Restoring private autism dataset from sanitized database using an optimized key produced from enhanced combined PSO-GWO framework.

The timely identification of autism spectrum disorder (ASD) in children is imperative to prevent potential challenges as they grow. When sharing data related to autism for an accurate diagnosis, safeguarding its security and privacy is a paramount concern to fend off unauthorized access, modification, or theft during transmission. Researchers have devised diverse security and privacy models or frameworks, most of which often leverage proprietary algorithms or adapt existing ones to address data leakage. However, conventional anonymization methods, although effective in the sanitization process, proved inadequate for the restoration process. Furthermore, despite numerous scholarly contributions aimed at refining the restoration process, the accuracy of restoration remains notably deficient. Based on the problems identified above, this paper presents a novel approach to data restoration for sanitized sensitive autism datasets with improved performance. In the prior study, we constructed an optimal key for the sanitization process utilizing the proposed Enhanced Combined PSO-GWO framework. This key was implemented to conceal sensitive autism data in the database, thus avoiding information leakage. In this research, the same key was employed during the data restoration process to enhance the accuracy of the original data recovery. Therefore, the study enhanced the restoration process for ASD data's security and privacy by utilizing an optimal key produced via the Enhanced Combined PSO-GWO framework. When compared to existing meta-heuristic algorithms, the simulation results from the autism data restoration experiments demonstrated highly competitive accuracies with 99.90%, 99.60%, 99.50%, 99.25%, and 99.70%, respectively. Among the four types of datasets used, this method outperforms other existing methods on the 30-month autism children dataset, mostly.

Protocol for a systematic review evaluating psychometric properties and gender-related measurement (non)invariance of self-report assessment tools for autism in adults.

BACKGROUND: Given the recent evidence on gender differences in the presentation of autism, there is an increasing concern that current tools for autism do not adequately capture traits more often found in women. If tools for autism measure autistic traits differently based on gender alone, their validity may be compromised as they may not be measuring the same construct across genders. Measurement invariance investigations of autism measures can help assess the validity of autism constructs for different genders. The aim of this systematic review is to identify and critically appraise the psychometric properties of all self-report tools for autism in adults that meet two criteria: (a) they have been published since or included in the NICE (2014) recommendations, and (b) they have undergone gender-related measurement invariance investigations as part of their validation process. METHODS: A search of electronic databases will be conducted from 2014 until the present using MEDLINE, Embase, and PsycINFO using predefined search terms to identify eligible studies. The search for grey literature will include sources such as OpenGrey, APA PsycEXTRA, and Scopus. Two reviewers will independently screen titles, abstracts, and full texts for eligibility. The references of included studies will be searched for additional records. The methodological quality of the studies will be evaluated using the COSMIN Risk of Bias checklist, while psychometric quality of findings will be assessed based on criteria for good measurement properties and ConPsy checklist. The quality of the total body of evidence will be appraised using the approach outlined in the modified GRADE guidelines. DISCUSSION: This systematic review will be among the first to assess the psychometric properties and gender-related measurement invariance of self-reported measures for autism in adults that were published since (or included in) NICE (2014) guidelines. The review will provide recommendations for the most suitable tool to assess for autism without gender bias. If no such measure is found, it will identify existing tools with promising psychometric properties that require further testing, or suggest developing a new measure. SYSTEMATIC REVIEW REGISTRATION: The protocol has been registered at the International Prospective Register of Systematic Reviews (PROSPERO). The registration number is CRD42023429350.

Structured neurological soft signs examination reveals motor coordination deficits in adults diagnosed with high-functioning autism.

