BackgroundAutism Spectrum Disorder (ASD) presents with complex, temporally evolving motor and social behaviours that are difficult to quantify in ecologically valid clinical contexts. While recent computational methods offer diagnostic insights, many depend on fully supervised learning, high-resolution video, or artificial experimental constraints, limiting scalability, interpretability, and privacy compliance. Few approaches leverage unsupervised models to uncover dynamic behavioural structure from minimally invasive inputs.MethodsTo address these limitations, we propose a privacy-preserving, unsupervised representation learning framework that operates solely on skeletal pose and optical flow features. Using 255 multimodal windows from 15 therapy sessions in the MMASD corpus, a publicly available, privacy-safe dataset of child-clinician interactions, we train a denoising temporal autoencoder to derive compact latent embeddings of behaviour.ResultsThe model uncovers a low-dimensional behavioural manifold composed of six latent motor clusters. Transition graphs reveal structured topologies, including behavioural hubs and bottlenecks. Saliency analyses identify anatomically and socially relevant features, such as joint pairs (LWrist-LAnkle, Neck-Rear Head) and dynamic flow regions (e.g., index pair 7, 14). Temporal saliency, based on reconstruction error, highlights spontaneous gesture onsets and socially salient events. KL divergence between early and late session phases quantified intra-session adaptation (range: 0.06–17.7) and showed a strong negative correlation with joint attention duration (r = −0.96, p = 0.002), suggesting links between behavioural dynamics and social engagement.DiscussionThese findings offer preliminary evidence that interpretable behavioural structure can be extracted from low-resolution, privacy-compliant inputs. While based on a limited sample, the framework illustrates potential for modeling learning dynamics, identifying salient motor patterns, and supporting objective progress tracking in ASD therapy. Future work will involve clinical validation and application to larger, longitudinal datasets to assess generalizability and therapeutic utility.
TeleABA for Hospitalized Adolescents and Young Adults With Autism Spectrum Disorder
Conditions: Autism Spectrum Disorder (ASD)
Interventions: Behavioral: Standard Hospital Care; Behavioral: Telehealth Applied Behavior Analysis (TeleABA)
Sponsors: Caring Technologies, Inc.; National Institute of Mental Health (NIMH); Hackensack Meridian Health; Center for Social Dynamics; Rutgers University
Not yet recruiting
Interventions: Behavioral: Standard Hospital Care; Behavioral: Telehealth Applied Behavior Analysis (TeleABA)
Sponsors: Caring Technologies, Inc.; National Institute of Mental Health (NIMH); Hackensack Meridian Health; Center for Social Dynamics; Rutgers University
Not yet recruiting
Autism-Related Information on Websites and General-Purpose Artificial Intelligence Chatbots: Comparative, Bilingual Study
Background: Parents increasingly consult the internet, both websites and, more recently, artificial intelligence chatbots, for information on autism spectrum disorder (ASD). However, the comparative quality of these two source types, especially across languages, remains underexplored. Objective: This study aimed to assess the completeness and accuracy of ASD information delivered by websites and 5 popular artificial intelligence chatbots and determine whether performance differs between English and Romanian content. Methods: In a cross-sectional design, 25 English-language and 25 Romanian-language websites and the responses of ChatGPT, Gemini, Claude, Copilot, and DeepSeek were evaluated. Content was benchmarked against a 24-item checklist, yielding completeness and accuracy scores. Chatbots were tested in 2 scenarios: a single broad query (A) and 24 item-specific queries (B). Results: Websites achieved higher completeness in English than in Romanian (6.9 vs 5.1; =.007) and marginally higher accuracy (6.9 vs 6.1; =.045). In scenario A, chatbot completeness (English: 5.3 vs Romanian: 6.2; =.15) and accuracy (English: 6.0 vs Romanian: 5.6; =.32) did not show significant differences by language. In the single-query scenario, websites showed higher accuracy than chatbots in both English (6.9 vs 6.0; =.19) and Romanian (6.1 vs 5.6; =.53), with neither difference reaching statistical significance. Conversely, item-specific questioning favored chatbots, which yielded higher accuracy scores than websites in English (8.3 vs 6.9; =.053) and Romanian (8.0 vs 6.1; =.007). Accuracy scores improved significantly from the single-query to the item-specific scenario (English: 6.0 vs 8.3; =.002; Romanian: 5.6 vs 8.0; =.001). While an initial analysis suggested variation in performance between chatbots (repeated measures ANOVA; =.005), pairwise differences between individual models did not remain significant after adjustment for multiple testing. Conclusions: This exploratory study indicates that the quality of online ASD information varies by language and source context. English-language websites are more complete than Romanian-language websites. Among chatbots, targeted questioning yields more accurate answers than single broad queries in both languages. The findings should be interpreted cautiously due to the temporal gap between website and chatbot data collection.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/9a4cf01573ef68781c683a28400cae07" />
