Microcephaly type 22 and autism spectrum disorder: A case report and review of literature.

INTRODUCTION: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder with a multifaceted etiology. This case report explores the ischemic cryptogenic vascular dissection as a potential underlying cause of ASD. METHODS: A 9-year-old child presented with symptoms of ASD, including social interaction difficulties, repetitive behaviors, and cognitive challenges. Despite conventional ASD treatments, significant improvement was only observed after addressing an underlying ischemic cryptogenic vascular dissection identified through DCE-CT. RESULTS: Following a reconstructive treatment approach to the vascular dissection, the patient showed marked improvement in cognitive functions, social abilities, and a reduction in ASD-related symptoms whether during the perioperative period or during approximately 5-month follow-up. CONCLUSION: This case suggests that ischemic cryptogenic vascular dissection may contribute to the symptoms of ASD. Identifying and treating underlying vascular anomalies may offer a new avenue for mitigating ASD symptoms, emphasizing the need for comprehensive diagnostic estimations in ASD management.

Diagnosis of Autism Spectrum Disorder by Dynamic Local Graph-Theory Indicators Based on Electroencephalogram.

BACKGROUND: Autism Spectrum Disorder (ASD) is a complex neurodevelopment disease characterized by impaired social and cognitive abilities. Despite its prevalence, reliable biomarkers for identifying individuals with ASD are lacking. Recent studies have suggested that alterations in the functional connectivity of the brain in ASD patients could serve as potential indicators. However, previous research focused on static functional-connectivity analysis, neglecting temporal dynamics and spatial interactions. To address this gap, our study integrated dynamic functional connectivity, local graph-theory indicators, and a feature-selection and ranking approach to identify biomarkers for ASD diagnosis. METHODS: The demographic information, as well as resting and sleeping electroencephalography (EEG) data, were collected from 20 ASD patients and 25 controls. EEG data were pre-processed and segmented into five sub-bands (Delta, Theta, Alpha-1, Alpha-2, and Beta). Functional-connection matrices were created by calculating coherence, and static-node-strength indicators were determined for each channel. A sliding-window approach, with varying widths and moving steps, was used to scan the EEG series; dynamic local graph-theory indicators were computed, including mean, standard deviation, median, inter-quartile range, kurtosis, and skewness of the node strength. This resulted in 95 features (5 sub-bands × 19 channels) for each indicator. A support-vector-machine recurrence-feature-elimination method was used to identify the most discriminative feature subset. RESULTS: The dynamic graph-theory indicators with a 3-s window width and 50% moving step achieved the highest classification performance, with an average accuracy of 95.2%. Notably, mean, median, and inter-quartile-range indicators in this condition reached 100% accuracy, with the least number of selected features. The distribution of selected features showed a preference for the frontal region and the Beta sub-band. CONCLUSIONS: A window width of 3 s and a 50% moving step emerged as optimal parameters for dynamic graph-theory analysis. Anomalies in dynamic local graph-theory indicators in the frontal lobe and Beta sub-band may serve as valuable biomarkers for diagnosing autism spectrum disorders.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor.

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

A study of the effects of screen exposure on the neuropsychological development in children with autism spectrum disorders based on ScreenQ.

