Energy-Efficient EEG-Based Autism Spectrum Disorder Detection Using a Hyperbolic Attention Neural Network.

IntroductionThe early detection and diagnosis of autism spectrum disorder (ASD) remain critical challenges in developmental healthcare, with traditional diagnostic methods relying heavily on subjective clinical observations.MethodsIn this paper, we introduce an innovative multi-stream framework that seamlessly integrates three state-of-the-art convolutional neural networks, namely, EfficientNetV2B0, ResNet50V2, DenseNet121, and Multi-Stream models to analyze stereotypical movements, particularly hand-flapping behaviors automatically. Our architecture incorporates sophisticated spatial and temporal attention mechanisms enhanced by hierarchical feature fusion and adaptive temporal sampling techniques designed to extract characteristics of ASD related movements across multiple scales. The system includes a custom designed temporal attention module that effectively captures the rhythmic nature of hand-flapping behaviors. The spatial attention mechanisms method was used to enhance the proposed models by focusing on the movement characteristics of the patients in the video. The experimental validation was conducted using the Self-Stimulatory Behavior Dataset (SSBD), which includes 66 videos.ResultsThe Multi-Stream framework demonstrated exceptional performance, with 96.55% overall accuracy, 100% specificity, and 94.12% sensitivity in terms of hand-flapping detection and an impressive F1 score of 97%.DiscussionThis research can provide healthcare professionals with a reliable, automated tool for early ASD screening that offers objective, quantifiable metrics that complement traditional diagnostic methods.

Offspring who encounter biological and psychosocial adversities early in development are vulnerable to lasting physical, mental, emotional, and social deficits across the lifespan, especially autism spectrum disorders (ASD) and socioemotional problems. Numerous individual risk factors have been linked with these problems separately in children of various ages. However, few studies have analyzed the effects of prenatal, perinatal, and early life exposure to cumulative risk factors in predicting socioemotional problems co-occurring with ASD in toddlers. The current study aimed to determine if ASD was associated with internalizing, externalizing, and dysregulation problems in toddlers, and if a novel measure of cumulative risk explained observed deficits above and beyond an ASD diagnosis. 344 participants from an ongoing multisite longitudinal study evaluating optimal timing for repeat ASD screening were divided into 3 groups based on a diagnosis given at a clinical evaluation by trained research staff: ASD (n = 107), developmental delays (DD; n = 145), and typical development (TD; n = 92). The Cumulative Risk Scale was developed from a developmental history questionnaire. The presence of a risk factor (e.g., prenatal SSRI exposure, prematurity, low birth weight, maternal psychiatric diagnosis) was coded as 1 and the absence as 0, and the sum total created each participant's Cumulative Risk Score. After handling significant amounts of missing data with five iterations of multiple imputation, three multiple hierarchical regressions were conducted to determine if an ASD diagnosis was significantly associated with the Externalizing, Internalizing, and Dysregulation domain standard scores of the Infant-Toddler Social-Emotional Assessment (ITSEA). A second block of the hierarchical regression containing the novel Cumulative Risk Scale was added to determine if cumulative risk predicted these outcomes and increased the predictive ability of the model. The "segmented" package of R was then utilized to identify a linear or threshold relationship between cumulative risk and ITSEA outcomes. Results show that an ASD diagnosis was significantly associated with Internalizing problems ([beta] = .143, p = .035, 95% CI [.305, 8.430]), partially supporting the first hypothesis that an ASD diagnosis would be associated with internalizing, externalizing, and dysregulation problems. Further analyses show that both an ASD ([beta] = .278, p < .001, 95% CI [.088, .231]) and DD diagnosis ([beta] = .157, p = .010, 95% CI [.020, .149]) predict Depression/Withdrawal symptoms when controlling for child age. The addition of the Cumulative Risk Scale to the regression model improved prediction of Dysregulation problems only ([beta] = .103, p = .039, 95% CI [.027, 1.010], R2 change = .009, p = .039), partially supporting the second hypothesis that Cumulative Risk would significantly predict socioemotional problems. Further hierarchical multiple linear regressions showed cumulative risk significantly predicted Sleep Problems ([beta] = .101, p = .048) and Eating Problems ([beta] = .102, p = .045). Both hierarchical regressions showed a significant R2 change as well, but should also be interpreted with caution, as both increases were small (0.9% increases). An ASD diagnosis was significantly predictive of only the Negative Emotionality Subscale of the Dysregulation domain ([beta] = .151, p = .047). Results from the "segmented" package of R estimate a break point of 10.27 (p = .04171) for predicting Externalizing problems, but not Internalizing or Dysregulation problems. Toddlers ages 12-60 months with ASD are more likely to experience comorbid internalizing problems, which can have numerous clinical implications in the detection and prevention of internalizing problems early in life. Cumulative risk in early developmental periods overall does not explain socioemotional deficits in toddlers with ASD, DD, or with typical development. However, cumulative risk does predict dysregulation problems across children, regardless of diagnosis. A model depicting the relationship between cumulative risk in early developmental periods, dysregulation or non-disorder-specific socioemotional problems, and later psychopathology was proposed and should be investigated further in future research. A significant threshold of 10 risk factors was identified in predicting externalizing problems but may be possible in predicting internalizing and dysregulation problems as well. A more sensitive measure of cumulative biomedical risk early in life may also improve assessment of cumulative risk.

