Early Autism Spectrum Disorder Research Articles

HLA-A, -B, -C and -DRB1 Association with Autism Spectrum Disorder Risk: A Sex-Related Analysis in Italian ASD Children and Their Siblings.

Autism Spectrum disorders (ASD) are diagnosed more often in males than in females, by a ratio of about 3:1; this is likely to be due to a difference in risk burden between the sexes and/or to "compensatory skills" in females, that may delay the diagnosis of ASD. Identifying specific risk factors for ASD in females may be important in facilitating early diagnosis. We investigated whether HLA- class I: -A, -B, -C and class II -DRB1 alleles, which have been suggested to play a role in the development of ASD, can be considered as sex-related risk/protective markers towards the ASD. We performed HLA allele genotyping in 178 Italian children with ASD, 94 healthy siblings, and their parents. HLA allele distribution was compared between children with ASD, sex-matched healthy siblings, and a cohort of healthy controls (HC) enrolled in the Italian bone marrow donor registry. Allele transmission from parents to children with ASD and their siblings was also assessed. Our findings suggest that HLA-A*02, B*38, and C*12 alleles are more frequently carried by females with ASD compared to both HC and healthy female siblings, indicating these alleles as potential risk factors for ASD in females. Conversely, the HLA-A*03 allele was more commonly transmitted to healthy female siblings, suggesting it might have a protective effect. Additionally, the HLA-B*44 allele was found to be more prevalent in boys with ASD, indicating it is a potential risk factor for male patients. This is the first Italian study of sex-related HLA association with ASD. If confirmed, these results could facilitate early ASD diagnosis in female patients, allowing earlier interventions, which are crucial in the management of neurodevelopmental disorders.

Early detection of autism spectrum disorder via deep-learning application of fMRI and machine learning for ASD children identifications

This study unveils an advanced convolutional-neural-network (CNN) algorithm that was meticulously engineered to examine resting-state functional magnetic resonance imaging (fMRI) for early ASD detection in pediatric cohorts. The CNN architecture amalgamates convolutional, pooling, batch-normalization, dropout, and fully connected layers, optimized for high-dimensional data interpretation. Rigorous preprocessing yielded 22,176 two-dimensional echo planar samples from 126 subjects (56 ASD, 70 controls) who were sourced from the Autism Brain Imaging Data Exchange (ABIDE I) repository. The model, trained on 17,740 samples across 50 epochs, demonstrated unparalleled diagnostic metrics – accuracy of 99.39%, recall of 98.80%, precision of 99.85%, and an F1 score of 99.32% – and thereby eclipsed extant computational methodologies. Feature map analyses substantiated the model’s hierarchical feature extraction capabilities. This research elucidates a deep learning framework for computer-assisted ASD screening via fMRI, with transformative implications for early diagnosis and intervention. And, this study addresses the critical need for early detection and intervention in autism spectrum disorder (ASD) using machine learning. Specific therapies are needed for ASD, a neurodevelopmental disease that affects social interaction and communication. To find trends in ASD, our research uses a variety of early childhood screening tests as training sets for machine learning algorithms. The methodology that has been suggested utilizes methods of machine learning to compute the ASD spectrum, considering its many expressions. By using multidisciplinary methods and sophisticated screening instruments, we want to create an accurate system for early ASD detection. Algorithmic transparency, data protection, and ethical considerations are essential. This study seeks to build precise instruments for early ASD detection by promoting collaboration between specialists in neurodevelopment, psychology, and machine learning. A robust instrument that enhances the knowledge of medical practitioners is machine learning. Results show how innovation may transform early interventions and help people on the autistic spectrum achieve enhanced results.

Association between exposure to antibiotics during pregnancy or early infancy and risk of autism spectrum disorder, intellectual disorder, language disorder, and epilepsy in children: population based cohort study

ObjectiveTo evaluate the association between antibiotic use during pregnancy or early infancy and the risk of neurodevelopmental disorders in children.DesignNationwide population based cohort study and sibling analysis.SettingKorea’s National Health Insurance...

