Identification Of Autism Spectrum Disorder Research Articles

Machine Learning Techniques for Detecting and Identifying Significant Autism Spectrum Disorder Speech Characteristics

Autism spectrum disorder (ASD) is a group of neuro-developmental disorders that has a lifelong effect on social and communicative behaviors, and restricted and repetitive behaviors. Even though there is no cure, initial stage identification of ASD can help improve the patient’s life expectancy Conventional diagnosis of ASD is commonly performed through observation of behaviors and interview of a patient with medical experts by following standard procedures. In any case, these finding strategies are time-consuming. By integrating Machine Learning with neuroscience, a conclusion strategy might potentially be laid out to identify ASD subjects from typical development (TD) subjects. In this study, our main aim is to detect significant features that are associated with speech of ASD subjects by apply machine learning models on a cross-linguistic corpus (English and Danish. These mechanisms can help in earlier diagnosis The speech features from recordings are analyzed by various machine learning algorithms (like “Support Vector Machines (SVM), Random Forest Classifier (RFC), Logistic Regression (LR), XGBoost”) to build a classification model that classifies ASD and TD. In this process we achieved 97% accuracy with XGBoost in classifying ASD and TD. The model recognizes the important features in the order quasi-open-quotient (QoQ), jitter, pitch, duration, Dominant frequency (F2, F1, and F3), creak probability. Additionally, the findings support the use of voice and speech analysis as cutting-edge diagnostic tools for autism in young preverbal children.

Wavelet Scattering Transform and Deep Learning Networks based Autism Spectrum Disorder Identification using EEG Signals

Autism Spectrum Disorder (ASD), a neurological abnormality that influences how an individual perceives and interacts with others, which leads to issues with social interaction and communication. In accordance with the Centers for Disease Control and Prevention, 1 in every 44 children in USA is affected by ASD. The identification of ASD is based on behavioural characteristics and it generally takes a long time from the initial observation of behavioural signs to the final diagnosis, due to the complexity and diversity of ASD symptoms. The application of Electroencephalography (EEG) signals, recorded from 14 ASD affected children and 14 healthy controls, as a potential biomarker for ASD categorisation, was analysed in this study. After pre-processing, second-order Wavelet Scattering Transform (WST) coefficients were extracted from the EEG signals and Deep Learning (DL) based ASD detection networks (WST-ASDNets) were used for categorisation of ASD and control subjects. Long Short Term Memory Network (LSTM) based WST-ASDNet and Convolution Neural Network (CNN) based WST-ASDNet achieved accuracy of 94% and 92% respectively, in ASD subject identification. The results demonstrate that the proposed WST-ASDNets can efficiently classify ASD and the usage of WST coefficients extracted from EEG signals can be used as potential biomarker for ASD categorisation.

Primary Care Pediatricians' Perspectives on Autism Care.

We aimed to explore pediatric primary care provider (PCP) experiences and needs around identification and management of autism spectrum disorder (ASD) in toddlers for the purpose of planning improved supports and services for ASD in the medical home. We recruited 28 PCPs to participate in semistructured interviews via Zoom. Probe questions elicited opinions about current screening and referral procedures, experiences obtaining services for patients, effective communication with parents, physician emotional experience when introducing ASD concerns, practice-based sources of disparities, and larger needs for ASD management in the primary care setting. Interview transcripts were analyzed qualitatively by a multispecialty research team for recurrent themes using grounded theory analysis. Participants were 89% women, ranging in clinical experience from <1 year to >27 years, representing 8 diverse pediatric primary care clinic sites at a Midwest academic medical center. Dominant themes relating to PCPs' cognitive, emotional, and environmental experience of caring for patients with ASD were identified, which reflected the trajectory of ASD identification (the parent lens; the "A" word), referral (the autism labyrinth; provider disempowerment; parent activation as a source of inequities), and long-term management (the "black box"; provider emotional investment). Existing literature and results from this study suggest a need for targeted improvements in primary care to: (1) increase PCP capacity and confidence in communicating concerns of ASD with families; (2) refer for timely diagnostic evaluations in trusted and easy-to-navigate care systems; and (3) increase family activation and capacity to follow up on ASD evaluation and treatment services.

Early Indicators of Autism in Infants: Development of the IMES Screening Tool.