Autism spectrum disorder (ASD) and gender dysphoria (GD) frequently cooccur. However, existing research has primarily used smaller samples, limiting generalizability and the ability to assess further demographic variation. The purpose of this study was to (1) examine the prevalence of cooccurring ASD and GD diagnoses among US adolescents aged 9 to 18 and (2) identify demographic differences in the prevalence of cooccurring ASD and GD diagnoses. This secondary analysis used data from the PEDSnet learning health system network of 8 pediatric hospital institutions. Analyses included descriptive statistics and adjusted mixed logistic regression testing for associations between ASD and GD diagnoses and interactions between ASD diagnosis and demographic characteristics in the association with GD diagnosis. Among 919 898 patients, GD diagnosis was more prevalent among youth with an ASD diagnosis compared with youth without an ASD diagnosis (1.1% vs 0.6%), and adjusted regression revealed significantly greater odds of GD diagnosis among youth with an ASD diagnosis (adjusted odds ratio = 3.00, 95% confidence interval: 2.72-3.31). Cooccurring ASD/GD diagnoses were more prevalent among youth whose electronic medical record-reported sex was female and those using private insurance, and less prevalent among youth of color, particularly Black and Asian youth. Results indicate that youth whose electronic medical record-reported sex was female and those using private insurance are more likely, and youth of color are less likely, to have cooccurring ASD/GD diagnoses. This represents an important step toward building services and supports that reduce disparities in access to care and improve outcomes for youth with cooccurring ASD/GD and their families.

It is important to better understand how adults with autism are functioning in adulthood. Studies that have tracked individuals across the lifespan can help identify developmental factors influence differences in adult outcomes. The present study examines the independence, well-being, and functioning of 123 adults that have been closely followed since early childhood. Autism diagnosis and cognitive assessments were given frequently throughout childhood and during adulthood. We examined differences between adults who had received an autism diagnosis at some point with higher cognitive abilities (Ever ASD-High IQ) and lower cognitive abilities (Ever ASD-Low IQ), as well as adults who never received a diagnosis of autism in the course of the study (Never ASD). We found that autistic features specifically related to adaptive skills and friendships, and verbal intelligence related to work outcomes. In many ways, the Never ASD group had similar outcomes compared to the ASD groups. However, adults with ASD tended to have lower well-being and fewer positive emotions. Families played a major role in supporting adults with and without ASD at all intellectual levels. The findings suggest that realistic ways of increasing independence need to be developed by working with adults and their families, while acknowledging the contribution of individual differences in mental health, intelligence and autism symptoms across neurodevelopmental disorders.

Effectively serving students with autism spectrum disorders (ASDs) requires professionals to possess specialized knowledge, skills, and understanding. When students with ASDs are from culturally or linguistically diverse (CLD) families, the professionals assessing and providing services to the students need the additional dimension of how cultural and linguistic differences may affect identification, assessment, and treatment strategies.