Cross-Cultural Generalizability of the First Year Inventory for Early ASD Screening in China.

The First Year Inventory (FYI) is a parent report screening measure, aimed at identifying the risk of autism spectrum disorder (ASD) in 12-month-old infants. This study aimed to investigate the utility of FYI within the Chinese community and develop a short version, encompassing both a low-risk sample and a high-risk sample comprising infants with older siblings diagnosed with ASD. Parents of 53 high-risk (HR) infants and 519 low-risk (LR) infants, aged 11 to 13 months, were recruited. After comparing response distributions across Chinese and American samples, a new factorial structure was developed according to the factor analyses. The construct validity and internal consistency of the two FYI versions were examined. The implementation of FYI in the HR sample was also assessed. Noteworthy disparities in response distribution were observed between the Chinese and American samples. Both FYI 2.0 and the FYI short version demonstrated moderate construct validity and internal consistency, with the FYI short version exhibiting better predictive ability in the HR sample. Significant lower risk scores was observed in the HR sample compared to the LR sample. These findings substantiate the applicability and validity of the Chinese short version of FYI. Future research should include follow-up assessments with the Chinese sample to evaluate cutoff scores, considering the cutoff between sensitivity and specificity and the sample?s characteristics.

Exploring the Neurogenetic Landscape of Autism Spectrum Disorder: The Role of Brain-Derived Neurotrophic Factor (BDNF) Gene in the Complex Web of Neurodevelopment

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder with varied manifestations including altered metabolic profiles. Recent research highlights the potential role of Brain-Derived Neurotrophic Factor (BDNF), a hormone derived from adipose tissue, in the pathology of ASD. BDNF levels are reportedly correlated with the severity of autism symptoms, suggesting a link between metabolic dysfunction and the disorder. Objective: This study aims to deepen the understanding of BDNF levels in individuals with ASD and to explore the implications for diagnosis, treatment, and management of the disorder. It seeks to elucidate the relationship between low BDNF levels and increased autism severity, and to identify potential therapeutic interventions targeting BDNF dysregulation. Methods: EDTA blood samples (5ml each) from 140 participants (108 with ASD and 32 healthy controls) were collected across various hospitals in Karachi. Plasma serum levels of BDNF were analyzed following a six-month follow-up. A comprehensive statistical analysis was performed, focusing on the relationship between BDNF levels and autism severity, and evaluating diagnostic and therapeutic implications of BDNF dysregulation. Results: Analysis revealed that lower BDNF serum levels were consistently associated with higher autism severity. Specifically, 60-70% of participants with ASD scored below 8 on the Mini-Mental State Examination (MMSE), indicating significant cognitive impairment. The statistical significance of these findings was confirmed with p-values <0.05. Conclusion: The study confirms that low BDNF levels are significantly associated with greater severity of autism symptoms, underscoring the importance of metabolic factors in the pathogenesis of ASD. BDNF stands out as a potential biomarker for early ASD diagnosis and personalized treatment strategies. Future Prospects: Future research should aim to delineate the mechanistic relationship between BDNF dysregulation and ASD pathology. Longitudinal studies are needed to assess the long-term effects of BDNF modulation on ASD outcomes and to validate its effectiveness as both a diagnostic and prognostic marker.

Deep Canonical Correlation Fusion Algorithm Based on Denoising Autoencoder for ASD Diagnosis and Pathogenic Brain Region Identification.