We developed the Infant, Motor, and Engagement Scale (IMES) to address the public health goal of early identification of autism spectrum disorder (ASD). The IMES is a screening tool that assesses quality of infants' interaction with people and objects during early play. We aimed to examine the IMES' preliminary psychometric properties and its value in discriminating between infants later diagnosed with ASD and typically developing infants. We used the IMES to score retrospective home videos of 15 male infants, 7 who were later diagnosed with autism. We examined interrater reliability using Cohen's Kappa, internal consistency with Cronbach's alpha and content validity through expert review. Preliminary data support validity and reliability of the IMES for early identification for infants at 6 to 9 months. With further research, the IMES has the potential to identify at risk infants at a young age that may have long-term impact on child and family outcomes.

Why not try to predict autism spectrum disorder with crucial biomarkers in cuproptosis signaling pathway?

The exact pathogenesis of autism spectrum disorder (ASD) is still unclear, yet some potential mechanisms may not have been evaluated before. Cuproptosis is a novel form of regulated cell death reported this year, and no study has reported the relationship between ASD and cuproptosis. This study aimed to identify ASD in suspected patients early using machine learning models based on biomarkers of the cuproptosis pathway. We collected gene expression profiles from brain samples from ASD model mice and blood samples from humans with ASD, selected crucial genes in the cuproptosis signaling pathway, and then analysed these genes with different machine learning models. The accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curves of the machine learning models were estimated in the training, internal validation, and external validation cohorts. Differences between models were determined with Bonferroni's test. The results of screening with the Boruta algorithm showed that FDX1, DLAT, LIAS, and ATP7B were crucial genes in the cuproptosis signaling pathway for ASD. All selected genes and corresponding proteins were also expressed in the human brain. The k-nearest neighbor, support vector machine and random forest models could identify approximately 72% of patients with ASD. The artificial neural network (ANN) model was the most suitable for the present data because the accuracy, sensitivity, and specificity were 0.90, 1.00, and 0.80, respectively, in the external validation cohort. Thus, we first report the prediction of ASD in suspected patients with machine learning methods based on crucial biomarkers in the cuproptosis signaling pathway, and these findings may contribute to investigations of the potential pathogenesis and early identification of ASD.

1H-NMR-Based Metabolomics in Autism Spectrum Disorder and Pediatric Acute-Onset Neuropsychiatric Syndrome

We recently described a unique plasma metabolite profile in subjects with pediatric acute-onset neuropsychiatric syndrome (PANS), suggesting pathogenic models involving specific patterns of neurotransmission, neuroinflammation, and oxidative stress. Here, we extend the analysis to a group of patients with autism spectrum disorder (ASD), as a consensus has recently emerged around its immune-mediated pathophysiology with a widespread involvement of brain networks. This observational case-control study enrolled patients referred for PANS and ASD from June 2019 to May 2020, as well as neurotypical age and gender-matched control subjects. Thirty-four PANS outpatients, fifteen ASD outpatients, and twenty-five neurotypical subjects underwent physical and neuropsychiatric evaluations, alongside serum metabolomic analysis with 1H-NMR. In supervised models, the metabolomic profile of ASD was significantly different from controls (p = 0.0001), with skewed concentrations of asparagine, aspartate, betaine, glycine, lactate, glucose, and pyruvate. Metabolomic separation was also observed between PANS and ASD subjects (p = 0.02), with differences in the concentrations of arginine, aspartate, betaine, choline, creatine phosphate, glycine, pyruvate, and tryptophan. We confirmed a unique serum metabolomic profile of PANS compared with both ASD and neurotypical subjects, distinguishing PANS as a pathophysiological entity per se. Tryptophan and glycine appear as neuroinflammatory fingerprints of PANS and ASD, respectively. In particular, a reduction in glycine would primarily affect NMDA-R excitatory tone, overall impairing downstream glutamatergic, dopaminergic, and GABAergic transmissions. Nonetheless, we found metabolomic similarities between PANS and ASD that suggest a putative role of N-methyl-D-aspartate receptor (NMDA-R) dysfunction in both disorders. Metabolomics-based approaches could contribute to the identification of novel ASD and PANS biomarkers.