PURPOSE: To investigate the relationship between multi-dimensional aspects of screen exposure and autistic symptoms, as well as neuropsychological development in children with ASD. METHODS: We compared the ScreenQ and Griffiths Development Scales-Chinese Language Edition (GDS-C) of 636 ASD children (40.79 ± 11.45 months) and 43 typically developing (TD) children (42.44 ± 9.61 months). Then, we analyzed the correlations between ScreenQ and Childhood Autism Rating Scale (CARS), and GDS-C. We further used linear regression model to analyze the risk factors associated with high CARS total scores and low development quotients (DQs) in children with ASD. RESULTS: The CARS of children with ASD was positively correlated with the ScreenQ total scores and "access, frequency, co-viewing" items of ScreenQ. The personal social skills DQ was negatively correlated with the "access, frequency, content, co-viewing and total scores" of ScreenQ. The hearing-speech DQ was negatively correlated with the "frequency, content, co-viewing and total scores" of ScreenQ. The eye-hand coordination DQ was negatively correlated with the "frequency and total scores" of ScreenQ. The performance DQ was negatively correlated with the "frequency" item of ScreenQ. CONCLUSION: ScreenQ can be used in the study of screen exposure in children with ASD. The higher the ScreenQ scores, the more severe the autistic symptoms tend to be, and the more delayed the development of children with ASD in the domains of personal-social, hearing-speech and eye-hand coordination. In addition, "frequency" has the greatest impact on the domains of personal social skills, hearing-speech, eye-hand coordination and performance of children with ASD.

A hybrid CNN-SVM model for enhanced autism diagnosis.

Autism is a representative disorder of pervasive developmental disorder. It exerts influence upon an individual's behavior and performance, potentially co-occurring with other mental illnesses. Consequently, an effective diagnostic approach proves to be invaluable in both therapeutic interventions and the timely provision of medical support. Currently, most scholars' research primarily relies on neuroimaging techniques for auxiliary diagnosis and does not take into account the distinctive features of autism's social impediments. In order to address this deficiency, this paper introduces a novel convolutional neural network-support vector machine model that integrates resting state functional magnetic resonance imaging data with the social responsiveness scale metrics for the diagnostic assessment of autism. We selected 821 subjects containing the social responsiveness scale measure from the publicly available Autism Brain Imaging Data Exchange dataset, including 379 subjects with autism spectrum disorder and 442 typical controls. After preprocessing of fMRI data, we compute the static and dynamic functional connectivity for each subject. Subsequently, convolutional neural networks and attention mechanisms are utilized to extracts their respective features. The extracted features, combined with the social responsiveness scale features, are then employed as novel inputs for the support vector machine to categorize autistic patients and typical controls. The proposed model identifies salient features within the static and dynamic functional connectivity, offering a possible biological foundation for clinical diagnosis. By incorporating the behavioral assessments, the model achieves a remarkable classification accuracy of 94.30%, providing a more reliable support for auxiliary diagnosis.

Autism Spectrum Disorder Diagnoses and Congenital Cytomegalovirus.

OBJECTIVE: To examine the association between congenital cytomegalovirus (cCMV) and autism spectrum disorder (ASD) administrative diagnoses in US children. METHODS: Cohort study using 2014 to 2020 Medicaid claims data. We used diagnosis codes to identify cCMV (exposure), ASD (outcome), and covariates among children enrolled from birth through ≥4 to <7 years. Covariates include central nervous system (CNS) anomaly or injury diagnosis codes, including brain anomaly, microcephaly within 45 days of birth, cerebral palsy, epilepsy, or chorioretinitis. We used Cox proportional hazards regression models to estimate hazard ratios and 95% confidence intervals, overall and stratified by sex, birth weight and gestational age outcome (low birth weight or preterm birth), and presence of CNS anomaly or injury. RESULTS: Among 2 989 659 children, we identified 1044 (3.5 per 10 000) children with cCMV and 74 872 (25.0 per 1000) children with ASD. Of those with cCMV, 49% also had CNS anomaly or injury diagnosis codes. Children with cCMV were more likely to have ASD diagnoses (hazard ratio: 2.5; 95% confidence interval: 2.0-3.2, adjusting for birth year, sex, and region). This association differed by sex and absence of CNS anomaly or injury but not birth outcome. CONCLUSIONS: Children with (versus without) cCMV diagnoses in Medicaid claims data, most of whom likely had symptomatic cCMV, were more likely to have ASD diagnoses. Future research investigating ASD risk among cohorts identified through universal cCMV screening may help elucidate these observed associations.

Interactions-based classification of a single microbial sample.