Autism Spectrum Disorder (ASD) is defined as a neurodevelopmental condition distinguished by unconventional neural activities. Early intervention is key to managing the progress of ASD, and current research primarily focuses on the use of structural magnetic resonance imaging (sMRI) or resting-state functional magnetic resonance imaging (rs-fMRI) for diagnosis. Moreover, the use of autoencoders for disease classification has not been sufficiently explored. In this study, we introduce a new framework based on autoencoder, the Deep Canonical Correlation Fusion algorithm based on Denoising Autoencoder (DCCF-DAE), which proves to be effective in handling high-dimensional data. This framework involves efficient feature extraction from different types of data with an advanced autoencoder, followed by the fusion of these features through the DCCF model. Then we utilize the fused features for disease classification. DCCF integrates functional and structural data to help accurately diagnose ASD and identify critical Regions of Interest (ROIs) in disease mechanisms. We compare the proposed framework with other methods by the Autism Brain Imaging Data Exchange (ABIDE) database and the results demonstrate its outstanding performance in ASD diagnosis. The superiority of DCCF-DAE highlights its potential as a crucial tool for early ASD diagnosis and monitoring.

Facial Classification for Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a mental condition that affects people’s learning, communication, and expression in their daily lives. ASD usually makes it difficult to socialize and communicate with others, and also sometimes shows repetition of certain behaviors. ASD can be a cause of intellectual disability. ASD is a big challenge in neural development, specially in children. It is very important that it is identified at an early stage for timely guidance and intervention. This research identifies the application of deep learning and vision transformer (ViT) models for classification of facial images of autistic and non-autistic children. ViT models are powerful deep learning models used for image classification tasks. This model applies transformer architectures to analyze input image patches and connect the information to achieve global-level information. By employing these techniques, this study aims to contribute toward early ASD detection. ViT models are showing good results in identifying facial features associated with ASD, leading toward early diagnostics. Results show the ViT model’s capability in distinguishing the faces of autistic and non-autistic children.

Biomarkers of preschool children with autism spectrum disorder: quantitative analysis of whole-brain tissue component volumes, intelligence scores, ADOS-CSS, and ages of first-word production and walking onset.

Preschooling is a critical time for intervention in children with autism spectrum disorder (ASD); thus, we analyzed brain tissue component volumes (BTCVs) and clinical indicators in preschool children with ASD to identify new biomarkers for early screening. Eighty preschool children (3-6 years) with ASD were retrospectively included. The whole-brain myelin content (MyC), white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and non-WM/GM/MyC/CSF brain component volumes were obtained using synthetic magnetic resonance imaging (SyMRI). Clinical data, such as intelligence scores, autism diagnostic observation schedule-calibrated severity scores, age at first production of single words (AFSW), age at first production of phrases (AFP), and age at walking onset (AWO), were also collected. The correlation between the BTCV and clinical data was evaluated, and the effect of BTCVs on clinical data was assessed by a regression model. WM and GM volumes were positively correlated with intelligence scores (both P < 0.001), but WM and GM did not affect intelligence scores (P = 0.116, P = 0.290). AWO was positively correlated with AFSW and AFP (both P < 0.001). The multivariate linear regression analysis revealed that MyC, AFSW, AFP, and AWO were significantly different (P = 0.005, P < 0.001, P < 0.001). This study revealed positive correlations between WM and GM volumes and intelligence scores. Whole-brain MyC affected AFSW, AFP, and AWO in preschool children with ASD. Noninvasive quantification of BTCVs via SyMRI revealed a new visualizable and quantifiable biomarker (abnormal MyC) for early ASD screening in preschool children.

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization.

