Identification Of Autism Spectrum Disorder Research Articles

Autism spectrum disorder identification with multi-site functional magnetic resonance imaging

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by enduring difficulties in social interaction and communication. People analyzed with ASD may display repetitive behaviors and limited interests. Autism is classified as a spectrum disorder, implying that the symptom intensity might range from mild to severe depending on the individual. To detect ASD in this paper an attribute feature graph approach is designed by using the stastical dependencies features that necessarily accomplish the diagnosis of ASD. In the first phase the features extracted are designed based on the functional magnetic resonance imaging (fMRI) data, in the next-step the attribute feature graph layer learns the features of the node information of various nodes by ASD classification. Further, in the third step, it is employed to independently extract distinguishing features from the functional connectivity matrices of the brain that are derived from fMRI. The custom convolutional neural network (CNN) used in this study is trained on a comprehensive dataset comprising individuals diagnosed with ASD and typically developing individuals. In the fourth stage, a prototype learning is developed to augment the classification performance of the custom-CNN. The experimental analysis further carried out states that the proposed model works efficiently in comparison with the existing system.

Early Play Behaviors of Infants at Elevated Likelihood for Autism Spectrum Disorder.

Although research has examined early identification of autism spectrum disorder (ASD), few studies have found behavioral markers during midinfancy associated with later ASD diagnosis. To examine infants' play behaviors and atypical positions at age 6 mo and later outcome classification among infants at elevated likelihood (EL) and typical likelihood (TL) for ASD. Atypical positions refer to movement patterns indicative of motor delays or deviations, including atypical extension and flexion, poor weight shift and rotation, hypertonicity or hypotonicity, and the presence of primitive reflex patterns. Observational cohort longitudinal design using blinded video analysis. Fifty-eight infants (41 EL infants and 17 TL infants) 6 mo of age. Infants later diagnosed with ASD needed more support to engage in play at age 6 mo compared with infants who did not receive an ASD diagnosis (U = 130, z = -2.29, p < .05, r = .31). Atypical positions at 6 mo of age were not associated with a later diagnosis of ASD. Play behaviors may be early indicators of developmental differences for infants later diagnosed with ASD. The results of this pilot study suggest the need to observe the quality of interaction with a caregiver and objects during early play, which may serve as potential early indicators of ASD. Plain-Language Summary: Few studies have found behavioral markers during midinfancy that are associated with a later diagnosis of autism spectrum disorder (ASD). The results of this study showed that infants who were later diagnosed with ASD were found to have differences in play behaviors compared to infants who were not later diagnosed with ASD. Thus, early play behaviors may be an early indicator of developmental differences for infants who are later diagnosed with ASD.

Autism spectrum disorder identification using multi‐model deep ensemble classifier with transfer learning

AbstractIdentifying autism spectrum disorder (ASD) symptoms accurately is a challenging task. The traditional subjective diagnostic process of ASD relies on time‐consuming behavioural and psychological observations. In this study, we introduce an ensemble learning‐based classification model using an open‐access database focusing on functional magnetic resonance imaging (fMRI). We propose a novel multi‐model ensemble classifier (MMEC) and multisite ensemble classifier (MSEC) with transfer learning (TL) for ASD classification to improve the prediction accuracy. The MMEC utilizes four base classifiers, Inception V3, ResNet50, MobileNet, and DenseNet to boost the performance of the individual convolutional neural network (CNN) models. The MSEC combined the base classifiers trained from different data sites. We evaluate the two models with ensemble averaging, weighted averaging, and stacking methods. The proposed MMEC with stacking shows the state of art performance compared to MSEC, improving the prediction accuracy by 3.25%. The obtained results have shown an accuracy of 97.82%, 97.82%, and 97.78% for ensemble averaging, weighted averaging, and stacking methods, respectively, on multi‐site datasets. The ensemble classifier MMEC performed better than a single classifier on the multi‐site dataset. The proposed MMEC opens a new paradigm to design a universal ASD classification framework.