To address the limitation of overlooking crucial ecological interactions due to relying on single time point samples, we developed a computational approach that analyzes individual samples based on the interspecific microbial relationships. We verify, using both numerical simulations as well as real and shuffled microbial profiles from the human oral cavity, that the method can classify single samples based on their interspecific interactions. By analyzing the gut microbiome of people with autistic spectrum disorder, we found that our interaction-based method can improve the classification of individual subjects based on a single microbial sample. These results demonstrate that the underlying ecological interactions can be practically utilized to facilitate microbiome-based diagnosis and precision medicine.

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

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

Identification and support of autistic individuals within the UK Criminal Justice System: a practical approach based upon professional consensus with input from lived experience.

BACKGROUND: Autism spectrum disorder (hereafter referred to as autism) is characterised by difficulties with (i) social communication, social interaction, and (ii) restricted and repetitive interests and behaviours. Estimates of autism prevalence within the criminal justice system (CJS) vary considerably, but there is evidence to suggest that the condition can be missed or misidentified within this population. Autism has implications for an individual's journey through the CJS, from police questioning and engagement in court proceedings through to risk assessment, formulation, therapeutic approaches, engagement with support services, and long-term social and legal outcomes. METHODS: This consensus based on professional opinion with input from lived experience aims to provide general principles for consideration by United Kingdom (UK) CJS personnel when working with autistic individuals, focusing on autistic offenders and those suspected of offences. Principles may be transferable to countries beyond the UK. Multidisciplinary professionals and two service users were approached for their input to address the effective identification and support strategies for autistic individuals within the CJS. RESULTS: The authors provide a consensus statement including recommendations on the general principles of effective identification, and support strategies for autistic individuals across different levels of the CJS. CONCLUSION: Greater attention needs to be given to this population as they navigate the CJS.

Diagnostic Evaluation of Autism Spectrum Disorder in Pediatric Primary Care.

BACKGROUND AND OBJECTIVES: Children with autism spectrum disorder (ASD) continue to experience significant delays in diagnosis and interventions. One of the main factors contributing to this delay is a shortage of developmental-behavioral specialists. Diagnostic evaluation of ASD by primary care pediatricians (PCPs) has been shown to be reliable and to decrease the interval from first concern to diagnosis. In this paper, we present the results of a primary care ASD diagnosis program in which the PCP serves as the primary diagnostician and leverages the infrastructure of the primary care medical home to support the child and family during the pre- and post-diagnostic periods, along with data on parental satisfaction with this model. METHODS: Retrospective data from a cohort of patients evaluated through this program were analyzed to determine the mean age at diagnosis and interval from referral for evaluation to diagnosis. We used survey methodology to obtain data from parents regarding their satisfaction with the process. RESULTS: Data from 8 of 20 children evaluated from April 2021 through May 2022 showed a median age of diagnosis of 34.5 months compared to the national average of 49 months. Mean interval from referral for evaluation to diagnosis was 3.5 months. Parental survey responses indicated high satisfaction. CONCLUSIONS: This model was successful in shortening the interval from referral to diagnosis resulting in significant decrease of age at diagnosis compared with the national average. Widespread implementation could improve access to timely diagnostic services and improve outcomes for children with ASD.

Diagnostic yield of the chromosomal microarray analysis in turkish patients with unexplained development delay/intellectual disability(ID), autism spectrum disorders and/or multiple congenital anomalies and new clinical findings.

