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.

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.

Autism spectrum disorder diagnosis with EEG signals using time series maps of brain functional connectivity and a combined CNN-LSTM model.

BACKGROUND AND OBJECTIVE: People with autism spectrum disorder (ASD) often have cognitive impairments. Effective connectivity between different areas of the brain is essential for normal cognition. Electroencephalography (EEG) has been widely used in the detection of neurological diseases. Previous studies on detecting ASD with EEG data have focused on frequency-related features. Most of these studies have augmented data by splitting the dataset into time slices or sliding windows. However, such approaches to data augmentation may cause the testing data to be contaminated by the training data. To solve this problem, this study developed a novel method for detecting ASD with EEG data. METHODS: This study quantified the functional connectivity of the subject's brain from EEG signals and defined the individual to be the unit of analysis. Publicly available EEG data were gathered from 97 and 92 subjects with ASD and typical development (TD), respectively, while they were at rest or performing a task. Time-series maps of brain functional connectivity were constructed, and the data were augmented using a deep convolutional generative adversarial network. In addition, a combined network for ASD detection, based on convolutional neural network (CNN) and long short-term memory (LSTM), was designed and implemented. RESULTS: Based on functional connectivity, the network achieved classification accuracies of 81.08% and 74.55% on resting state and task state data, respectively. In addition, we found that the functional connectivity of ASD differed from TD primarily in the short-distance functional connectivity of the parietal and occipital lobes and in the distant connections from the right temporoparietal junction region to the left posterior temporal lobe. CONCLUSIONS: This paper provides a new perspective for better utilizing EEG to understand ASD. The method proposed in our study is expected to be a reliable tool to assist in the diagnosis of ASD.

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 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.

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.

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.

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.

The assessment of microbial infection in children with autism spectrum disorders and genetic folate cycle deficiency.

BACKGROUND: The results of disparate clinical studies indicate abnormally frequent cases of certain microorganisms in children with autism spectrum disorders (ASD). However, these data require clarification and systematization. The study aims to study the structure of the microbial profile in children with ASD and genetic folate cycle deficiency (GFCD) and consider differences in diagnostic approaches for identifying microorganisms of different types. METHODS: The study analyzed medical data from 240 children (187 boys and 63 girls) with GFCD aged 2 to 9 years. The children had clinical manifestations of ASD (the study group, SG). The control group (CG) included 53 clinically healthy children (37 boys and 16 girls) of the same age but without GFCD. Both groups of children were tested on active herpetic infections (HSV-1/2, VZV, EBV, CMV, HHV-6, HHV-7, HHV-8), ТТV, Streptococcus pyogenes, Candida albicans, Borrelia burgdorferi, Mycoplasma pneumoniae, Chlamydia pneumoniae, Yersinia enterocolitica, Toxoplasma gondii, congenital CMV neuroinfection and postnatal HSV-1/2 encephalitis. The testing used diagnostic methods specified in PubMed-indexed studies. RESULTS: In the SG, TTV was found in 196 children (82%), HHV-7 - in 172 (72%), HHV-6 - in 162 (68%), EBV - in 153 (64%), Streptococcus pyogenes - in 127 (53%), Candida albicans - in 116 (48%), Borrelia - in 107 (45%), Mycoplasma pneumoniae - in 94 (39%), Chlamydia pneumoniae - in 85 (35%), Yersinia entеrocolitica - in 71 (30%), Toxoplasma gondii - in 54 (23%), congenital CMV neuroinfection - in 26 (11%), and postnatal HSV-1/2 encephalitis - in 11 children (5% of cases) (p < p0.05; Z < Z0.05). In the SG, there was a higher microbial load in older children (p < p0.05; Z < Z0.05). No gender differences were found. CONCLUSIONS: The study described and characterized a specific abnormal microbial spectrum with a predominance of viral opportunistic agents in children with ASD associated with GFCD.

Evaluation of functional gastrointestinal disorders in children aged 4-10 years with autism spectrum disorder.

