Identification Of Autism Spectrum Disorder Research Articles

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.

Validating the Child Behavior Checklist 1.5-5 as a screening tool for autism spectrum disorder.

Early identification of Autism Spectrum Disorder is very important, especially in low and middle-income countries, where access to resources is often limited. The Child Behavior Checklist 1.5-5 is a tool that has been used to help identify children with autism spectrum disorder through specific behavior patterns. However, its effectiveness in low- and middle-income country settings has not been thoroughly studied. This research focused on evaluating the Child Behavior Checklist 1.5-5 as a screening tool for autism spectrum disorder among Brazilian children. The study involved 1292 children aged 3-5 years from the general population and 70 children with autism spectrum disorder aged 1-5 years. Using advanced statistical methods, the study tested how well the Child Behavior Checklist identified children with autism spectrum disorder and how reliable it was in this context. The findings showed that the Child Behavior Checklist 1.5-5 performed well in identifying autism spectrum disorder, with high reliability and consistency in the results. Although one item in each of the autism spectrum problems and withdrawn syndrome subscales did not perform as strongly, the overall tool was effective. In summary, the Child Behavior Checklist 1.5-5 proves to be a reliable and valid tool for early autism spectrum disorder screening in Brazilian children. This can help ensure that more children in low- and middle-income country settings are identified early and receive the necessary support and interventions to help them thrive. Future research should continue to test this tool in different contexts to confirm its usefulness across various populations.

Enhancing Autism Spectrum Disorder identification in multi-site MRI imaging: A multi-head cross-attention and multi-context approach for addressing variability in un-harmonized data

Multi-site MRI imaging poses a significant challenge due to the potential variations in images across different scanners at different sites. This variability can introduce ambiguity in further image analysis. Consequently, the image analysis techniques become site-dependent and scanner-dependent, implying that adjustments in the analysis methodologies are necessary for each scanner configuration. Further, implementing real-time modifications becomes intricate, particularly when incorporating a new type of scanner, as it requires adapting the analysis methods accordingly. Taking into account the aforementioned challenge, we have considered its implications for an Autism spectrum disorder (ASD) application. Our objective is to minimize the impact of site and scanner variability in the analysis, aiming to develop a model that remains effective across different scanners and sites.This entails devising a methodology that allows the same model to function seamlessly across multiple scanner configurations and sites. ASD, a behavioral disorder affecting child development, requires early detection. Clinical observation is time-consuming, prompting the use of fMRI with machine/deep learning for expedited diagnosis. Previous methods leverage fMRI’s functional connectivity but often rely on less generalized feature extractors and classifiers. Hence, there is significant room for improvement in the generalizability of detection methods across multi-site data, which is acquired from multiple scanners with different settings. In this study, we propose a Cross-Combination Multi-Scale Multi-Context Framework (CCMSMCF) capable of performing neuroimaging-based diagnostic classification of mental disorders for a multi-site dataset. Thus, this framework attains a degree of internal data harmonization, rendering it to some extent site and scanner-agnostic. Our proposed network, CCMSMCF, is constructed by integrating two sub-modules: the Multi-Head Attention Cross-Scale Module (MHACSM) and the Residual Multi-Context Module (RMCN). We also employ multiple loss functions in a novel manner for training the model, which includes Binary Cross Entropy, Dice loss, and Embedding Coupling loss. The model is validated on the Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, which includes data from multiple scanners across different sites, and achieves promising results.

ESTRATÉGIAS DA ANÁLISE DO COMPORTAMENTO APLICADA PARA DESENVOLVER A INTERAÇÃO SOCIAL EM CRIANÇAS AUTISTAS

Autism Spectrum Disorder (ASD) has evolved from a psychiatric classification to a neurodevelopmental disorder, reflecting advances in scientific understanding and diagnostic approaches. The DSM-5, with its more sensitive criteria, facilitates early identification of ASD, which is crucial for effective interventions. Applied Behavior Analysis (ABA) is a proven approach for enhancing social skills and reducing problematic behaviors in children with ASD. By employing techniques such as positive reinforcement and modeling, ABA fosters individualized communication and social interaction, providing significant benefits for both children and their families. Integrating playful resources and innovative strategies can complement interventions, promoting greater autonomy and self-awareness in autistic children. Ongoing advancements in ASD diagnosis and treatment, combined with scientific innovation, are essential for improving the quality of life for children and their families.