Identifying autism spectrum disorder in resting-state fNIRS signals based on multiscale entropy and a two-branch deep learning network

BackgroundThe demand for early and precise identification of autism spectrum disorder (ASD) presented a challenge to the prediction of ASD with a non-invasive neuroimaging method. New methodA deep learning model was proposed to identify children with ASD using the resting-state functional near-infrared spectroscopy (fNIRS) signals. In this model, the input was the pattern of brain complexity represented by multiscale entropy of fNIRS time-series signals, with the purpose to solve the problem of deep learning analysis when the raw signals were limited by length and the number of subjects. The model consisted of a two-branch deep learning network, where one branch was a convolution neural network and the other was a long short-term memory neural network based on an attention mechanism. ResultsOur model could achieve an identification accuracy of 94%. Further analysis used the SHapley Additive exPlanations (SHAP) method to balance the accuracy and the number of optical channels, thus reducing the complexity of fNIRS experiment. Comparison with previously used method(s)in identification accuracy, our model was about 14% higher than previously used deep learning models with the same input and 4% higher than the same model but directly using fNIRS signals as input. We could obtain a discriminative accuracy of 90% with nearly half of the measurement channels by the SHAP method. ConclusionsUsing the pattern of brain complexity as input was effective in the deep learning model when the fNIRS signals were insufficient. With the SHAP method, it was possible to reduce the number of optical channels, while maintaining high accuracy in ASD identification.

9 Congenital Heart Disease and Autism Spectrum Disorders: Is There a Link?

Abstract Background Congenital heart disease (CHD) has been linked to an increased incidence of intellectual disability and neurodevelopmental impairments in young patients. The relationship between CHD and autism spectrum disorders (ASD) is not well investigated. Objectives We performed a systematic review and meta-analysis of the medical literature to assess the evidence linking CHD to incidence of ASD. Design/Methods A systematic review of studies on CHD and ASD in PubMed, Cochrane and ISI from 1965 to May 2021 was conducted. Only retrospective or prospective cohort, case-control and cross-sectional human studies in the English language were included. Quantitative estimates of association between CHD and ASD were extracted from eligible studies for the meta-analysis. Pooled estimates were obtained using a random effect models fit by a generalised linear mixed model. Quantitative results not included in the meta-analysis were summarized using descriptive statistics. Results We screened 2,709 articles and 24 articles were included in this review. Among the 24 studies, there was a total of 348,771 subjects (12,114 CHD, 9,829 ASD and 326,828 controls). Patient age (range of 0 to 26 years) was reported in all studies. The proportion of males in CHD, ASD and controls were 50%, 80%, and 55%. CHD diagnosis ranged from non-specific (9/16), single ventricle lesion (2/16), dextro-transposition of the great arteries (2/16), and tetralogy of Fallot (1/16). Overall, seven articles reported a 4.66 times increase in the percentage of ASD cases in patients with CHD compared to the percentage of ASD cases in the general population: (5.87% vs 1.14% of ASD cases in CHD vs the general population). Seven of 24 studies were eligible for the meta-analysis, which included information on a total of 250,611 subjects (3,984 CHD, 9,829 ASD, and 236,798 controls). The summary estimate indicated that CHD patients are associated with almost double the odds of being diagnosed with autism compared with non-CHD patients: (OR 1.99, 95% CI 1.77-2.24, p&amp;lt;0.01). Early developmental delay, perinatal factors, genetics and neurological development were potential risk factors and etiologies for the onset of ASD in CHD patients. Suggestions for improvement of future clinical care include early identification and treatment of ASD among the CHD population. Limitations of this study include few articles explicitly exploring the link between CHD and ASD and lack of standardized ASD endpoints. Conclusion This review outlines that CHD patients are at an increased risk of presenting with a diagnosis or symptoms suggestive of ASD.

Screening of autism spectrum disorder based on task-free fMRI using tensor decomposition approach

In recent decades, autism spectrum disorder (ASD) has displayed an incremental prevalence rate. Due to the unavailability of a definite cure, the early diagnosis of the disorder is of high significance. There is evidence suggesting the discriminable differences between the resting state networks of people who suffer from the disorder and healthy individuals. This distinguishability allows for the utilization of fMRI imaging to perform as a good instrument for the identification of autism spectrum disorder. In this paper, a tensor decomposition method for the diagnosis of autism from fMRI images is presented. The selected dataset for testing the performance of the proposed algorithm is ABIDE1. All sites of the ABIDE1 are used for training the algorithm which is a challenging problem in fMRI data analysis. Our proposed method successfully achieves the classification performance of about 60% for all site analyses.