Neurological soft signs (NSS), discrete deficits in motor coordination and sensory integration, have shown promise as markers in autism diagnosis. While motor impairments, partly associated with core behavioral features, are frequently found in children with autism, there is limited evidence in adults. In this study, NSS were assessed in adults undergoing initial diagnosis of high-functioning autism (HFA), a subgroup difficult to diagnose due to social adaptation and psychiatric comorbidity. Adults with HFA (n = 34) and 1:1 sex-, age-, and intelligence-matched neurotypical controls were administered a structured NSS examination including motor, sensory, and visuospatial tasks. We showed that adults with HFA have significantly increased motor coordination deficits compared with controls. Using hierarchical cluster analysis within the HFA group, we also identified a subgroup that was particularly highly affected by NSS. This subgroup differed from the less affected by intelligence level, but not severity of autism behavioral features nor global psychological distress. It remains questionable whether motor impairment represents a genuinely autistic trait or is more a consequence of factors such as intelligence. Nevertheless, we conclude that examining NSS in terms of motor coordination may help diagnose adults with HFA and identify HFA individuals who might benefit from motor skills interventions.

Enhanced interest in letters and numbers in autistic children.

BACKGROUND: An intense and precocious interest in written material, together with a discrepancy between decoding and reading comprehension skills are defining criteria for hyperlexia, which is found in up to 20% of autistic individuals. It may represent the extreme end of a broader interest in written material in autism. This study examines the magnitude and nature of the interest in written material in a large population of autistic and non-autistic children. METHODS: All 701 children (391 autistic, 310 non-autistic) under the age of 7 referred to an autism assessment clinic over a span of 4 years were included. Ordinal logistic regressions assessed the association between diagnosis and the level of interest in letters and numbers. A nested sample of parents of 138 autistic, 99 non-autistic clinical, and 76 typically developing (TD) children completed a detailed questionnaire. Cox proportional hazards models analyzed the age of emergence of these interests. Linear regressions evaluated the association between diagnosis and interest level. The frequency of each behaviour showing interest and competence with letters and numbers were compared. RESULTS: In the two studies, 22 to 37% of autistic children had an intense or exclusive interest in letters. The odds of having a greater interest in letters was 2.78 times higher for autistic children than for non-autistic clinical children of the same age, and 3.49 times higher for the interest in numbers, even if 76% of autistic children were minimally or non-verbal. The age of emergence of these interests did not differ between autistic and TD children and did not depend on their level of oral language. Non-autistic children showed more interest in letters within a social context. LIMITATIONS: The study holds limitations inherent to the use of a phone questionnaire with caregivers and missing sociodemographic information. CONCLUSIONS: The emergence of the interest of autistic children toward written language is contemporaneous to the moment in their development where they display a strong deficit in oral language. Together with recent demonstrations of non-social development of oral language in some autistic children, precocious and intense interest in written material suggests that language acquisition in autism may follow an alternative developmental pathway.

Using AI-Based Virtual Companions to Assist Adolescents with Autism in Recognizing and Addressing Cyberbullying.

Social media platforms and online gaming sites play a pervasive role in facilitating peer interaction and social development for adolescents, but they also pose potential threats to health and safety. It is crucial to tackle cyberbullying issues within these platforms to ensure the healthy social development of adolescents. Cyberbullying has been linked to adverse mental health outcomes among adolescents, including anxiety, depression, academic underperformance, and an increased risk of suicide. While cyberbullying is a concern for all adolescents, those with disabilities are particularly susceptible and face a higher risk of being targets of cyberbullying. Our research addresses these challenges by introducing a personalized online virtual companion guided by artificial intelligence (AI). The web-based virtual companion's interactions aim to assist adolescents in detecting cyberbullying. More specifically, an adolescent with ASD watches a cyberbullying scenario in a virtual environment, and the AI virtual companion then asks the adolescent if he/she detected cyberbullying. To inform the virtual companion in real time to know if the adolescent has learned about detecting cyberbullying, we have implemented fast and lightweight cyberbullying detection models employing the T5-small and MobileBERT networks. Our experimental results show that we obtain comparable results to the state-of-the-art methods despite having a compact architecture.

Measuring self and informant perspectives of Restricted and Repetitive Behaviours (RRBs): psychometric evaluation of the Repetitive Behaviours Questionnaire-3 (RBQ-3) in adult clinical practice and research settgs.