A - 65 Neuropsychological Testing to Increase Early and Accurate Identification of Autism Spectrum Disorder in Black and Brown Children

Abstract Objectives Neuropsychological evaluations provide information that can potentially minimize the risk of poor outcomes and enhance the quality of life for children with Autism Spectrum Disorder (ASD). Black and Brown children have higher incidences of misdiagnosis and are also diagnosed later than their White peers. There is support for the efficacy of neuropsychological evaluation compared to routine care in the diagnosis of ASD. This study analyzes neuropsychological assessment practices and diagnosis trends by race, ethnicity, and gender, incorporating teacher and parent perceptions through behavioral rating scales. Data Selection The following selection criteria were utilized: -articles published in peer-reviewed journals focusing on neuropsychological evaluations of ASD among black and brown children-employed a variety of assessment tools and methodologies - reporting on cultural considerations, validity, and reliability of neuropsychological assessments in children of color. Data Synthesis Gender, ethnic, and racial differences in the timing and rate of diagnosis have delayed the onset of crucial treatment. Additionally, there are linguistic variables and differences in how parents and teachers endorse symptoms of ASD by race and ethnicity on rating scales included in comprehensive neuropsychological evaluations that can impact the assessment. Conclusions Early intervention is associated with improved outcomes for individuals diagnosed with ASD. However, there is a significant imbalance between the growing numbers of ethnic/racial and linguistic minority children in the United States who require neuropsychological services and the limited number of neuropsychologists trained to handle the cultural complexities. Accurate, culturally informed neuropsychological assessments are needed to ensure equitable behavioral health services are provided to this vulnerable population.

A - 64 Neuropsychological Assessment of Autism Spectrum Disorder

Abstract Objective Now more than ever, the neuropsychologist is frequently called upon to assess and diagnosis Autism Spectrum Disorder (ASD). Neuropsychological assessment provides a comprehensive and objective analysis of a child suspected of having ASD. To ensure accurate and early diagnosis of young children, this review will inform on the essential domains to include in the evaluation of ASD, highlight the cognitive profile of individuals with ASD, and address gender differences to consider as part of the diagnosis. Data Selection The following selection criteria were utilized: -articles published in peer-reviewed journals during the previous 10 years focusing on neuropsychological evaluations of ASD -employed a variety of assessment tools and methodologies - reporting on validity and reliability of specific measures to include in the evaluation of ASD in children. Data Synthesis It is essential to evaluate intelligence, attention, executive functioning, social communication, and fine motor skills as part of a comprehensive neuropsychological evaluation. Intelligence tests can sometimes underestimate the IQ of individuals with ASD. The uneven cognitive development in children with ASD makes accurate diagnosis even more challenging. Sex related cognitive profiles should be considered to assist in the accurate diagnosis of girls with ASD. Conclusions Early and accurate identification of ASD in children is essential for improved outcomes. Schools, physicians, insurance agencies, and other stakeholders rely on the results of the neuropsychological evaluation to authorize essential interventions. Therefore, it is imperative to employ the most recent research related to the assessment of ASD, with an emphasis on increasing the identification of girls.

Relationship between teacher ideals and attitudes toward peers with autism spectrum disorder among teacher college students