Identifying autism spectrum disorder from multi-modal data with privacy-preserving

The application of deep learning models to precision medical diagnosis often requires the aggregation of large amounts of medical data to effectively train high-quality models. However, data privacy protection mechanisms make it difficult to perform medical data collection from different medical institutions. In autism spectrum disorder (ASD) diagnosis, automatic diagnosis using multimodal information from heterogeneous data has not yet achieved satisfactory performance. To address the privacy preservation issue as well as to improve ASD diagnosis, we propose a deep learning framework using multimodal feature fusion and hypergraph neural networks for disease prediction in federated learning (FedHNN). By introducing the federated learning strategy, each local model is trained and computed independently in a distributed manner without data sharing, allowing rapid scaling of medical datasets to achieve robust and scalable deep learning predictive models. To further improve the performance with privacy preservation, we improve the hypergraph model for multimodal fusion to make it suitable for autism spectrum disorder (ASD) diagnosis tasks by capturing the complementarity and correlation between modalities through a hypergraph fusion strategy. The results demonstrate that our proposed federated learning-based prediction model is superior to all local models and outperforms other deep learning models. Overall, our proposed FedHNN has good results in the work of using multi-site data to improve the performance of ASD identification.

A Nomogram for Predicting ADHD and ASD in Child and Adolescent Mental Health Services (CAMHS).

Objectives: To enhance the early detection of Attention Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) by leveraging clinical variables collected at child and adolescent mental health services (CAMHS). Methods: This study included children diagnosed with ADHD and/or ASD (n = 857). Three logistic regression models were developed to predict the presence of ADHD, its subtypes, and ASD. The analysis began with univariate logistic regression, followed by a multicollinearity diagnostic. A backward logistic regression selection strategy was then employed to retain variables with p < 0.05. Ethical approval was obtained from the local ethics committee. The models' internal validity was evaluated based on their calibration and discriminative abilities. Results: The study produced models that are well-calibrated and validated for predicting ADHD (incorporating variables such as physical activity, history of bone fractures, and admissions to pediatric/psychiatric services) and ASD (including disability, gender, special education needs, and Axis V diagnoses, among others). Conclusions: Clinical variables can play a significant role in enhancing the early identification of ADHD and ASD.

Early identification of autism spectrum disorder based on machine learning with eye-tracking data

BackgroundEarly identification of autism spectrum disorder (ASD) improves long-term outcomes, yet significant diagnostic delays persist. MethodsA retrospective cohort of 449 children (ASD: 246, typically developing [TD]: 203) was used for model development. Eye-movement data were collected from the participants watching videos that featured eye-tracking paradigms for assessing social and non-social cognition. Five machine learning algorithms, namely random forest, support vector machine, logistic regression, artificial neural network, and extreme gradient boosting, were trained to classify children with ASD and TD. The best-performing algorithm was selected to build the final model which was further evaluated in a prospective cohort of 80 children. The Shapley values interpreted important eye-tracking features. ResultsRandom forest outperformed other algorithms during model development and achieved an area under the curve of 0.849 (< 3 years: 0.832, ≥ 3 years: 0.868) on the external validation set. Of the ten most important eye-tracking features, three measured social cognition, and the rest were related to non-social cognition. A deterioration in model performance was observed using only the social or non-social cognition-related eye-tracking features. LimitationsThe sample size of this study, although larger than that of existing studies of ASD based on eye-tracking data, was still relatively small compared to the number of features. ConclusionsMachine learning models based on eye-tracking data have the potential to be cost- and time-efficient digital tools for the early identification of ASD. Eye-tracking phenotypes related to social and non-social cognition play an important role in distinguishing children with ASD from TD children.

A novel approach for ASD recognition based on graph attention networks.