The early diagnosis of autism spectrum disorder (ASD) encounters challenges stemming from domain variations in facial image datasets. This study investigates the potential of active learning, particularly uncertainty-based sampling, for domain adaptation in early ASD diagnosis. Our focus is on improving model performance across diverse data sources. Utilizing the Kaggle ASD and YTUIA datasets, we meticulously analyze domain variations and assess transfer learning and active learning methodologies. Two state-of-the-art convolutional neural networks, Xception and ResNet50V2, pretrained on distinct datasets, demonstrate noteworthy accuracies of 95% on Kaggle ASD and 96% on YTUIA, respectively. However, combining datasets results in a modest decline in average accuracy, underscoring the necessity for effective domain adaptation techniques. We employ uncertainty-based active learning to address this, which significantly mitigates the accuracy drop. Xception and ResNet50V2 achieve 80% and 79% accuracy when pretrained on Kaggle ASD and applying active learning on YTUIA, respectively. Our findings highlight the efficacy of uncertainty-based active learning for domain adaptation, showcasing its potential to enhance accuracy and reduce annotation needs in early ASD diagnosis. This study contributes to the growing body of literature on ASD diagnosis methodologies. Future research should delve deeper into refining active learning strategies, ultimately paving the way for more robust and efficient ASD detection tools across diverse datasets.

Harnessing the Power of Mobile Phone Technology: Screening and Identifying Autism Spectrum Disorder With Smartphone Apps.

Integrating smartphone applications into screening and identifying autism spectrum disorder (ASD) represents a promising and innovative frontier within healthcare. This forward-looking paper examines the current landscape of ASD screening apps, shedding light on their potential advantages and addressing and navigating significant challenges. One of the most compelling aspects of these apps lies in their potential to democratize access to ASD screening, effectively breaking down geographical barriers. By using the widespread availability of smartphones, these apps make it possible for individuals, caregivers, and healthcare providers to engage in early ASD screening from virtually anywhere. This accessibility is especially crucial in underserved areas or regions with limited access to specialized healthcare services. Moreover, these apps offer a degree of objectivity that traditional screening methods may need help to match. By relying on data-driven algorithms and machine learning, they can provide a more impartial assessment of a child's behavior, minimizing the potential for subjective bias. This objectivity, combined with the ability to monitor and assess a child's development over time, empowers caregivers with valuable insights into their child's progress. However, as with any technological advancement in healthcare, integrating smartphone apps for ASD screening is not without its share of ethical and privacy considerations. Ensuring informed consent is obtained, especially when collecting data from children, is complex and critical. Striking the right balance between collecting necessary data and protecting an individual's privacy requires careful thought and transparent communication. Additionally, the "digital divide" represents a challenge that needs to be acknowledged and addressed. Not all individuals and families have equal access to smartphones or the technological literacy required to use these apps effectively. This disparity in access must be considered when developing and implementing app-based screening solutions to prevent exacerbating existing healthcare inequalities. Nevertheless, the future of ASD screening apps holds significant promise. Advancements in technology, including integrating advanced sensors, wearables, augmented reality, and machine learning, can further enhance the accuracy and depth of screening. Interdisciplinary collaboration between researchers, developers, clinicians, and educators is crucial to ensure that these apps are effective, culturally sensitive, and user-friendly. Furthermore, integrating these apps into broader healthcare systems, including electronic health records and telehealth platforms, can streamline the screening process and enable a more seamless transition from screening to diagnosis and intervention.

Age at autism spectrum disorder diagnosis and its association with child and family characteristics in a tertiary care hospital in Malaysia.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder. Despite the absence of a cure, early diagnosis and intensive early intervention can improve the outcomes. However, little is known about the median age at ASD diagnosis in Malaysia or the child/family characteristics associated with early diagnosis. Therefore, this study aimed to determine the median age at ASD diagnosis among Malaysian children presenting to the country's largest public tertiary neurodevelopmental center and to investigate the possible demographic, child, and family characteristics associated with an early age at diagnosis. Data were collected between February 2017 and February 2019 from a database maintained by the child development unit of the country's largest publicly funded tertiary hospital, containing data from an ethnically diverse population. Among Malaysian children attending the clinic, the median age at ASD diagnosis was 48 months. Early autism diagnosis (<36 months of age) was associated with increased severity of social communication and interaction impairments, coexisting intellectual impairment, children from high socioeconomic status families, and children who receive joint care from their families and a maid or babysitter. The study findings highlight the socioeconomic inequalities in the country, a lack of parental awareness of early ASD signs, and the presence of cultural influences on the age at diagnosis of ASD.