Purpose This study aims to examine the relationship between teacher ideals and attitudes toward peers with autism spectrum disorder (ASD) among teacher college students, and the effect of knowledge of ASD identification on this relationship. Design/methodology/approach This study used a quantitative approach and included 341 teacher college students. A vignette was used to assess social and professional attitudes toward peers with ASD. The participants were divided into identification and nonidentification groups based on how accurately they identified the peer depicted in the vignette as having ASD. A teacher ideals questionnaire consisting of two subscales indicating different ideal teachers − a dedicated/engaging teacher (e.g. a teacher who can work with enthusiasm) and a skillful teacher (e.g. a teacher who is knowledgeable) − was developed and administered to evaluate the participants’ teacher ideals and self-perceptions of a teacher. Findings In the nonidentification group, ideals of a skillful teacher were significantly correlated with social attitudes toward peers with ASD. The identification group exhibited no significant correlations between ideals and social attitudes. Furthermore, the self-perceptions of being a dedicated/engaging teacher was significantly correlated with professional attitudes toward peers with ASD in the identification group. Originality/value To the best of the authors’ knowledge, this study is the first to examine the relationship between teacher ideals and attitudes toward peers with ASD. Teacher ideals were related to negative social attitudes toward peers with ASD. While knowledge of ASD identification weakens this relationship, it may drive the relationship between self-perceptions of a teacher and professional attitudes toward peers with ASD. Therefore, ASD education is important for reducing the stigma toward ASD in teacher education.

Performance of the Social Responsiveness Scale-2 for the Assessment of Autistic Behaviors in a Sample of Canadian Preschool-Aged Children.

Behavioral traits of autism spectrum disorder (ASD) typically present in early childhood, underscoring the importance of screening tools for the early identification of ASD. The current study compared scores on the Social Responsiveness Scale-Second Edition (SRS-2) Preschool Form between the US standardization sample (n = 247) and a Canadian cohort of preschool-aged children (n = 595) recruited from the Maternal-Infant Research on Environmental Chemicals (MIREC) study. In the MIREC sample, we examined whether ASD-like traits are correlated with sociodemographic characteristics and child intellectual abilities, and how maternal ratings of social skills assessed by the SRS-2 are associated with maternal ratings of general problem behaviors. Mean total SRS-2 raw score was significantly lower in the MIREC sample (mean = 29.7, SD = 15.8) compared to the US standardization sample (mean = 41.9, SD = 26.0). Total raw score in the US standardization sample did not significantly differ between males (mean = 40.6, SD = 23.1) and females (mean = 42.8, SD = 28.7), whereas in the MIREC sample the total raw score was significantly higher among males (mean = 33.0, SD = 17.1) than females (mean = 26.6, SD = 13.9). A significantly larger proportion of the MIREC sample was White, younger in age, and had more educated parents compared to the US standardization sample. ASD-like traits were correlated with lower intellectual abilities, a less enriched home environment, more behavioral problems, and poorer adaptive skills. SRS-2 Preschool Form scores were significantly lower in the Canadian sample compared to the US standardization sample, which may reflect demographic differences between the two groups. Girls may be under-identified when SRS-2 Preschool Form norms are used for screening ASD.

A multi-frequency approach of the altered functional connectome for autism spectrum disorder identification.

Autism spectrum disorder stands as a multifaceted and heterogeneous neurodevelopmental condition. The utilization of functional magnetic resonance imaging to construct functional brain networks proves instrumental in comprehending the intricate interplay between brain activity and autism spectrum disorder, thereby elucidating the underlying pathogenesis at the cerebral level. Traditional functional brain networks, however, typically confine their examination to connectivity effects within a specific frequency band, disregarding potential connections among brain areas that span different frequency bands. To harness the full potential of interregional connections across diverse frequency bands within the brain, our study endeavors to develop a novel multi-frequency analysis method for constructing a comprehensive functional brain networks that incorporates multiple frequencies. Specifically, our approach involves the initial decomposition of functional magnetic resonance imaging into distinct frequency bands through wavelet transform. Subsequently, Pearson correlation is employed to generate corresponding functional brain networks and kernel for each frequency band. Finally, the classification was performed by a multi-kernel support vector machine, to preserve the connectivity effects within each band and the connectivity patterns shared among the different bands. Our proposed multi-frequency functional brain networks method yielded notable results, achieving an accuracy of 89.1%, a sensitivity of 86.67%, and an area under the curve of 0.942 in a publicly available autism spectrum disorder dataset.