Early detection and diagnosis of Autism Spectrum Disorder (ASD) can significantly improve the quality of life for affected individuals. Identifying ASD based on brain functional connectivity (FC) poses a challenge due to the high heterogeneity of subjects' fMRI data in different sites. Meanwhile, deep learning algorithms show efficacy in ASD identification but lack interpretability. In this paper, a novel approach for ASD recognition is proposed based on graph attention networks. Specifically, we treat the region of interest (ROI) of the subjects as node, conduct wavelet decomposition of the BOLD signal in each ROI, extract wavelet features, and utilize them along with the mean and variance of the BOLD signal as node features, and the optimized FC matrix as the adjacency matrix, respectively. We then employ the self-attention mechanism to capture long-range dependencies among features. To enhance interpretability, the node-selection pooling layers are designed to determine the importance of ROI for prediction. The proposed framework are applied to fMRI data of children (younger than 12 years old) from the Autism Brain Imaging Data Exchange datasets. Promising results demonstrate superior performance compared to recent similar studies. The obtained ROI detection results exhibit high correspondence with previous studies and offer good interpretability.

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.

Community testing practices for autism within the autism and developmental disabilities monitoring network.

No data exist at the population level on what tests are used to aid in the diagnosis of autism spectrum disorder in community practice. To describe autism spectrum disorder testing practices to inform autism spectrum disorder identification efforts. Data are from the Autism and Developmental Disabilities Monitoring Network, a multi-site surveillance system reporting prevalence estimates and characteristics of 8-year-old children with autism spectrum disorder. Percentages of children with autism spectrum disorder who received any autism spectrum disorder test or a 'gold standard' test were calculated by site, sex, race, median household income, and intellectual ability status. Risk ratios were calculated to compare group differences. Of 5058 8-year-old children with autism spectrum disorder across 11 sites, 3236 (64.0%) had a record of any autism spectrum disorder test and 2136 (42.2%) had a 'gold standard' ADOS or ADI-R test. Overall, 115 children (2.3%) had both the ADOS and ADI-R in their records. Differences persisted across race, median household income, and intellectual ability status. Asian/Pacific Islander children had the highest percent receiving any ASD test (71.8%; other groups range: 57.4-66.0%) and White children had the highest percent receiving 'gold standard' tests (46.4%; other groups range: 35.6-43.2%). Children in low-income neighbourhoods had a lower percent of any test (62.5%) and 'gold standard' tests (39.4%) compared to medium (70.2% and 47.5%, respectively) and high (69.6% and 46.8%, respectively) income neighbourhoods. Children with intellectual disability had a lower percent of any ASD test (81.7%) and 'gold standard' tests (52.6%) compared to children without intellectual disability (84.0% and 57.6%, respectively). Autism spectrum disorder testing practices vary widely by site and differ by race and presence of co-occurring intellectual disability, suggesting opportunities to standardise and/or improve autism spectrum disorder identification practices.

Identifying autism using EEG: unleashing the power of feature selection and machine learning

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that is characterized by communication barriers, societal disengagement, and monotonous actions. Currently, the diagnosis of ASD is made by experts through a subjective and time-consuming qualitative behavioural examination using internationally recognized descriptive standards. In this paper, we present an EEG-based three-phase novel approach comprising 29 autistic subjects and 30 neurotypical people. In the first phase, preprocessing of data is performed from which we derived one continuous dataset and four condition-based datasets to determine the role of each dataset in the identification of autism from neurotypical people. In the second phase, time-domain and morphological features were extracted and four different feature selection techniques were applied. In the last phase, five-fold cross-validation is used to evaluate six different machine learning models based on the performance metrics and computational efficiency. The neural network outperformed when trained with maximum relevance and minimum redundancy (MRMR) algorithm on the continuous dataset with 98.10% validation accuracy and 0.9994 area under the curve (AUC) value for model validation, and 98.43% testing accuracy and AUC test value of 0.9998. The decision tree overall performed the second best in terms of computational efficiency and performance accuracy. The results indicate that EEG-based machine learning models have the potential for ASD identification from neurotypical people with a more objective and reliable method.