BACKGROUND: Chromosomal microarray analysis is an essential tool for copy number variants detection in patients with unexplained developmental delay/intellectual disability, autism spectrum disorders, and multiple congenital anomalies. The study aims to determine the clinical significance of chromosomal microarray analysis in this patient group. Another crucial aspect is the evaluation of copy number variants detected in terms of the diagnosis of patients. METHODS AND RESULTS: A Chromosomal microarray analysis was was conducted on a total of 1227 patients and phenotype-associated etiological diagnosis was established in 135 patients. Phenotype-associated copy number variants were detected in 11% of patients. Among these, 77 patients 77 (57%, 77/135) were diagnosed with well-recognized genetic syndromes and phenotype-associated copy number variants were found in 58 patients (42.9%, 58/135). The study was designed to collect data of patients in Kocaeli Derince Training and Research Hospital retrospectively. In our study, we examined 135 cases with clinically significant copy number variability among all patients. CONCLUSIONS: In this study, chromosomal microarray analysis revealed pathogenic de novo copy number variants with new clinical features. Chromosomal microarray analysis in the Turkish population has been reported in the largest patient cohort to date.

Clinical correlates of diagnostic certainty in children and youths with Autistic Disorder.

BACKGROUND: Clinicians diagnosing autism rely on diagnostic criteria and instruments in combination with an implicit knowledge based on clinical expertise of the specific signs and presentations associated with the condition. This implicit knowledge influences how diagnostic criteria are interpreted, but it cannot be directly observed. Instead, insight into clinicians' understanding of autism can be gained by investigating their diagnostic certainty. Modest correlations between the certainty of an autism diagnosis and symptom load have been previously reported. Here, we investigated the associations of diagnostic certainty with specific items of the ADOS as well as other clinical features including head circumference. METHODS: Phenotypic data from the Simons Simplex Collection was used to investigate clinical correlates of diagnostic certainty in individuals diagnosed with Autistic Disorder (n = 1511, age 4 to 18 years). Participants were stratified by the ADOS module used to evaluate them. We investigated how diagnostic certainty was associated with total ADOS scores, age, and ADOS module. We calculated the odds-ratios of being diagnosed with the highest possible certainty given the presence or absence of different signs during the ADOS evaluation. Associations between diagnostic certainty and other cognitive and clinical variables were also assessed. RESULTS: In each ADOS module, some items showed a larger association with diagnostic certainty than others. Head circumference was significantly higher for individuals with the highest certainty rating across all three ADOS modules. In turn, head circumference was positively correlated with some of the ADOS items that were associated with diagnostic certainty, and was negatively correlated with verbal/nonverbal IQ ratio among those assessed with ADOS module 2. LIMITATIONS: The investigated cohort was heterogeneous, e.g. in terms of age, IQ, language level, and total ADOS score, which could impede the identification of associations that only exist in a subgroup of the population. The variability of the certainty ratings in the sample was low, limiting the power to identify potential associations with other variables. Additionally, the scoring of diagnostic certainty may vary between clinicians. CONCLUSION: Some ADOS items may better capture the signs that are most associated with clinicians' implicit knowledge of Autistic Disorder. If replicated in future studies, new diagnostic instruments with differentiated weighting of signs may be needed to better reflect this, possibly resulting in better specificity in standardized assessments.

Attention-deficit Hyperactivity Disorder and Autism Spectrum Disorder: Towards Better Diagnosis and Management.

Background: Attention-deficit hyperactivity disorder (ADHA) is one of the most common comorbid disorders of autism spectrum disorder (ASD) that can accompany autism, triggered by it, or be a consequence of it. Objective: This review explored the prevalence of the comorbidity of both disorders, neurobiological background, symptoms, latest assessment methods, and therapeutic approaches. Results and Discussion: It concluded that effective assessment, diagnosis and management of ADHD in ASD children and adults is essential for this group of patients to thrive and live a good quality of life. Further research is recommended to explore the most effective intervention for such important members of our society. Conclusion: More studies are needed to understand the mechanisms underlying these comorbidities, and to prevent the misdiagnosis and mismanagement of these disorders. Also, to develop up to date personalized therapeutic plans for such children.

ESDM intervention in severe preschool autism: an Italian Case report, psychological and social medicine reflections.