Case Report: A novel de novo heterozygous truncating mutation in MED12L identified in a Chinese autistic boy
BackgroundAutism spectrum disorder (ASD) is a highly heterogeneous neurodevelopmental disorder. A previous study by Nizon et al. indicated that some children with intellectual disability (ID) carrying de novo MED12L mutations exhibited mild to moderate autistic features. However, the relationship between MED12L and ASD remains unclear.Case presentationHere we reported a male child with severe autistic features carrying a novel de novo heterozygous truncating mutation of MED12L (NM_053002.5:c.586C>T, p.(Arg196Ter)). He was diagnosed with ASD according to ICD-11 and DSM-5 criteria. Clinical examination indicated that this child exhibited severe autistic features and several dysmorphic features, including a flat nasal bridge, bulbous nasal tip, thin upper lip, and triangular face. Magnetic resonance imaging (MRI) of the brain revealed an enlarged perivascular space in the right temporal lobe.ConclusionThis case demonstrates that this de novo heterozygous truncating mutation in MED12L may be involved in the development of ASD, and haploinsufficiency of MED12L may be associated with severe autistic features. Obvious clinical manifestations and dysmorphic features in this child with a truncating mutation in MED12L expand the phenotypic spectrum of MED12L-related cases and warrant further functional studies to elucidate the relationship between MED12L and ASD.
Nominee for key federal health role has a history of questioning vaccines
WASHINGTON — The Trump administration’s pick to oversee preparedness and response to public health emergencies and disasters has questioned the use of the hepatitis B vaccine in infants and raised the disproven link between vaccines and autism in past comments reviewed by STAT.
Those comments by Sean Kaufman, nominated to be Assistant Secretary for Preparedness and Response, are part of an undercurrent of vaccine skepticism among some high-ranking Department of Health and Human Services officials under Secretary Robert F. Kennedy Jr. — despite efforts from White House officials to steer the conversation away from vaccines.
Blended Genome–Exome Sequencing Slashes Costs Without Quality Loss
A novel sequencing strategy that combines low-pass whole-genome sequencing with deep whole-exome sequencing in a single assay could significantly lower the cost of large-scale genomic studies without sacrificing analytical performance, according to a study published in Nature Genetics. The approach, known as blended genome–exome (BGE) sequencing, may help accelerate precision medicine initiatives by making comprehensive genomic profiling more accessible across diverse populations.
Researchers from Massachusetts General Hospital and the Broad Institute of MIT and Harvard developed BGE to overcome a persistent tradeoff in human genomics. High-coverage whole-genome sequencing offers the most comprehensive view of genetic variation but remains prohibitively expensive for many population studies. Genotyping arrays and exome sequencing are more affordable but either miss large portions of the genome or introduce bias by relying on variants selected primarily from European ancestry populations.
The BGE workflow integrates low-pass whole-genome sequencing at 1–4x coverage with deep exome sequencing at 30–40x coverage within a single library preparation and sequencing run on Illumina’s NovaSeqS4. The result is a unified dataset capable of supporting genome-wide association studies, rare variant discovery, copy number variant (CNV) detection, and polygenic analyses at approximately 28% of the cost of conventional 30x whole-genome sequencing.
The investigators validated the approach in more than 53,000 participants enrolled in the Populations Underrepresented in Mental Illness Associations Studies (PUMAS) Project, which includes African, African American, Hispanic/Latino, and Colombian cohorts. The scale and diversity of the study allowed the researchers to assess performance in populations that have historically been underrepresented in genomic research.
Imputed genotypes generated from BGE showed excellent agreement with Illumina Global Screening Array data, achieving concordance exceeding 95% for variants with minor allele frequencies above 1%. Importantly, performance remained consistent across multiple ancestry groups and local ancestry backgrounds, addressing one of the major limitations of conventional array-based genotyping.
The platform also demonstrated strong performance for clinically relevant structural variation. Using established computational pipelines, investigators achieved approximately 90% positive predictive value for protein-coding CNVs spanning three or more exons compared with deep whole-genome sequencing. In benchmarking studies, the method successfully detected all validated de novo coding CNVs in a reference autism cohort while maintaining low false-positive rates.
Beyond analytical performance, the study highlights potential operational advantages. By combining genome and exome sequencing into a single workflow, BGE simplifies laboratory processing, reduces the need for multiple assays, and minimizes sample attrition between sequencing platforms. These efficiencies could prove valuable for national biobanks, health system sequencing programs, and pharmaceutical research efforts that increasingly require genomic datasets from hundreds of thousands of participants.