Advancing ASD identification with neuroimaging: a novel GARL methodology integrating Deep Q-Learning and generative adversarial networks

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects an individual's behavior, speech, and social interaction. Early and accurate diagnosis of ASD is pivotal for successful intervention. The limited availability of large datasets for neuroimaging investigations, however, poses a significant challenge to the timely and precise identification of ASD. To address this problem, we propose a breakthrough approach, GARL, for ASD diagnosis using neuroimaging data. GARL innovatively integrates the power of GANs and Deep Q-Learning to augment limited datasets and enhance diagnostic precision. We utilized the Autistic Brain Imaging Data Exchange (ABIDE) I and II datasets and employed a GAN to expand these datasets, creating a more robust and diversified dataset for analysis. This approach not only captures the underlying sample distribution within ABIDE I and II but also employs deep reinforcement learning for continuous self-improvement, significantly enhancing the capability of the model to generalize and adapt. Our experimental results confirmed that GAN-based data augmentation effectively improved the performance of all prediction models on both datasets, with the combination of InfoGAN and DQN's GARL yielding the most notable improvement.

Restoring private autism dataset from sanitized database using an optimized key produced from enhanced combined PSO-GWO framework

The timely identification of autism spectrum disorder (ASD) in children is imperative to prevent potential challenges as they grow. When sharing data related to autism for an accurate diagnosis, safeguarding its security and privacy is a paramount concern to fend off unauthorized access, modification, or theft during transmission. Researchers have devised diverse security and privacy models or frameworks, most of which often leverage proprietary algorithms or adapt existing ones to address data leakage. However, conventional anonymization methods, although effective in the sanitization process, proved inadequate for the restoration process. Furthermore, despite numerous scholarly contributions aimed at refining the restoration process, the accuracy of restoration remains notably deficient. Based on the problems identified above, this paper presents a novel approach to data restoration for sanitized sensitive autism datasets with improved performance. In the prior study, we constructed an optimal key for the sanitization process utilizing the proposed Enhanced Combined PSO-GWO framework. This key was implemented to conceal sensitive autism data in the database, thus avoiding information leakage. In this research, the same key was employed during the data restoration process to enhance the accuracy of the original data recovery. Therefore, the study enhanced the restoration process for ASD data's security and privacy by utilizing an optimal key produced via the Enhanced Combined PSO-GWO framework. When compared to existing meta-heuristic algorithms, the simulation results from the autism data restoration experiments demonstrated highly competitive accuracies with 99.90%, 99.60%, 99.50%, 99.25%, and 99.70%, respectively. Among the four types of datasets used, this method outperforms other existing methods on the 30-month autism children dataset, mostly.

Object Exploration and Manipulation in Infants at Typical vs. Elevated Likelihood for ASD: A Review.

The present review considers the growing body of literature on fine motor skills in infants at elevated genetic likelihood (EL) for autism spectrum disorder (ASD). This area of study aims to identify crucial motor markers associated with the disorder, facilitating earlier and more accurate identification of ASD, using various experimental methodologies, including standardized assessments, observational measures, and technological tools. The reviewed evidence revealed distinct developmental trajectories in EL infants, marked by differences in fine motor skills and exploratory behaviors compared to typically developing infants. We discuss the developmental trajectory of fine motor skills in infants and their predictive value for later ASD diagnosis, highlighting the significance of fine motor skills as early indicators of ASD risk in infants and emphasizing the need for further research to elucidate their predictive value and underlying mechanisms.