BACKGROUND: The goal of our contribution is to discuss a preschool intervention based on the Early Start Denver Model and the use of the main tools for the detection of adaptive behaviour in cases of autism: Vineland, ABAS. CASE PRESENTATION: the work is the presentation of a clinical case that has benefited from an intervention with the Early Start Denver Model methodology for the benefit of a child with socio-cultural and economic disadvantages. This early intervention, in a child of 36 months, which followed the diagnosis, was possible thanks to the intervention of many third-sector organizations which allowed this child, with a serious autism profile, to receive an evidence-based intervention for free. At the beginning of the intervention, the child presented a diagnosis of severe autism with absence of gaze, vocalizations and other communicative impairments. The level of motor clumsiness was also quite high, as were stereotypies. CONCLUSIONS: Research has shown the usefulness of intervening in this area with an early assessment and/or diagnosis and immediate intervention; however, public health services are not always able to maintain this pace. Our contribution therefore shows on the one hand the evidence of the improvements achieved by the child despite the low intensity of the treatment, and on the other hand, demonstrates the total versatility and adaptability of the Denver Model to the Italian context. In our conclusions, there are also some reflections on the tools used to measure adaptive behavior which seem to have a number of limitations and criticalities.

BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping.

Converging evidence increasingly suggests that psychiatric disorders, such as major depressive disorder (MDD) and autism spectrum disorder (ASD), are not unitary diseases, but rather heterogeneous syndromes that involve diverse, co-occurring symptoms and divergent responses to treatment. This clinical heterogeneity has hindered the progress of precision diagnosis and treatment effectiveness in psychiatric disorders. In this study, we propose BPI-GNN, a new interpretable graph neural network (GNN) framework for analyzing functional magnetic resonance images (fMRI), by leveraging the famed prototype learning. In addition, we introduce a novel generation process of prototype subgraph to discover essential edges of distinct prototypes and employ total correlation (TC) to ensure the independence of distinct prototype subgraph patterns. BPI-GNN can effectively discriminate psychiatric patients and healthy controls (HC), and identify biological meaningful subtypes of psychiatric disorders. We evaluate the performance of BPI-GNN against 11 popular brain network classification methods on three psychiatric datasets and observe that our BPI-GNN always achieves the highest diagnosis accuracy. More importantly, we examine differences in clinical symptom profiles and gene expression profiles among identified subtypes and observe that our identified brain-based subtypes have the clinical relevance. It also discovers the subtype biomarkers that align with current neuro-scientific knowledge.

Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes.

OBJECTIVE: Machine learning (ML) is increasingly employed to diagnose medical conditions, with algorithms trained to assign a single label using a black-box approach. We created an ML approach using deep learning that generates outcomes that are transparent and in line with clinical, diagnostic rules. We demonstrate our approach for autism spectrum disorders (ASD), a neurodevelopmental condition with increasing prevalence. METHODS: We use unstructured data from the Centers for Disease Control and Prevention (CDC) surveillance records labeled by a CDC-trained clinician with ASD A1-3 and B1-4 criterion labels per sentence and with ASD cases labels per record using Diagnostic and Statistical Manual of Mental Disorders (DSM5) rules. One rule-based and three deep ML algorithms and six ensembles were compared and evaluated using a test set with 6773 sentences (N = 35 cases) set aside in advance. Criterion and case labeling were evaluated for each ML algorithm and ensemble. Case labeling outcomes were compared also with seven traditional tests. RESULTS: Performance for criterion labeling was highest for the hybrid BiLSTM ML model. The best case labeling was achieved by an ensemble of two BiLSTM ML models using a majority vote. It achieved 100% precision (or PPV), 83% recall (or sensitivity), 100% specificity, 91% accuracy, and 0.91 F-measure. A comparison with existing diagnostic tests shows that our best ensemble was more accurate overall. CONCLUSIONS: Transparent ML is achievable even with small datasets. By focusing on intermediate steps, deep ML can provide transparent decisions. By leveraging data redundancies, ML errors at the intermediate level have a low impact on final outcomes.