White matter development and language abilities during infancy in autism spectrum disorder.

White matter (WM) fiber tract differences are present in autism spectrum disorder (ASD) and could be important markers of behavior. One of the earliest phenotypic differences in ASD are language atypicalities. Although language has been linked to WM in typical development, no work has evaluated this association in early ASD. Participants came from the Infant Brain Imaging Study and included 321 infant siblings of children with ASD at high likelihood (HL) for developing ASD; 70 HL infants were later diagnosed with ASD (HL-ASD), and 251 HL infants were not diagnosed with ASD (HL-Neg). A control sample of 140 low likelihood infants not diagnosed with ASD (LL-Neg) were also included. Infants contributed expressive language, receptive language, and diffusion tensor imaging data at 6-, 12-, and 24 months. Mixed effects regression models were conducted to evaluate associations between WM and language trajectories. Trajectories of microstructural changes in the right arcuate fasciculus were associated with expressive language development. HL-ASD infants demonstrated a different developmental pattern compared to the HL-Neg and LL-Neg groups, wherein the HL-ASD group exhibited a positive association between WM fractional anisotropy and language whereas HL-Neg and LL-Neg groups showed weak or no association. No other fiber tracts demonstrated significant associations with language. In conclusion, results indicated arcuate fasciculus WM is linked to language in early toddlerhood for autistic toddlers, with the strongest associations emerging around 24 months. To our knowledge, this is the first study to evaluate associations between language and WM development during the pre-symptomatic period in ASD.

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.

Analysis of Brain Imaging Data for the Detection of Early Age Autism Spectrum Disorder Using Transfer Learning Approaches for Internet of Things

Analysis of Brain Imaging Data for the Detection of Early Age Autism Spectrum Disorder Using Transfer Learning Approaches for Internet of Things

Validation of preparedness and willingness on early detection of autism spectrum disorder among healthcare providers in Jordan

In recent years, there have been significant advancements in the field of early detection and intervention for children with developmental and behavioural disorders, with significant in the context of Autism Spectrum Disorder (ASD). It highlights the advantages of early detection, such as reduced long-term costs and positive effects on a child's development. However, it also acknowledges the prevalent barriers to early ASD diagnosis and intervention. This study aims to develop and validate questionnaires on Preparedness and Willingness in early ASD detection among Al-Mafraq City, Jordan, healthcare providers. The research in the Al-Mafraq region of Jordan employed a cross-sectional research design. The study first involved the development of a questionnaire, which underwent rigorous content validation by a panel of experts well-versed in ASD. Face validity was assessed utilizing the Face Validity Index (FVI). A random sample of 130 healthcare providers from one hospital answered the draft questionnaires online for the EFA analysis recommended. It resulted in satisfactory items' factor loadings (r&gt;0.60) and internal reliability (Cronbach's alpha &gt;0.8). Followed by CFA from a random sample of another 202 healthcare providers from another hospital and healthcare centres in Al-Mafraq showed that the instrument effectively met the validation criteria, demonstrating its reliability and validity in assessing healthcare providers' Preparedness and Willingness for early ASD detection. Notably, the participants in the study exhibit differing degrees of Preparedness and Willingness. In conclusion, the study underscores the critical standing of developing a comprehensive instrument to evaluate the limitations associated with early ASD detection among healthcare providers.