Family socioeconomic status has been associated with autism spectrum disorder (ASD) diagnoses. Less is known regarding the role of neighborhood disadvantage in the United States, particularly when children have similar access to health insurance. To evaluate the association between neighborhood disadvantage and the diagnosis of ASD and potential effect modification by maternal and child demographic characteristics. This cohort study examined a retrospective birth cohort from Kaiser Permanente Southern California (KPSC), an integrated health care system. Children born in 2001 to 2014 at KPSC were followed up through KPSC membership records. Electronic medical records were used to obtain an ASD diagnosis up to December 31, 2019, or the last follow-up. Data were analyzed from February 2022 to September 2023. Socioeconomic disadvantage at the neighborhood level, an index derived from 7 US census tract characteristics using principal component analysis. Clinical ASD diagnosis based on electronic medical records. Associations between neighborhood disadvantage and ASD diagnosis were determined by hazard ratios (HRs) from Cox regression models adjusted for birth year, child sex, maternal age at delivery, parity, severe prepregnancy health conditions, maternal race and ethnicity, and maternal education. Effect modification by maternal race and ethnicity, maternal education, and child sex was assessed. Among 318 372 mothers with singleton deliveries during the study period, 6357 children had ASD diagnoses during follow-up; their median age at diagnosis was 3.53 years (IQR, 2.57-5.34 years). Neighborhood disadvantage was associated with a higher likelihood of ASD diagnosis (HR, 1.07; 95% CI, 1.02-1.11, per IQR = 2.70 increase). Children of mothers from minoritized racial and ethnic groups (African American or Black, Asian or Pacific Islander, Hispanic or Latinx groups) had increased likelihood of ASD diagnosis compared with children of White mothers. There was an interaction between maternal race and ethnicity and neighborhood disadvantage (difference in log-likelihood = 21.88; P < .001 for interaction under χ24); neighborhood disadvantage was only associated with ASD among children of White mothers (HR, 1.17; 95% CI, 1.09-1.26, per IQR = 2.00 increase). Maternal education and child sex did not significantly modify the neighborhood-ASD association. In this study, children residing in more disadvantaged neighborhoods at birth had higher likelihood of ASD diagnosis among a population with health insurance. Future research is warranted to investigate the mechanisms behind the neighborhood-related disparities in ASD diagnosis, alongside efforts to provide resources for early intervention and family support in communities with a higher likelihood of ASD.

Autism spectrum disorder (ASD) refers to a heterogeneous condition characterized by deficits in social communication and the presence of restricted, repetitive, and stereotypic behaviors, interests, or activities. While some neurodevelopmental disorders have a well-established correlation with ASD, people continue to believe that because individuals with Down syndrome are characteristically perceived as affectionate and engaging, a diagnosis of ASD is contradictory. However, some people with Down syndrome indeed do meet diagnostic criteria for ASD and this chapter examines the research literature regarding Down syndrome and ASD, presenting information regarding the establishment of a diagnosis of ASD in individuals with Down syndrome and research techniques to understand the dual diagnosis of ASD and Down syndrome. Behavioral manifestations of ASD in Down syndrome are presented and research methodologies which address possible underlying mechanisms in Down syndrome and ASD are surveyed. Finally, the need for specification of behavioral profiles for individuals with a dual diagnosis of Down syndrome and ASD, in order to design and implement appropriate therapeutic interventions, is highlighted. Once a person with Down syndrome is diagnosed with ASD, he or she should automatically receive a combined treatment approach incorporating direct instruction, natural environment teaching, and incidental teaching. The manifestation of ASD in individuals with Down syndrome can shed light on our understanding of how ASD and intellectual disability are associated and what impact these diagnoses have on individuals and their families. This knowledge can help shape public policy and our research agenda in the areas of ASD, intellectual impairment, and Down syndrome.