BACKGROUND: Brief questionnaires that comprehensively capture key restricted and repetitive behaviours (RRBs) across different informants have potential to support autism diagnostic services. We tested the psychometric properties of the 20-item Repetitive Behaviours Questionnaire-3 (RBQ-3), a questionnaire that includes self-report and informant-report versions enabling use across the lifespan. METHOD: In Study 1, adults referred to a specialised adult autism diagnostic service (N = 110) completed the RBQ-3 self-report version, and a relative or long-term friend completed the RBQ-3 informant-report version. Clinicians completed the abbreviated version of the Diagnostic Interview for Social and Communication Disorders (DISCO-Abbreviated) with the same adults as part of the diagnostic process. For half of the assessments, clinicians were blind to the RBQ-3 ratings. We tested internal consistency, cross-informant reliability and convergent validity of the RBQ-3. In Study 2, a follow-up online study with autistic (N = 151) and non-autistic (N = 151) adults, we further tested internal consistency of the RBQ-3 self-report version. We also tested group differences and response patterns in this sample. RESULTS: Study 1 showed good to excellent internal consistency for both self- and informant-report versions of the RBQ-3 (total score, α = 0.90, ω = 0.90, subscales, α = 0.76-0.89, ω = 0.77-0.88). Study 1 also showed cross-informant reliability as the RBQ-3 self-report scores significantly correlated with RBQ-3 informant-report scores for the total score (rs = 0.71) and subscales (rs= 0.69-0.72). Convergent validity was found for both self and informant versions of the RBQ-3, which significantly correlated with DISCO-Abbreviated RRB domain scores (rs = 0.45-0.54). Moreover, the RBQ-3 scores showed significantly weaker association with DISCO -Abbreviated scores for the Social Communication domain, demonstrating divergent validity. Importantly, these patterns of validity were found even when clinicians were blind to RBQ-3 items. In Study 2, for both autistic and non-autistic groups, internal consistency was found for the total score (α = 0.82-0.89, ω = 0.81-0.81) and for subscales (α = 0.68-0.85, ω = 0.69-0.85). A group difference was found between groups. LIMITATIONS: Due to the characteristics and scope of the specialist autism diagnostic service, further testing is needed to include representative samples of age (including children) and intellectual ability, and those with a non-autistic diagnostic outcome. CONCLUSIONS: The RBQ-3 is a questionnaire of RRBs that can be used across the lifespan. The current study tested its psychometric properties with autistic adults without intellectual disability and supported its utility for both clinical diagnostic and research settings.

Improving Access to Autism Evaluation: A Coordinated Developmental-Behavioral Pediatrics and Pediatric Neurology Diagnostic Pathway.

A shortage of board-certified developmental-behavioral pediatricians generates a bottleneck for children and families who seek autism diagnostic services. Wait time for autism evaluation commonly exceeds a year. To improve access, clinicians developed a coordinated Developmental-Behavioral Pediatrics and Pediatric Neurology autism diagnostic pathway. For a subset of children referred to neurology clinic, pediatric neurologists completed the medical part of an autism evaluation and Knights of Columbus Developmental Center psychologists or speech-language pathologists completed developmental assessments. Forty-four autism diagnostic evaluations completed through this coordinated pathway over the course of six months had shortened wait time [mean=50.89 days; range 3 to 184 days; median= 48.50 day]. Parents reported satisfaction with the autism evaluation and resources navigation process. Sustainability and scalability efforts are discussed.

A national research survey of childhood autism assessment services in the UK: empirical evidence of diagnostic practice, challenges and improvement opportunities.