Key personal factors and moderation effect of belief on shaping the willingness for early ASD detection in Jordan: A SEM Analysis

Background: Autism Spectrum Disorder (ASD) prevalence increases healthcare utilisation, underscoring healthcare providers' vital role in early detection. This growing prominence underscores the pivotal roles of healthcare providers in the early detection of ASD. Understanding the influence of their factors, Knowledge, Awareness, Experience, Preparedness, and Beliefs impact providers' Willingness for early ASD detection. This study explores these factors comprehensively, contributing to a nuanced understanding and assessing the effect of Beliefs on healthcare providers' Willingness for early ASD detection, examining their influence on Awareness, Knowledge, Experience, and perceived Preparedness. Methodology: In the Al-Mafraq region of Jordan, this study surveyed 202 participants from various healthcare facilities using structural equation modelling (SEM) to analyse the connection between Beliefs and healthcare providers' Awareness, Knowledge, Experience, perceived Preparedness, and Willingness for early ASD detection. Result: Belief moderated the path from Preparedness towards Willingness. This means that the higher the value of Belief, the greater the effect of healthcare providers' Preparedness for early ASD detection. Conclusion: The study uncovers significant associations between healthcare providers' Knowledge, Experience, and perceived Preparedness and their Willingness for early ASD detection. Belief emerges as a pivotal moderator, emphasising its influential role in shaping the connection between Preparedness and Willingness.

Neurobiology of cognitive abilities in early childhood autism.

This perspective considers complexities in the relationship between impaired cognitive abilities and autism from a maturational, developmental perspective, and aims to serve as a helpful guide for the complex and growing investigation of cognitive abilities and Autism Spectrum Disorder (ASD). Low Intelligence Quotient (IQ) and ASD are frequently co-occurring. About 37% of 8-year old children and 48% of 4-year old children diagnosed with ASD also have Intellectual Disability, with IQ below 70. And, low IQ in early infancy, including below 1year of age, carries a 40% greater chance of receiving ASD diagnosis in early childhood. We consider the evidence that may explain this co-occurrence, including the possibility that high IQ may "rescue" the social communication issues, as well as the possible role of critical periods during growth and development. We consider how early low IQ may subsume a part of a subgroup of individuals with ASD, in particular, those diagnosed with autism in very early childhood, and we provide neurobiological evidence in support of this subtype. Moreover, we distinguish the concept of early low IQ from the delay in speech onset in preschool and school-aged children, based on (i) age and (ii) impairments in both verbal and non-verbal domains. The etiology of these early-diagnosed, early low IQ ASD cases is different from later-diagnosed, average or higher-IQ cases, and from children with speech delay onset. Given recent interest in formulating new subtypes of autism, rather than continuing to conceive of ASD as a spectrum, as well as new subtypes that vary in the degree of severity along the spectrum, we identify gaps in knowledge and directions for future work in this complex and growing area.

Assessing cortical features in early stage ASD children.

Autism Spectrum Disorder (ASD) is defined as a neurodevelopmental disorder largely investigated in the neurologic field. Recently, neuroimaging studies have been conducted in order to investigate cerebral morphologic alterations in ASD patients, demonstrating an atypical brain development before the clinical manifestations of the disorder. Cortical Thickness (CT) and Local Gyrification Index (LGI) distribution for ASD children were investigated in this study, with the aim to evaluate possible relationship between brain measures and individual characteristics (i.e., IQ and verbal ability). 3D T1-w sequences from 129 ASD and 58 age-matched Healthy Controls (HC) were acquired and processed in order to assess CT and LGI for each subject. Intergroup differences between ASD and HC were investigated, including analyses of 2 ASD subgroups, split according to patient verbal ability and IQ. When compared to HC, ASD showed increased CT and LGI within several brain areas, both as an overall group and as verbal ability an IQ subgroups. Moreover, when comparing language characteristics of the ASD subjects, those patients with verbal ability exhibit significant CT and LGI increase was found within the occipital lobe of right hemisphere. No significant results occurred when comparing ASD patients according to their IQ value. These results support the hypothesis of abnormal brain maturation in ASD since early childhood with differences among clinical subgroups suggesting different anatomical substrates underlying an aberrant connectivity.

Urine manganese, cadmium, lead, arsenic, and selenium among autism spectrum disorder children in Kuala Lumpur.