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

To determine the effect the COVID-19 pandemic had on autism spectrum disorder (ASD) diagnosis in the Military Health System (MHS). Repeated cross-sectional study utilized MHS Data Repository from JAN2018 to FEB2023. ASD encounters identified by ICD-10 diagnosis codes. Incident ASD encounters and overall visits were evaluated. Study included periods: Pre-COVID (PCo) (1/18 -2/20), COVID-19 Year (CoY) CoY1(3/20 -2/21), CoY2(3/21 -2/22) and CoY3(3/22 -2/23). Incident rates and overall visits were compared across time periods using Poisson regression, adjusting for sex, age group, region, and parent rank. Median age at first diagnosis across time periods were compared using generalized linear modeling. 2million dependents ages 1-17 years were eligible for care over the study, with 44,508 incident ASD diagnoses (Table1). ASD diagnosis incident rate decreased 10% in CoY1 vs. PCo (RR 0.90, 95% CI 0.87-0.93) and increased during CoY2 and CoY3 [RR2 1.21, 95% CI (1.18-1.24), RR3 1.50, 95% CI (1.46-1.54)]. CoY1-CoY3 vs. PCo all had statistically significant increased ASD visit rates (RR1 1.20, RR2 1.44, RR3 1.67). ASD diagnosis median age was 6 years (Table1). The incidence of ASD and related encounters decreased at the COVID-19 pandemic onset, highlighting the impact COVID-19 had on a delayed process within the MHS. The ASD incidence and encounters following the pandemic onset improved and continued to increase through CoY3. This uptrend suggests adaptation by providers during COVID-19 restrictions to use telehealth for developmental screening and ASD diagnosis.

This study explores whether providing information about a juvenile defendant's autism spectrum disorder (ASD) diagnosis, the type of offense (violent/nonviolent), and their race influences laypersons' credibility evaluations and legal decisions (verdicts/sentencing). We expected participants to render more not guilty verdicts and show leniency in sentencing when the defendant is White, has an ASD diagnosis, and is charged with a nonviolent offense. We anticipated credibility evaluations would mediate the relationships between ASD diagnosis and race, type of offense and sentencing views. Using a mock-juror paradigm, 466 participants read a vignette in which the juvenile defendant's diagnosis (ASD + information vs. no diagnosis), race (White vs. Black), and the charged offense (violent vs. nonviolent) were experimentally manipulated. Participants were highly unlikely to render guilty verdicts (p < .001, OR = 0.33) and harsh sentences (p < .001, ηp² = .11) when the defendant had an ASD diagnosis, even less so for violent offenses (p = .005, ηp² = .02). The defendant's likability (p < .001, ηp² = .04), honesty (p < .001, ηp² = .11), and believability (p < .001, ηp² = .09) were rated higher when the defendant had an ASD diagnosis, and these considerations led to significantly more lenient sentences compared to the no diagnosis condition. Participants were also twice as likely to find the White defendant guilty (p = .003, OR = 1.95) and reported being significantly more certain in their verdicts for the White defendant (p = .017, ηp² = .02). These results highlight the complex interplay between defendant characteristics and public perceptions of ASD in criminal legal proceedings. Findings highlight the need for judicial education, clearer guidelines on presenting ASD information in court, and further research on how race and neurodevelopmental diagnoses influence legal decisions. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

This study assessed the relationship of timeliness of autism spectrum disorder (ASD) diagnosis with current use of ASD-related services in a nationally representative sample of U.S. children. The Centers for Disease Control's (CDC's) Survey of Pathways to Diagnosis and Services was used to assess experiences of 722 children ages six to 11 with ASD. Bivariate and multivariate analyses were used to explore associations between age at ASD diagnosis and delay in ASD diagnosis and use of health services. Health services included current use of behavioral intervention (BI) therapy, school-based therapy, complementary and alternative medicine (CAM), and psychotropic medications. Mean age at ASD diagnosis was 4.4 years, and mean diagnostic delay was 2.2 years. In adjusted analysis, older age at diagnosis (≥4 versus <4) was associated with lower likelihood of current BI or school-based therapy use and higher likelihood of current psychotropic medication use. Analyses that treated age at diagnosis as a continuous variable found that likelihood of current psychotropic medication use increased with older age at diagnosis. A delay of two or more years between parents' first discussion of concerns with a provider and ASD diagnosis was associated with higher likelihood of current CAM use. Likelihood of current CAM use increased as delay in diagnosis became longer. Both older age at diagnosis and longer delay in diagnosis were associated with different health services utilization patterns among younger children with ASD. Prompt and early diagnosis may be associated with increased use of evidence-based therapies for ASD.