BACKGROUND: The UK National Health Service (NHS) Long Term Plan aims to reduce waiting times for childhood autism diagnostic assessment and improve parent and child satisfaction. This empirical research investigated current childhood diagnostic practice provision, and changes made by teams to address challenges faced. METHODS: Data were collected using an online semi-structured research questionnaire. UK childhood autism diagnostic assessment services (for children aged 1-18 years) were invited to participate through multidisciplinary clinical networks, special interest groups and professionals mailing lists. The study was on the National Institute for Health Research Clinical Research Network portfolio. RESULTS: 128 clinicians from diverse NHS services responded including: 10 (8%) integrated services, 46 (36%) Child and Adolescent Mental Health Services (CAMHS) and 72 (56%) paediatric services. A minority of services (23, 17.9%) reported always meeting the National Institute for Health and Care Excellence guidance for assessment. Referrals rose 115% between 2015 and 2019. Clinicians described increased child and family complexity compared with previously; children had more co-occurring physical, mental health and neurodevelopmental conditions and there were more frequent family health problems and safeguarding concerns. Most services (97, 75.8%) reported recent funding stayed constant/decreased. Incomplete multidisciplinary teams (MDTs) were frequently reported; a minority of services reported increased availability of professionals, and some experienced reductions in key professionals. Many teams were unable to undertake assessments or make recommendations for associated neurodevelopmental and co-existing conditions. Teams described improvement strategies implemented (eg, adapting professionals' roles, supporting parents). CONCLUSIONS: Most UK autism paediatric and CAMHS diagnostic teams experience significant challenges affecting the assessment of children with possible autism, and recommendations regarding treatment/intervention. Where CAMHS or paediatric services work in isolation, there are often competency gaps in MDTs and ability to deliver full neurodevelopmental and mental health assessments. Teams identified service improvement strategies; however, investment in MDT expertise is required to enable services to implement changes to meet the needs of children and families.

Eye-Tracking Biomarkers and Autism Diagnosis in Primary Care.

Importance: Finding effective and scalable solutions to address diagnostic delays and disparities in autism is a public health imperative. Approaches that integrate eye-tracking biomarkers into tiered community-based models of autism evaluation hold promise for addressing this problem. Objective: To determine whether a battery of eye-tracking biomarkers can reliably differentiate young children with and without autism in a community-referred sample collected during clinical evaluation in the primary care setting and to evaluate whether combining eye-tracking biomarkers with primary care practitioner (PCP) diagnosis and diagnostic certainty is associated with diagnostic outcome. Design, Setting, and Participants: Early Autism Evaluation (EAE) Hub system PCPs referred a consecutive sample of children to this prospective diagnostic study for blinded eye-tracking index test and follow-up expert evaluation from June 7, 2019, to September 23, 2022. Participants included 146 children (aged 14-48 months) consecutively referred by 7 EAE Hubs. Of 154 children enrolled, 146 provided usable data for at least 1 eye-tracking measure. Main Outcomes and Measures: The primary outcomes were sensitivity and specificity of a composite eye-tracking (ie, index) test, which was a consolidated measure based on significant eye-tracking indices, compared with reference standard expert clinical autism diagnosis. Secondary outcome measures were sensitivity and specificity of an integrated approach using an index test and PCP diagnosis and certainty. Results: Among 146 children (mean [SD] age, 2.6 [0.6] years; 104 [71%] male; 21 [14%] Hispanic or Latine and 96 [66%] non-Latine White; 102 [70%] with a reference standard autism diagnosis), 113 (77%) had concordant autism outcomes between the index (composite biomarker) and reference outcomes, with 77.5% sensitivity (95% CI, 68.4%-84.5%) and 77.3% specificity (95% CI, 63.0%-87.2%). When index diagnosis was based on the combination of a composite biomarker, PCP diagnosis, and diagnostic certainty, outcomes were concordant with reference standard for 114 of 127 cases (90%) with a sensitivity of 90.7% (95% CI, 83.3%-95.0%) and a specificity of 86.7% (95% CI, 70.3%-94.7%). Conclusions and Relevance: In this prospective diagnostic study, a composite eye-tracking biomarker was associated with a best-estimate clinical diagnosis of autism, and an integrated diagnostic model including PCP diagnosis and diagnostic certainty demonstrated improved sensitivity and specificity. These findings suggest that equipping PCPs with a multimethod diagnostic approach has the potential to substantially improve access to timely, accurate diagnosis in local communities.

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.

Categorizing and identifying preferred interests in autistic toddlers.