Identification of autism spectrum disorder using multiple functional connectivity-based graph convolutional network.

Presently, the combination of graph convolutional networks (GCN) with resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising approach for early diagnosis of autism spectrum disorder (ASD). However, the prevalent approach involves exclusively full-brain functional connectivity data for disease classification using GCN, while overlooking the prior information related to the functional connectivity of brain subnetworks associated with ASD. Therefore, in this study, the multiple functional connectivity-based graph convolutional network (MFC-GCN) framework is proposed, using not only full brain functional connectivity data but also the established functional connectivity data from networks of key brain subnetworks associated with ASD, and the GCN is adopted to acquire complementary feature information for the final classification task. Given the heterogeneity within the Autism Brain Imaging Data Exchange (ABIDE) dataset, a novel External Attention Network Readout (EANReadout) is introduced. This design enables the exploration of potential subject associations, effectively addressing the dataset's heterogeneity. Experiments were conducted on the ABIDE dataset using the proposed framework, involving 714 subjects, and the average accuracy of the framework was 70.31%. The experimental results show that the proposed EANReadout outperforms the best traditional readout layer and improves the average accuracy of the framework by 4.32%.

Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing

PurposeThe main aim of our study was to explore the utility of artificial intelligence (AI) in diagnosing autism spectrum disorder (ASD). The study primarily focused on using machine learning (ML) and deep learning (DL) models to detect ASD potential cases by analyzing text inputs, especially from social media platforms like Twitter. This is to overcome the ongoing challenges in ASD diagnosis, such as the requirement for specialized professionals and extensive resources. Timely identification, particularly in children, is essential to provide immediate intervention and support, thereby improving the quality of life for affected individuals.MethodsWe employed natural language processing (NLP) techniques along with ML models like decision trees, extreme gradient boosting (XGB), k-nearest neighbors algorithm (KNN), and DL models such as recurrent neural networks (RNN), long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), bidirectional encoder representations from transformers (BERT and BERTweet). We extracted a dataset of 404,627 tweets from Twitter users using the platform’s API and classified them based on whether they were written by individuals claiming to have ASD (ASD users) or by those without ASD (non-ASD users). From this dataset, we used a subset of 90,000 tweets (45,000 from each classification group) for the training and testing of these models.ResultsThe application of our AI models yielded promising results, with the predictive model reaching an accuracy of almost 88% when classifying texts that potentially originated from individuals with ASD.ConclusionOur research demonstrated the potential of using AI, particularly DL models, in enhancing the accuracy of ASD detection and diagnosis. This innovative approach signifies the critical role AI can play in advancing early diagnostic techniques, enabling better patient outcomes and underlining the importance of early identification of ASD, especially in children.

Multipattern graph convolutional network-based autism spectrum disorder identification.

The early diagnosis of autism spectrum disorder (ASD) has been extensively facilitated through the utilization of resting-state fMRI (rs-fMRI). With rs-fMRI, the functional brain network (FBN) has gained much attention in diagnosing ASD. As a promising strategy, graph convolutional networks (GCN) provide an attractive approach to simultaneously extract FBN features and facilitate ASD identification, thus replacing the manual feature extraction from FBN. Previous GCN studies primarily emphasized the exploration of topological simultaneously connection weights of the estimated FBNs while only focusing on the single connection pattern. However, this approach fails to exploit the potential complementary information offered by different connection patterns of FBNs, thereby inherently limiting the performance. To enhance the diagnostic performance, we propose a multipattern graph convolution network (MPGCN) that integrates multiple connection patterns to improve the accuracy of ASD diagnosis. As an initial endeavor, we endeavored to integrate information from multiple connection patterns by incorporating multiple graph convolution modules. The effectiveness of the MPGCN approach is evaluated by analyzing rs-fMRI scans from a cohort of 92 subjects sourced from the publicly accessible Autism Brain Imaging Data Exchange database. Notably, the experiment demonstrates that our model achieves an accuracy of 91.1% and an area under ROC curve score of 0.9742. The implementation codes are available at https://github.com/immutableJackz/MPGCN.