BACKGROUND: Gastrointestinal system disorders are known to be prevalent among children with autism spectrum disorder (ASD). Some ASD-associated comorbidities are abdominal pain, constipation, diarrhea, gastroesophageal reflux, sleep disturbances, epilepsy, and psychiatric problems. Nonetheless, there is still limited information about the presence of functional GI disorders (FGIDs) among children with ASD, especially in Türkiye. Using the Rome criteria, we aimed to investigate FGIDs in children with ASD. METHODS: The sample of the study consisted of 68 children aged 4-10 years, diagnosed with ASD according to the DSM-5 diagnostic criteria and had scores greater than 30 on the Childhood Autism Rating Scale (CARS-2) and an age-sex matched control group (n=78). The Rome III criteria were used to evaluate FGIDs. RESULTS: The frequency of FGIDs in the ASD group was higher (76.5%) compared to the control group (p < 0.001). Compared to the control group, abdominal migraine frequency increased 10 times (p=0.012), functional constipation 7 times (p < 0.001), and fecal incontinence 6 times (p < 0.001) in the ASD group. Stool retention was not present in most children in the ASD group who were found to have fecal incontinence. CONCLUSION: In this study, the most common FGIDs in the ASD group were abdominal migraine, functional constipation, and non-retentive fecal incontinence. The finding that most children with ASD who had fecal incontinence did not show stool retention implicated social, psychological, and behavioral factors as the causes of incontinence. Raising awareness of healthcare professionals about the frequency of FGIDs in children with ASD will improve many areas in the daily lives of these children.

Relationship between serum cortisol levels, stereotypies, and the presence of autism spectrum disorder in patients with severe intellectual disability.

Stereotypies are one of the diagnostic criteria for autism spectrum disorder (ASD) and are common to both ASD and intellectual disability (ID). Previous studies have been inconclusive, with some showing a positive correlation between stereotypies and cortisol, while others have shown a negative correlation. We hypothesised and investigated the presence of ASD as one of the variables involved in this discrepancy. We tested the following hypotheses on serum cortisol in a total of 84 hospitalised patients with severe ID and ASD with severe ID. Hypothesis (1) Higher levels of stereotypies are associated with higher levels of serum cortisol. Hypothesis (2) The presence of ASD will moderate the association between stereotypies and high serum cortisol levels. The results of the analysis supported hypotheses (1) and (2). We also found that in the population with ID, serum cortisol levels were significantly lower in the ASD group compared to the non-ASD group. The present findings that the association between stereotypies and serum cortisol levels in people with severe ID is moderated by the presence of ASD suggest that the stress response system may function differently in people with ID and ASD than in the general population.

The Autism Spectrum Disorder and Its Possible Origins in Pregnancy.

Autism Spectrum Disorder (ASD) belongs to the group of neurodevelopmental disorders, and has a high prevalence, affecting 1 in 100 children according to data from the World Health Organization (WHO). To be diagnosed with ASD, the child must have persistent deficits in communication and social interactions, and restricted and repetitive patterns of behavior, interests, or activities. Despite its prevalence, the etiology of ASD is still uncertain, with multifactorial characteristics, including those associated with the gestational period, where maternal exposure to biological, chemical, or physical hazards occurs, some of which have already been proposed as causes of ASD outcomes. Since pregnancy requires a balance between the maternal-fetal binomial, the breakdown of this balance caused by such environmental hazards can lead to altered fetal neurodevelopment, including ASD. With this firmly in mind, this review aims to compile the most recent data on the gestational causes that may be associated with the development of ASD to help health professionals identify risk factors and act for the prevention and management of ASD.

Body Composition and Anthropometric Measurements in Children and Adolescents with Autism Spectrum Disorder: A Case-Control Study in Lebanon.

The occurrence of overweight and obesity among individuals with Autism Spectrum Disorder (ASD) has become a worldwide epidemic. However, there is limited research on this topic in the Lebanese population. Therefore, this study aimed to assess the differences in anthropometric measurements and body composition variables among Lebanese children, pre-adolescents, and adolescents diagnosed with ASD in contrast to typically developing peers across various developmental stages. Additionally, it aimed to investigate the prevalence of overweight and obesity within this population. A total of 86 participants with ASD and 86 controls were involved in this case-control study, conducted between June 2022 and June 2023. Anthropometric measurements and body composition variables were assessed, followed by statistical analyses to examine the differences between these two groups. The results revealed a significantly higher prevalence of overweight and obesity among individuals with ASD, particularly evident during childhood and pre-adolescence. Additionally, this group exhibited a higher body fat mass and total body fat percentage compared to controls. However, there were no significant differences observed between the two groups during adolescence. These findings emphasize the significance of monitoring and addressing weight status in individuals with ASD to improve their overall health outcomes. Future research directions could focus on investigating the underlying mechanisms contributing to the heightened prevalence of overweight and obesity in this population, ultimately enhancing their quality of life and well-being.