A hybrid graph network model for ASD diagnosis based on resting-state EEG signals

Several studies have suggested an association between vitamin D in childhood and autism spectrum disorder. No prospective studies have evaluated whether lower vitamin D levels precede ASD diagnoses - a necessary condition for causality. The objective of this study was to prospectively evaluate whether vitamin D serum levels in early childhood was associated with incident physician diagnosed ASD. A prospective cohort study was conducted using data from preschool-aged children in the TARGet Kids! practice-based research network in Toronto, Canada, from June 2008 to July 2015. 25-hydroxyvitamin D concentration was measured through blood samples and vitamin D supplementation from parent report. Autism spectrum disorder diagnosis was determined from medical records at follow-up visits. Covariates included age, sex, family history of autism spectrum disorder, maternal ethnicity, and neighborhood household income. Unadjusted and adjusted relative risks and 95% confidence intervals were estimated using Poisson regression with a robust error variance. In this study, 3852 children were included. Autism spectrum disorder diagnosis was identified in 41 children (incidence = 1.1%) over the observation period (average follow-up time = 2.5 years). An association between 25-hydroxyvitamin D concentration and autism spectrum disorder was not identified in the unadjusted (relative risk = 1.04, 95% confidence interval: 0.97, 1.11 per 10 nmol/L increase in 25-hydroxyvitamin D concentration) or adjusted models (adjusted relative risk = 1.06; 95% confidence interval: 0.95, 1.18). An association between vitamin D supplementation in early childhood and autism spectrum disorder was also not identified (adjusted relative risk = 0.86, 95% confidence interval: 0.46, 1.62). Vitamin D in early childhood may not be associated with incident physician diagnoses of autism spectrum disorder.

Psychometric properties of the French Version of the Social Responsiveness Scale in autism spectrum disorder with or without attention deficit hyperactivity disorder

While the prevalence of autism spectrum disorder (ASD) continues to increase and early diagnosis is emphasized, there is limited information on outcomes for children diagnosed with ASD in early childhood using contemporary diagnostic criteria. To determine the frequency with which children who are clinically diagnosed with ASD at 12 to 36 months of age continue to meet diagnostic criteria for ASD at 5 to 7 years of age and to evaluate whether baseline child-specific and demographic characteristics and receipt of interventions are associated with ASD persistence. In this natural history cohort study, children who received a clinical ASD diagnosis at 12 to 36 months of age underwent a research diagnostic assessment at 5 to 7 years of age. Research assessments occurred from August 14, 2018, to January 8, 2022. Children received community-based interventions, and parents provided details about interventions received. The main outcome was persistence of ASD diagnosis based on current functioning. An experienced research psychologist assigned an ASD diagnosis (present or absent) according to criteria from the Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) after the research assessment. The research assessment included administration of the Autism Diagnostic Observation Schedule-2, Autism Diagnostic Interview-Research, and a cognitive measure. Of the 213 participants diagnosed with ASD at initial clinical assessment (mean [SD] age, 24.6 [3.9] months; 177 boys [83.1%]), 79 (37.1%) did not continue to meet diagnostic criteria for ASD (nonpersistent ASD) at research assessment (mean [SD] age, 74.3 [7.1] months). All children with nonpersistent ASD had IQ of at least 70, while there was a bimodal distribution of IQ for those with persistent ASD (46 with IQ <70 and 88 with IQ ≥70). All children received some interventions, and 201 (94.4%) received ASD-specific intervention, mostly applied behavioral analysis. In a multilevel logistic regression model, the only variables associated with increased odds of being in the nonpersistent ASD group at 6 years of age were higher baseline adaptive skills (b coefficient = -0.287 [SE, 0.108]) and female sex (b = 0.239 [SE, 0.064]). The findings of this cohort study suggest that among toddlers diagnosed with ASD, baseline adaptive function and sex may be associated with persistence of ASD.