The impact of educational rewards on the diagnosis of autism spectrum disorder

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects social interactions and communication. The prevalence of ASD has risen dramatically in recent years, but the underlying factors leading to this rise are not clear. In this paper, we test whether changes in state-level educational policy that impact school-level resources are associated with the rise in ASD diagnostic prevalence. Early identification of ASD can improve an array of outcomes for children, and school systems play an important role with identification of the condition. It is plausible that children attending schools with better resources from state governments are more likely to receive an ASD diagnosis and presumably appropriate services. We focus on one educational policy in particular, state-level rewards, which consist of a monetary transfer from state governments to school districts. To test the impact of educational rewards on ASD diagnosis, we rely on policy variation across states and time and estimate both two-way fixed effects (TWFE) models alongside recently advanced methods in the difference-in-differences (DiD) literature. Under a baseline TWFE specification we estimate that rewards policies are associated with a 18.46% increase in ASD diagnosis. Further, using DiD methods that account for bias in settings of differential policy timing, we find that the magnitude of the effect increases to 24.8%. We believe these findings to be suggestive evidence that educational rewards policies improved the likelihood of detection and diagnosis of ASD.

Factors affecting knowledge of autism spectrum disorder among pediatric residents in eastern China: a cross-sectional study

BackgroundThere is a global increase in the prevalence of autism spectrum disorder (ASD). Early identification of ASD in children and intervention are key aspects in the management of ASD. However, early identification is partly dependent on knowledge on ASD among pediatricians. This study analyzed the extent of ASD knowledge and its underlying factors among pediatric residents in eastern China, to provide a reference for medical education reforms.MethodsThe study employed the Knowledge about Childhood Autism among Health Workers questionnaire. A total of 138 pediatric residents participated in the survey. Descriptive statistics were used to describe demographic characteristics and the four domains of the questionnaire. Univariate analysis was employed to assess impacts of the demographic characteristics on the questionnaire scores. On the other hand, multivariate regression analysis was used to analyze the correlation between the participants’ demographic characteristics and the questionnaire scores.ResultsThe average ASD cognitive score of 138 respondents was 13.38 ± 4.48. The ASD cognitive scores in female pediatric residents were higher compared to that in males (p < 0.05). Residents who had obtained professional doctor qualification certificate were more than those without professional doctor qualification certificate (p < 0.05). The ASD knowledge in the group which did not have rotation in both departments was lower than in the group which had rotation in both departments (p < 0.05) as well as the group that had rotation in developmental and behavioral pediatrics department only (p < 0.05). Our multivariate linear regression model demonstrated significant statistical differences (p < 0.05), and showed that gender and systematic exposure to ASD knowledge had significant effects on cognitive scores (p < 0.05).ConclusionMost participants had relatively low levels of awareness and knowledge about ASD, especially on ASD comorbidities and age of onset. Women, systematic learning of ASD knowledge in medical school, successful passing of the physician examination, and rotation in the developmental and behavioral pediatrics (DBP) department significantly influence the levels of ASD awareness and knowledge. It is, therefore, important to strengthen ASD education in medical students at the university level and make rotation in the DBP department a requisite for pediatric trainees.

A new model for recognition, referral, and follow‐up of autism spectrum disorder: A nationwide program