Self-Guided DMT: Exploring a Novel Paradigm of Dance Movement Therapy in Mixed Reality for Children with ASD.

Children diagnosed with Autism Spectrum Disorder (ASD) often exhibit motor disorders. Dance Movement Therapy (DMT) has shown great potential for improving the motor control ability of children with ASD. However, traditional DMT methods often lack vividness and are difficult to implement effectively. To address this issue, we propose a Mixed Reality DMT approach, utilizing interactive virtual agents. This approach offers immersive training content and multi-sensory feedback. To improve the training performance of children with ASD, we introduce a novel training paradigm featuring a self-guided mode. This paradigm enables the rapid creation of a virtual twin agent of the child with ASD using a single photo to embody oneself, which can then guide oneself during training. We conducted an experiment with the participation of 24 children diagnosed with ASD (or ASD propensity), recording their training performance under various experimental conditions. Through expert rating, behavior coding of training sessions, and statistical analysis, our findings revealed that the use of the twin agent for self-guidance resulted in noticeable improvements in the training performance of children with ASD. These improvements were particularly evident in terms of enhancing movement quality and refining overall target-related responses. Our study holds clinical potential in the field of medical treatment and rehabilitation for children with ASD.

Caregiver and youth inter-rater assessment agreement in autism spectrum disorder, developmental coordination disorder, and typical development.

Youth diagnosed with autism spectrum disorder (ASD) and those with developmental coordination disorder (DCD) are at heightened risk for co-occurring mental health diagnoses, especially anxiety and attention-deficit/hyperactivity disorder (ADHD). However, caregiver-child agreement on presence of related symptoms in populations with neurodevelopmental conditions is not well understood. Here, we examine the extent to which 37 ASD, 26 DCD, and 40 typically developing children and their caregivers agree on the degree of the child's symptoms of anxiety and ADHD. All caregiver-child dyads completed the Screen for Child Anxiety Related Emotional Disorders and Conners 3 ADHD Index. Across groups, intraclass correlations indicated generally poor agreement on anxiety and ADHD symptomatology. Although youth generally reported greater internalizing symptoms (i.e., anxiety), caregivers tended to report more observable externalizing behaviors (i.e., ADHD). Together, the results of this study support the need for a multi-informant approach in assessments of anxiety and ADHD in youth with neurodevelopmental disorders.

Biosignal comparison for autism assessment using machine learning models and virtual reality.

Clinical assessment procedures encounter challenges in terms of objectivity because they rely on subjective data. Computational psychiatry proposes overcoming this limitation by introducing biosignal-based assessments able to detect clinical biomarkers, while virtual reality (VR) can offer ecological settings for measurement. Autism spectrum disorder (ASD) is a neurodevelopmental disorder where many biosignals have been tested to improve assessment procedures. However, in ASD research there is a lack of studies systematically comparing biosignals for the automatic classification of ASD when recorded simultaneously in ecological settings, and comparisons among previous studies are challenging due to methodological inconsistencies. In this study, we examined a VR screening tool consisting of four virtual scenes, and we compared machine learning models based on implicit (motor skills and eye movements) and explicit (behavioral responses) biosignals. Machine learning models were developed for each biosignal within the virtual scenes and then combined into a final model per biosignal. A linear support vector classifier with recursive feature elimination was used and tested using nested cross-validation. The final model based on motor skills exhibited the highest robustness in identifying ASD, achieving an AUC of 0.89 (SD = 0.08). The best behavioral model showed an AUC of 0.80, while further research is needed for the eye-movement models due to limitations with the eye-tracking glasses. These findings highlight the potential of motor skills in enhancing objectivity and reliability in the early assessment of ASD compared to other biosignals.