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.

A Thorough Review of Deep Learning in Autism Spectrum Disorder Detection: From Data to Diagnosis

Background: Autism Spectrum Disorder (ASD) is a multifaceted neurodevelopmental condition with significant heterogeneity in its clinical presentation. Timely and precise identification of ASD is crucial for effective intervention and assistance. Recent advances in deep learning techniques have shown promise in enhancing the accuracy of ASD detection. Objective: This comprehensive review aims to provide an overview of various deep learning methods employed in detecting ASD, utilizing diverse neuroimaging modalities. We analyze a range of studies that use resting-state functional Magnetic Resonance Imaging (rsfMRI), structural MRI (sMRI), task-based fMRI (tfMRI), and electroencephalography (EEG). This paper aims to assess the effectiveness of these techniques based on criteria such as accuracy, sensitivity, specificity, and computational efficiency. Methods: We systematically review studies investigating ASD detection using deep learning across different neuroimaging modalities. These studies utilize various preprocessing tools, atlases, feature extraction techniques, and classification algorithms. The performance metrics of interest include accuracy, sensitivity, specificity, precision, F1-score, recall, and area under the curve (AUC). Results: The review covers a wide range of studies, each with its own dataset and methodology. Notable findings include a study employing rsfMRI data from ABIDE that achieved an accuracy of 80% using LeNet. Another study using rsfMRI data from ABIDE-II achieved an impressive accuracy of 95.4% with the ASGCN deep learning model. Studies utilizing different modalities, such as EEG and sMRI, also reported high accuracies ranging from 74% to 95%. Conclusion: Deep learning-based approaches for ASD detection have demonstrated significant potential across multiple neuroimaging modalities. These methods offer a more objective and data-driven approach to diagnosis, potentially reducing the subjectivity associated with clinical evaluations. However, challenges remain, including the need for larger and more diverse datasets, model interpretability, and clinical validation. The field of deep learning in ASD diagnosis continues to evolve, holding promise for early and accurate identification of individuals with ASD, which is crucial for timely intervention and support.

Psychological Assessment of Autism Spectrum Disorders using Machine Learning

This research aims to advance the field of autism spectrum disorder (ASD) assessment by proposing a machine learning-based approach tailored for school and community settings. Leveraging a diverse dataset encompassing behavioral, physiological, and neuroimaging data, we apply advanced machine learning algorithms to develop predictive models for early ASD detection. Our study integrates expert interviews to validate the clinical utility of these models and explores ethical considerations surrounding data privacy and bias. Preliminary results show promising accuracy in ASD identification. This research contributes to a more accessible and objective ASD assessment, with implications for early intervention and inclusive support, particularly in educational and community contexts.

Cranio-Facial Characteristics in Autism Spectrum Disorder: A Scoping Review

Autism spectrum disorders (ASD) consist of a complex group of neurodevelopmental disorders characterised by qualitative impairments of social interactions, communication abilities, and a limited, stereotyped, and repetitive selection of interests and activities. In light of the imperative to identify a possible biomarker for ASD, it has been determined that craniofacial anomalies serve as significant risk factors for neurodevelopmental disorders. The aim of this scoping review is to deepen the knowledge of the scientific literature related to cranio-facial characteristics in individuals with ASD, with a particular focus on recent research advancements. The review was performed by employing the search strings ((“Autism Spectrum Disorder” OR autism OR ASD OR “Autism Spectrum”) AND (“facial morphology” OR “facial phenotype”)) on the databases PubMed/MEDLINE, Scopus, and ERIC as of March 9, 2023. The review comprised seven studies whose findings were obtained through quantitative analysis of Euclidean distances between anatomical landmarks. The examination of facial abnormalities represents a possible reliable diagnostic biomarker that could aid in the timely identification of ASD. Phenotypic characteristics that may serve as predictive indicators of the severity of autistic symptoms can be observed in certain individuals with ASD by applying anthropometric and instrumental measurements. The presence of a phenotype characterised by an increased intercanthal distance and a reduced facial midline height appears to be associated with a higher degree of severity in autistic symptoms. In addition, it is worth noting that facial asymmetry and facial masculinity can be considered reliable indicators for predicting a more severe manifestation of symptoms.