AbstractEarly diagnosis of autism certainly stands as one of the most important determinants to ensure a better prognosis of the disorder, it is common that the screening programs to ensure this, end up not being implemented in health systems of many countries. This may stem from the disadvantages of classically suggested scale‐based screening (SBS) programs. This study presents a nationwide recognition and referral model for early diagnosis of autism spectrum disorders (ASD), in order to meet the obvious need for new methods. The model consists of interactive video‐based training (IVBAT) of health care workers (HCW), a system where family physicians (FPs) record five probable indicators of autism in their family medicine information system; and is therefore, a practical referral system in which the FP may refer a child with any suggestive finding to a child psychiatrist and may well continue to monitor recently diagnosed cases. The autism teams consist of trained child psychiatrists and coordinators, who delivered trainings to 29,612 FPs and 23,511 nurses countrywide. Of 98.8% FPs were trained throughout the country. Total of 1,863,096 children were reported to have a brief examination of autism signs in Family Medicine Units by trained FPs and nurses. A total of 55,314 (2.96%) these children were deemed at risk for ASD and were referred to child psychiatrists. In the evaluation of 55,314 children by child psychiatrists, 10,087 cases were diagnosed with developmental disorders, while 3226 of children at risk were diagnosed with autism. The results of this study, which reached to the largest sample to date, suggest that some other alternative methods, in addition to SBS should also be tested in order to screen ASD.Lay SummaryIn this study, a nationwide recognition and referral model for early identification of autism spectrum disorders (ASD) is presented. Scale‐based screening (SBS) is the most recommended model for autism, however, it is clear that most countries can not implement this model in their health system. The results of this study, which reached to the largest sample to date, suggest that SBS may not be the only me for screening ASD and that alternative methods should be tried, as there is an obvious need for exploratory approaches.

Early Developmental Trends in High-Risk Neonates Later Diagnosed With Autism Spectrum Disorder.

We hypothesized that clinical data from a neonatal intensive care unit (NICU) infant developmental follow-up clinic would identify early manifestations of autism spectrum disorder (ASD). One hundred forty-four infants were identified; 72 later diagnosed with ASD and 72 controls. Retrospective chart review provided data from the Test of Infant Motor Performance (TIMP) and the Bayley Scales of Infant and Toddler Development, third edition (Bayley-III), between 8 and 26 months of age. Between-group comparisons indicated no significant group difference in TIMP scores; however, Bayley-III scaled scores differed between the groups at 2 administration times. The within-group Bayley-III change scores declined significantly more for the ASD group in cognitive and communication subtests. High-risk neonates, due to prematurity or morbidity, later diagnosed with ASD demonstrated statistically significant differences, including a more precipitous drop in Bayley-III scores over time. Early, longitudinal developmental surveillance for neonates at risk of ASD is critical. What this adds to the evidence: Early identification of ASD is critical to optimize developmental outcomes in young children, including infants born prematurely or with neonatal morbidity, who are perceived to have an increased risk for ASD. Despite these findings, minimal research has been conducted to evaluate the utility of commonly administered norm-referenced developmental surveillance instruments to identify possible early signs of ASD in this high-risk population due to prematurity or neonatal morbidity and not familial association. The present study analyzed retrospectively collected clinical data from a NICU developmental follow-up clinic for 144 infants, 72 of which were later diagnosed with ASD and 72 sex- and gestational age-matched controls. Results demonstrated statistically significant poorer Bayley-III outcomes for the ASD group compared with controls at 2 different study time points, including a more precipitous drop in Bayley-III scaled scores over time. This study highlights the importance of early and longitudinal developmental surveillance for high-risk neonates at risk of ASD.

Early identification of autism in Egyptian children using Arabic version of checklist for autism in toddlers-23 (CHAT-23)

Background: Screening is the first important step in the diagnostic process. There is strong evidence that early diagnosis and management of autism spectrum disorder (ASD) can lead to a better prognosis. The purpose of this study was to develop an Arabic version of the Chinese Checklist for Autism in Toddlers-23 (CHAT-23) to distinguish children with ASD in the Egyptian community. Methods: The Arabic CHAT-23 checklist was applied to 100 Egyptian children with mental age 18-24 months including 30 autistic and 70 typically-developing children. Results and conclusion: Arabic CHAT-23 checklist is a valid and reliable tool for early identification of ASD in Egyptian children with high sensitivity (93.3%) and specificity (97%). Children failing any 15 of all 23 questions of the parental questionnaire should be observed with observational items. Failing any 3 of the 4 observational items would suggest ASD.

Is traditional back translation enough? Comparison of translation methodology for an ASD screening tool.