Preferred interests are characteristic of autism spectrum disorder and are reported by parents starting at an early age. However, limited research has explored the presentation of preferred interests in toddlerhood. Previous literature suggests that both the intensity and type of preferred interests held by autistic individuals differ from those held by peers with developmental delay and no diagnosis and that autistic interests are more unusual in nature. While preferred interests are seen in typical child development, previous research suggests that the presence of preferred interests in children with no diagnosis declines with age. Literature also indicates that the sex and cognitive ability of autistic children influences preferred interests. Identification of early preferred interests commonly held by autistic toddlers could serve as a useful clinical indicator of future diagnosis. This article explored whether diagnostic group, age, sex, and cognitive ability predict the likelihood that parents reported preferred interests in children aged 12-36 months with diagnoses of autism, developmental delay, and those with no diagnosis. Additionally, we explored potential diagnostic group differences in interest type. Results suggest that diagnostic group, but not age, sex, or cognitive ability, predicts the likelihood that parents report preferred interests. No differences in the type of interests among diagnostic groups were identified. These results support the use of preferred interests as an early sign of autism but suggest that interest type may not be a helpful clinical indicator of autism in toddlerhood.

Individualized Care Delivery for Children With Autism and Related Disabilities Undergoing Overnight Video Electroencephalography (EEG): One Hospital's Experience With a Coordinated Team Approach.

Background and Purpose: Children with developmental disabilities have increased risk of epilepsy and need for overnight video electroencephalographic (EEG) monitoring. However, video EEGs have historically been considered difficult to complete for this population. An autism support service at a pediatric tertiary care hospital implemented a coordinated team approach to help children with developmental disability tolerate overnight video EEGs. The project included completion of a caregiver-report preprocedure questionnaire that then was shared with the multidisciplinary team and used to create individualized care plans. The current study aims to describe rates of video EEG completion and need for lead placement under general anesthesia among children with autism and related disabilities who received these supports. Methods: Rates of video EEG completion and general anesthesia use were analyzed for children referred to the support service between April 2019 and November 2021. Results: A total of 182 children with developmental disability (mean age = 10.3 years, 54.9% diagnosed with autism) met inclusion criteria. 92.9% (n = 169) of children successfully completed EEG (leads on ≥12 hours). Only 19.2% (n = 35) required general anesthesia for video EEG lead placement. The majority (80.2%) of parents (n = 146) completed the preprocedure questionnaire. Video EEG outcomes did not differ based on completion of the questionnaire. Parent-reported challenges with communication and cooperation were associated with shorter video EEG duration and greater use of general anesthesia. Conclusions: These findings suggest that most children with developmental disability can complete video EEG with sufficient support. Preprocedure planning can identify children who would benefit from additional accommodations. Further research is necessary to clarify which supports are most helpful.

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.

Enhancing early autism diagnosis through machine learning: Exploring raw motion data for classification.

In recent years, research has been demonstrating that movement analysis, utilizing machine learning methods, can be a promising aid for clinicians in supporting autism diagnostic process. Within this field of research, we aim to explore new models and delve into the detailed observation of certain features that previous literature has identified as prominent in the classification process. Our study employs a game-based tablet application to collect motor data. We use artificial neural networks to analyze raw trajectories in a "drag and drop" task. We compare a two-features model (utilizing only raw coordinates) with a four-features model (including velocities and accelerations). The aim is to assess the effectiveness of raw data analysis and determine the impact of acceleration on autism classification. Our results revealed that both models demonstrate promising accuracy in classifying motor trajectories. The four-features model consistently outperforms the two-features model, as evidenced by accuracy values (0.90 vs. 0.76). However, our findings support the potential of raw data analysis in objectively assessing motor behaviors related to autism. While the four-features model excels, the two-features model still achieves reasonable accuracy. Addressing limitations related to sample size and noise is essential for future research. Our study emphasizes the importance of integrating intelligent solutions to enhance and assist autism traditional diagnostic process and intervention, paving the way for more effective tools in assessing motor skills.