The development of autism spectrum disorder (ASD) may stem from exposure to environmental pollutants such as heavy metals. The primary objective of this study is to determine the role of heavy metals of concern such as manganese (Mn), cadmium (Cd), lead (Pb), arsenic (As), and essential trace element selenium (Se) among ASD children in Kuala Lumpur, Malaysia. A total of 155 preschoolers in Kuala Lumpur between the ages 3 to 6 participated in an unmatched case-control study, comprising ASD children (n=81) recruited from an early intervention program for autism, and 74 children without autism who were recruited from public preschools. Urine samples were collected at home, delivered to the study site, and transported to the environmental lab within 24 hours. Inductively coupled plasma mass spectrometry (ICP-MS) was applied to measure the concentration of heavy metals in the samples. Data were analysed using bivariate statistical tests (Chi-square and T-test) and logistic regression models. This study demonstrated that Cd, Pb, and As urine levels were significantly greater in children without autism relative to those affected with ASD (p<0.05). No significant difference was in the levels of Se (p=0.659) and Mn (p=0.875) between children with ASD and the control group. The majority of children in both groups have urine As, Pb, and Cd values lower than 15.1 µg/dL, 1.0 µg/dL, and 1.0 µg/dL, respectively which are the minimal risk values for noncarcinogenic detrimental human health effect due to the heavy metal's exposure . Factors associated with having an ASD child included being a firstborn, male, and higher parental education levels (adjusted odds ratios (aOR) > 1, p<0.05). Preschoolers in this study demonstrated low levels of heavy metals in their urine samples, which was relatively lower in ASD children compared to the healthy matched controls. These findings may arise from the diminished capacity to excrete heavy metals, especially among ASD children, thereby causing further accumulation of heavy metals in the body. These findings, including the factors associated with having an ASD child, may be considered by healthcare professionals involved in child development care, for early ASD detection. Further assessment of heavy metals among ASD children in the country and interventional studies to develop effective methods of addressing exposure to heavy metals will be beneficial for future reference.

Utilizing deep learning models in an intelligent eye-tracking system for autism spectrum disorder diagnosis.

Timely and unbiased evaluation of Autism Spectrum Disorder (ASD) is essential for providing lasting benefits to affected individuals. However, conventional ASD assessment heavily relies on subjective criteria, lacking objectivity. Recent advancements propose the integration of modern processes, including artificial intelligence-based eye-tracking technology, for early ASD assessment. Nonetheless, the current diagnostic procedures for ASD often involve specialized investigations that are both time-consuming and costly, heavily reliant on the proficiency of specialists and employed techniques. To address the pressing need for prompt, efficient, and precise ASD diagnosis, an exploration of sophisticated intelligent techniques capable of automating disease categorization was presented. This study has utilized a freely accessible dataset comprising 547 eye-tracking systems that can be used to scan pathways obtained from 328 characteristically emerging children and 219 children with autism. To counter overfitting, state-of-the-art image resampling approaches to expand the training dataset were employed. Leveraging deep learning algorithms, specifically MobileNet, VGG19, DenseNet169, and a hybrid of MobileNet-VGG19, automated classifiers, that hold promise for enhancing diagnostic precision and effectiveness, was developed. The MobileNet model demonstrated superior performance compared to existing systems, achieving an impressive accuracy of 100%, while the VGG19 model achieved 92% accuracy. These findings demonstrate the potential of eye-tracking data to aid physicians in efficiently and accurately screening for autism. Moreover, the reported results suggest that deep learning approaches outperform existing event detection algorithms, achieving a similar level of accuracy as manual coding. Users and healthcare professionals can utilize these classifiers to enhance the accuracy rate of ASD diagnosis. The development of these automated classifiers based on deep learning algorithms holds promise for enhancing the diagnostic precision and effectiveness of ASD assessment, addressing the pressing need for prompt, efficient, and precise ASD diagnosis.