of Autism Spectrum Disorder.

ASD (autism spectrum disorder) is a complex developmental and neurological disorder that impacts the social life of the affected person by disturbing their capability for interaction and communication. As it is a behavioural disorder, early treatment will improve the quality of life of ASD patients. Traditional screening is carried out with behavioural assessment through trained physicians, which is expensive and time-consuming. To resolve the issue, several conventional methods strive to achieve an effective ASD identification system, but are limited by handling large data sets, accuracy, and speed. Therefore, the proposed identification system employed the MBA (modified bat) algorithm based on ANN (artificial neural networks), modified ANN (modified artificial neural networks), DT (decision tree), and KNN (k-nearest neighbours) for the classification of ASD in children and adolescents. A BA (bat algorithm) is utilised for the automatic zooming capability, which improves the system's efficacy by excellently finding the solutions in the identification system. Conversely, BA is effective in the identification, it still has certain drawbacks like speed, accuracy, and falls into local extremum. Therefore, the proposed identification system modifies the BA optimisation with random perturbation of trends and optimal orientation. The dataset utilised in the respective model is the Q-chat-10 dataset. This dataset contains data of four stages of age groups such as toddlers, children, adolescents, and adults. To analyse the quality of the dataset, dataset evaluation mechanism, such as the Chi-Squared Statistic and p-value, are used in the respective research. The evaluation signifies the relation of the dataset with respect to the proposed model. Further, the performance of the proposed detection system is examined with certain performance metrics to calculate its efficiency. The outcome revealed that the modified ANN classifier model attained an accuracy of 1.00, ensuring improved performance when compared with other state-of-the-art methods. Thus, the proposed model was intended to assist physicians and researchers in enhancing the diagnosis of ASD to improve the standard of life of ASD patients.

Fusing modalities by multiplexed graph neural networks for outcome prediction from medical data and beyond

With the emergence of multimodal electronic health records, the evidence for diseases, events, or findings may be present across multiple modalities ranging from clinical to imaging and genomic data. Developing effective patient-tailored therapeutic guidance and outcome prediction will require fusing evidence across these modalities. Developing general-purpose frameworks capable of modeling fine-grained and multi-faceted complex interactions, both within and across modalities is an important open problem in multimodal fusion. Generalized multimodal fusion is extremely challenging as evidence for outcomes may not be uniform across all modalities, not all modality features may be relevant, or not all modalities may be present for all patients, due to which simple methods of early, late, or intermediate fusion may be inadequate. In this paper, we present a novel approach that uses the machinery of multiplexed graphs for fusion. This allows for modalities to be represented through their targeted encodings. We model their relationship between explicitly via multiplexed graphs derived from salient features in a combined latent space. We then derive a new graph neural network for multiplex graphs for task-informed reasoning. We compare our framework against several state-of-the-art approaches for multi-graph reasoning and multimodal fusion. As a sanity check on the neural network design, we evaluate the multiplexed GNN on two popular benchmark datasets, namely the AIFB and the MUTAG dataset against several state-of-the-art multi-relational GNNs for reasoning. Second, we evaluate our multiplexed framework against several state-of-the-art multimodal fusion frameworks on two large clinical datasets for two separate applications. The first is the NIH-TB portals dataset for treatment outcome prediction in Tuberculosis, and the second is the ABIDE dataset for Autism Spectrum Disorder classification. Through rigorous experimental evaluation, we demonstrate that the multiplexed GNN provides robust performance improvements in all of these diverse applications.

Age- and Severity-Specific Deep Learning Models for Autism Spectrum Disorder Classification Using Functional Connectivity Measures

Age- and Severity-Specific Deep Learning Models for Autism Spectrum Disorder Classification Using Functional Connectivity Measures