Autism spectrum disorder in ICD-11-a critical reflection of its possible impact on clinical practice and research.

This perspective article compares and contrasts the conceptualization of Autism Spectrum Disorder (ASD) in ICD-11 and DSM-5. By guiding the user through the ICD-11 text, it is argued that, in contrast to DSM-5, ICD-11 allows a high variety in symptom combinations, which results in an operationalization of ASD that is in favor of an extreme diverse picture, yet possibly at the expense of precision, including unforeseeable effects on clinical practice, care, and research. The clinical utility is questionable as this conceptualization can hardly be differentiated from other mental disorders and autism-like traits. It moves away from an observable, behavioral, and neurodevelopmental disorder to a disorder of inner experience that can hardly be measured objectively. It contains many vague and subjective concepts that lead to non-falsifiable diagnoses. This bears a large danger of false positive diagnoses, of further increased prevalence rates, limitations of access to ASD-specific services and of increasing the non-specificity of treatments. For research, the hypothesis is that the specificity of ASD will be reduced and this will additional increase the already high heterogeneity with the effect that replication of studies will be hampered. This could limit our understanding of etiology and biological pathways of ASD and bears the risk that precision medicine, i.e., a targeted approach for individual treatment strategies based on precise diagnostic markers, is more far from becoming reality. Thus, a more precise, quantitative description and more objective measurement of symptoms are suggested that define the clinical ASD phenotype. Identification of core ASD subtypes/endophenotypes and a precise description of symptoms is the necessary next step to advance diagnostic classification systems. Therefore, employing a more finely grained, objective, clinical symptom characterization which is more relatable to neurobehavioral concepts is of central significance.

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.

EASDM: Explainable Autism Spectrum Disorder Model Based on Deep Learning

A neuro-developmental disorder known as autism spectrum disorder (ASD) affects a significant portion of the global population. Those with ASD frequently struggle to interact and communicate with others and may engage in restricted or repetitive behaviors or interests. The symptoms of autism begin early in childhood and can continue into adulthood. Machine learning and deep learning (DL) models are employed in clinical research for the early identification and diagnosis of ASD. However, the majority of the existing models lack interpretability in their results for ASD diagnosis. The explainable artificial intelligence (XAI) concepts can be used to provide transparent and understandable explanations for models’ decisions. In this work, we present an explainable autism spectrum disorder model based on DL for autism disorder detection in toddlers and children. The primary objective of this study is to better understand and interpret the classification process and to discern the significant features that contribute to the prediction of ASD. The proposed model is divided into two distinct components. The first component employs a DL model for autism disorder detection. The second uses an XAI technique known as shapley additive explanations (SHAP) to emphasis key characteristics and explain the model’s outcomes. The model showed perfect performance on the training set, with an accuracy of 1 and a receiver operating characteristic score of 1. On the test set, the model achieved an accuracy score of 0.9886, indicating that it performed nearly as well as on the training set. The experimental results demonstrate that the proposed model has the capability to accurately predict and diagnose ASD while also providing explanatory insights into the obtained results. Furthermore, the results indicate that the proposed model performs competitively compared to the state-of-the-art models in terms of accuracy and F1-score. The results highlight the efficacy and potential of the proposed model in accurately predicting ASD in binary classification tasks.