Early identification of autism spectrum disorders (ASD) in non-English speaking children often relies on translation of English ASD screening measures. Most measures employ a forward-back translation approach, despite data suggesting that this method may result in poor psychometric properties. Some studies in non-ASD fields have suggested that a rigorous method of translation with cultural adaptation may yield better psychometric properties, but no studies in the ASD field have compared the two approaches directly. This investigation compares these two translation methodologies to determine if they produce psychometrically similar or dissimilar measures. Three hundred and eighty US-based Spanish-speaking caregivers of children 8-16 months old were randomly assigned to complete either a forward-back Spanish translation or a rigorous translation with cultural adaptation of a parent-report ASD screening tool. Measurement invariance analyses determined that the two translations were psychometrically dissimilar. Additional qualitative explanatory methods using cognitive interviews examined textual differences and participant preferences between non-invariant items. LAY SUMMARY: Autism screening questionnaires created in English need to be translated into other languages so non-English speaking parents can fill them out accurately. Traditionally, researchers have not considered cultural differences when they translate these questionnaires. When we compared a direct translation to a translation with cultural adaptations, the two questionnaires were statistically different. Parents interpreted and responded to the same questions differently, depending on which version they filled out.

Disparities in Early Intervention Program Participation by Children With Autism Spectrum Disorder in a US Metropolitan Area, 2006 to 2016

Multiple studies have shown the value of early interventions for autism spectrum disorder (ASD). In the US, the Early Intervention Program (EIP) is mandated by law (Part C of the Individuals With Disabilities Education Act [IDEA]) to provide services to all young children with delays or disabilities. However, the extent to which children with ASD participate in this key service system is unknown. To evaluate EIP use by children with ASD from 2006 to 2016 and to describe the factors associated with EIP participation. This cross-sectional study used repeated data collected from 2006 to 2016 by active ASD surveillance of the New York-New Jersey metropolitan area as reported in the New Jersey Autism Study. The New Jersey Autism Study identified 4050 children aged 8 years with ASD from 2006 to 2016. Demographic and clinical data were collected and participation in an EIP was assessed through active surveillance. Data were analyzed from June to December 2021. Sociodemographic factors associated with the outcome of EIP participation. Participation in an EIP assessed at age 8 years. Demographic, ecological, and clinical factors, as well as temporal patterns, were examined by using standard and multilevel logistic regression models. Among 4050 children aged 8 years with ASD by active surveillance, 1887 (46.6%) received EIP services. Of these children, 3303 (81.6%) were boys; 1105 (27.3%) were Hispanic, 801 (19.8%) were non-Hispanic Black, 1816 (44.8%) were non-Hispanic White, and 328 (8.1%) were non-Hispanic other (included Alaska Native or American Indian and Asian or Pacific Islander). In adjusted regression models, non-Hispanic Black children with ASD had lower odds of EIP participation (adjusted odds ratio [AOR], 0.67; 95% CI, 0.54-0.84) compared with their non-Hispanic White peers, and children residing in affluent areas had higher odds of receiving EIP services (AOR, 1.71; 95% CI, 1.36-2.15) compared with children residing in underserved areas. Children with ASD born in 2008 had higher odds of EIP participation than children born in 1998 (AOR, 2.64; 95% CI, 2.07-3.36). Early identification of ASD is an important public health priority and receipt of EIP services may improve ASD outcomes. Approximately half of the population of children aged 8 years with ASD received EIP services between 2006 and 2016, and EIP participation by children with ASD increased during the 10-year period. However, receipt of EIP services was marked by strong socioeconomic status- and race and ethnicity-based disparities. Universal ASD screening and additional strategies are needed to address disparities and to increase access to EIP services.

Identification of Autism spectrum disorder based on a novel feature selection method and Variational Autoencoder

The development of noninvasive brain imaging such as resting-state functional magnetic resonance imaging (rs-fMRI) and its combination with AI algorithm provides a promising solution for the early diagnosis of Autism spectrum disorder (ASD). However, the performance of the current ASD classification based on rs-fMRI still needs to be improved. This paper introduces a classification framework to aid ASD diagnosis based on rs-fMRI. In the framework, we proposed a novel filter feature selection method based on the difference between step distribution curves (DSDC) to select remarkable functional connectivities (FCs) and utilized a multilayer perceptron (MLP) which was pretrained by a simplified Variational Autoencoder (VAE) for classification. We also designed a pipeline consisting of a normalization procedure and a modified hyperbolic tangent (tanh) activation function to replace the classical tanh function, further improving the model accuracy. Our model was evaluated by 10 times 10-fold cross-validation and achieved an average accuracy of 78.12%, outperforming the state-of-the-art methods reported on the same dataset. Given the importance of sensitivity and specificity in disease diagnosis, two constraints were designed in our model which can improve the model’s sensitivity and specificity by up to 9.32% and 10.21%, respectively. The added constraints allow our model to handle different application scenarios and can be used broadly.