STDCformer: Spatial-temporal dual-path cross-attention model for fMRI-based autism spectrum disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive neuroimaging technique widely utilized in the research of Autism Spectrum Disorder (ASD), providing preliminary insights into the potential biological mechanisms underlying ASD. Deep learning techniques have demonstrated significant potential in the analysis of rs-fMRI. However, accurately distinguishing between healthy control group and ASD has been a longstanding challenge. In this regard, this work proposes a model featuring a dual-path cross-attention framework for spatial and temporal patterns, named STDCformer, aiming to enhance the accuracy of ASD identification. STDCformer can preserve both temporal-specific patterns and spatial-specific patterns while explicitly interacting spatiotemporal information in depth. The embedding layer of the STDCformer embeds temporal and spatial patterns in dual paths. For the temporal path, we introduce a perturbation positional encoding to improve the issue of signal misalignment caused by individual differences. For the spatial path, we propose a correlation metric based on Gramian angular field similarity to establish a more specific whole-brain functional network. Subsequently, we interleave the query and key vectors of dual paths to interact spatial and temporal information. We further propose integrating the dual-path attention into a tensor that retains spatiotemporal dimensions and utilizing 2D convolution for feed-forward processing. Our attention layer allows the model to represent spatiotemporal correlations of signals at multiple scales to alleviate issues of information distortion and loss. Our STDCformer demonstrates competitive results compared to state-of-the-art methods on the ABIDE dataset. Additionally, we conducted interpretative analyses of the model to preliminarily discuss the potential physiological mechanisms of ASD. This work once again demonstrates the potential of deep learning technology in identifying ASD and developing neuroimaging biomarkers for ASD.

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.

Adversarial Learning Based Node-Edge Graph Attention Networks for Autism Spectrum Disorder Identification.

Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.

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.

Trailblazing ASD Behavioral Research: Leveraging Modified MLP with Cross-Weighted Attention Mechanism at the Forefront

Autism spectrum disorder (ASD) is an enduring and intricate condition that encompasses issues with behavior and communication. This disability has become common among several individuals globally. To ensure that all the autistic individuals get the correct support and care throughout their lifetime, it is significant that the autism signs are realized and the condition is spotted in the initial phase itself to avoid further complications. However, the process of ASD diagnosis is time-consuming, with expensive testing procedures. An effective screening method is needed for early treatment to improve the quality of the ASD patient’s life. Several conventional studies thrived on attaining ASD identification with machine learning and deep learning) but lacked in accuracy and computation. Therefore, the propounded system employs modified multi-layer perceptron (MLP) with cross-weighted attention mechanism. MLP is utilized for its capability in resolving intricate nonlinear complications, handling huge datasets, and enhancing the accuracy of the model. Though existing studies have utilized MLP for various identification processes, it still lacks identification speed, has overfitting issues, and requires more parameters. To overcome these issues, the proposed system employs cross-weighted attention mechanism, to enhance the identification process. As few researchers focused only on identifying and diagnosing the ASD adult, the proposed system uses autism screening in adult datasets and intends to improve the diagnosis of ASD adult patients. Attention ASD-modified MLP with cross-weighted algorithm is applied to classify and perform with various algorithms such as random forest, MLP, and Naïve Bayes. Furthermore, the performance is examined with certain metrics to calculate the efficacy of the proposed system.

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.

Deep learning performance analysis for facial expression based autism spectrum disorder identification

The subject matter of this paper revolves around the utilization of Deep Learning techniques for the identification of Autism Spectrum Disorder (ASD) through facial expression analysis. The goal is to assess the performance of various Deep Learning architectures in this context, aiming to support the evaluation of AI-based ASD identification technologies within medical imaging standards. The tasks undertaken include conducting a comprehensive performance analysis of different Deep Learning models, emphasizing the significance of data augmentation techniques, and evaluating the convergence ability of these models. Methods employed involve a simulation setup for evaluating Deep Learning architectures using facial expression images of children with ASD. The research utilizes secondary data from open-source sharing platforms comprising 2,840 optical images. The evaluation is conducted with consideration of data ratio settings and data augmentation procedures. Results indicate that data augmentation significantly improves the recall performance, with ResNet-101 architecture demonstrating superior accuracy, precision, and convergence ability compared to ResNet-50 and VGG-16. Finally, the conclusion drawn from this analysis highlights the efficacy of ResNet-101 with augmented data. It stands out as the most suitable model for ASD identification based on facial expressions, emphasizing its potential for early intervention and increased awareness. the scientific novelty of the results obtained lies in its contribution to advancing the state of the art in AI-driven ASD identification, adhering to medical standards, enhancing model performance through data augmentation, and facilitating early intervention strategies for improved patient outcomes.