Identification of Young High-Functioning Autism Individuals Based on Functional Connectome Using Graph Isomorphism Network: A Pilot Study.

Accumulated studies have determined the changes in functional connectivity in autism spectrum disorder (ASD) and spurred the application of machine learning for classifying ASD. Graph Neural Network provides a new method for network analysis in brain disorders to identify the underlying network features associated with functional deficits. Here, we proposed an improved model of Graph Isomorphism Network (GIN) that implements the Weisfeiler-Lehman (WL) graph isomorphism test to learn the graph features while taking into account the importance of each node in the classification to improve the interpretability of the algorithm. We applied the proposed method on multisite datasets of resting-state functional connectome from Autism Brain Imaging Data Exchange (ABIDE) after stringent quality control. The proposed method outperformed other commonly used classification methods on five different evaluation metrics. We also identified salient ROIs in visual and frontoparietal control networks, which could provide potential neuroimaging biomarkers for ASD identification.

Progress and Disparities in Early Identification of Autism Spectrum Disorder: Autism and Developmental Disabilities Monitoring Network, 2002-2016.

Early identification can improve outcomes for children with autism spectrum disorder (ASD). We sought to assess changes in early ASD identification over time and by co-occurring intellectual disability (ID) and race/ethnicity. Using data for 2002-2016 from a biennial population-based ASD surveillance program among 8-year-old children in the United States, we defined identification as a child's earliest recorded ASD diagnosis or special education eligibility. Unidentified children had characteristics meeting the ASD surveillance case definition but no recorded identification by age 8 years. We calculated median age at identification among identified children, median age at identification including unidentified children, and cumulative incidence of identification by age 48 months. ASD identification by age 48 months was 4 times (95% CI: 3.6-4.3) as likely in 2016 as in 2002, with the largest increases among children without ID. Median age at ASD identification among identified children decreased 3 months during this time. Children of every race/ethnicity were more likely to be identified over time. There were racial disparities stratified by ID: in 2016, Black and Hispanic children without ID were less likely to be identified with ASD than were White children (both groups risk ratio: 0.7; 95% CI: 0.5-0.8), but Black children were 1.5 times (95% CI: 1.3-1.9) as likely as White children to be identified with ASD and ID. Substantial progress has been made to identify more children with ASD early, despite minimal decrease in median age at diagnosis. Considerable disparities remain in early ASD identification by race/ethnicity and co-occurring intellectual disability.

Individual Brain Morphological Connectome Indicator Based on Jensen-Shannon Divergence Similarity Estimation for Autism Spectrum Disorder Identification.

BackgroundStructural magnetic resonance imaging (sMRI) reveals abnormalities in patients with autism spectrum syndrome (ASD). Previous connectome studies of ASD have failed to identify the individual neuroanatomical details in preschool-age individuals. This paper aims to establish an individual morphological connectome method to characterize the connectivity patterns and topological alterations of the individual-level brain connectome and their diagnostic value in patients with ASD.MethodsBrain sMRI data from 24 patients with ASD and 17 normal controls (NCs) were collected; participants in both groups were aged 24–47 months. By using the Jensen–Shannon Divergence Similarity Estimation (JSSE) method, all participants’s morphological brain network were ascertained. Student’s t-tests were used to extract the most significant features in morphological connection values, global graph measurement, and node graph measurement.ResultsThe results of global metrics’ analysis showed no statistical significance in the difference between two groups. Brain regions with meaningful properties for consensus connections and nodal metric features are mostly distributed in are predominantly distributed in the basal ganglia, thalamus, and cortical regions spanning the frontal, temporal, and parietal lobes. Consensus connectivity results showed an increase in most of the consensus connections in the frontal, parietal, and thalamic regions of patients with ASD, while there was a decrease in consensus connectivity in the occipital, prefrontal lobe, temporal lobe, and pale regions. The model that combined morphological connectivity, global metrics, and node metric features had optimal performance in identifying patients with ASD, with an accuracy rate of 94.59%.ConclusionThe individual brain network indicator based on the JSSE method is an effective indicator for identifying individual-level brain network abnormalities in patients with ASD. The proposed classification method can contribute to the early clinical diagnosis of ASD.