The technology may also advance equity in precision medicine. Because low-pass genome sequencing does not depend on predefined variant content, it avoids many of the ascertainment biases associated with traditional genotyping arrays. The authors found that BGE captured substantially more coding and noncoding variants than array-based approaches while maintaining high-quality rare variant detection through deep exome coverage.
The researchers acknowledge that imputation performance remains influenced by the diversity of available reference panels, particularly for Indigenous American ancestry. However, as more globally representative reference datasets become available, they expect the accuracy of low-pass genome imputation to improve further.
As precision medicine increasingly depends on large, ancestrally diverse genomic datasets, technologies that balance cost, scalability, and comprehensive variant detection will be essential. BGE sequencing offers a practical alternative to deep whole-genome sequencing, enabling broader participation in genomic discovery while preserving much of the analytical power needed to identify clinically meaningful genetic variation.
The post Blended Genome–Exome Sequencing Slashes Costs Without Quality Loss appeared first on Inside Precision Medicine.
Autism service barriers for Latine children and their families: a participatory approach to adapting autism diagnostic care
IntroductionLatine children from families with limited English proficiency (LEP) experience barriers to timely autism diagnosis resulting in persistent health inequities. This participatory mixed-methods study examined these barriers and identified multi-level strategies to adapt diagnostic care models for Spanish-speaking Latine families.MethodsParticipants included twelve caregivers of thirteen autistic children with parent reported diagnosis of autism, twelve clinicians, and six care coordinators. All participants completed surveys and participated in qualitative interviews or focus groups.ResultsQuantitative findings revealed significant lag between caregiver’s first developmental concern and diagnosis, limited autism knowledge, and difficulty navigating care. Qualitative results highlighted systemic barriers, including clinician-patient language discordance, interpreter inaccuracies and quality variability, cultural stigma, and long waitlists. Clinicians reported challenges with communicating about autism with Spanish-speaking families and emphasized language and cultural differences as primary barriers. Caregivers described social isolation, mistrust of health systems, and emotional distress compounded by immigration-related stressors.DiscussionFindings underscore the need for structural adaptation of care approaches beyond translation services.
Parental broad autism phenotype traits and executive function in families of children with autism spectrum disorder
BackgroundParents of children with autism spectrum disorder (ASD) frequently exhibit subclinical Broad Autism Phenotype (BAP) traits, though their relationship with executive function (EF) remains underexplored. This study investigated associations between parental BAP traits and their EF performance.MethodsThe Broad Autism Phenotype Questionnaire (BAPQ) was used to assess the BAP traits in parents of children with ASD and parents of healthy children. Among them 20 of the high-BAP ASD parents with a total BAPQ score exceeding 3.55 and 20 of the parents of typically developing children completed executive function tests. The researchers utilized the flanker, 2-back, and Task-switching paradigm to examine their EF. Correlations analysis was used to analyze BAP-EF relationships.ResultsThe self-reported questionnaires indicated that parents of children with ASD had significantly higher BAPQ scores than non-ASD’s parents, with fathers scoring 41.21% versus 15% (χ2 = 31.628, p < 0.01), and mothers 26.25% versus 8.37% (χ2 = 25.764, p < 0.01). Parents of ASD children exhibited significantly prolonged reaction times on the Flanker task (528.95 ± 78.90 ms vs. 426.80 ± 18.40 ms, T = 15.639, p<0.01), with BAPQ total scores positively correlating with slower responses (R² = 0.2325, p = 0.0313). Paradoxically, they demonstrated accelerated 2-Back incongruent reaction times (537.60 ± 80.21 ms vs. 665.70 ± 137.17 ms, T = 6.715, p=0.001) but reduced accuracy (0.947 ± 0.037 vs. 0.983 ± 0.016, T = 16.875, p<0.01), where BAPQ again correlated with reaction times (R² = 0.2318, p = 0.0316). Crucially, these associations were absent in controls, and BAPQ scores showed no relationship with task accuracy in either group.ConclusionsBAP traits are associated with attentional control challenges (indexed by Flanker Task) and a maladaptive speed-accuracy tradeoffs during working memory demands.
AI-Based Reflective Parenting Simulation for Parents of Autistic Children
Conditions: Autism Spectrum Disorder
Interventions: Behavioral: AI-Based Reflective Parenting Simulation
Sponsors: University of Haifa
Not yet recruiting
Interventions: Behavioral: AI-Based Reflective Parenting Simulation
Sponsors: University of Haifa
Not yet recruiting
From spatial patterning to coordinated execution: a cross-system framework for autism spectrum disorder
Autism spectrum disorder (ASD) is characterized by differences in social communication and restricted or repetitive behaviors, yet converging evidence also points to altered neural timing, synchronization, and large-scale coordination despite largely preserved gross neuroanatomy. Parallel observations across non-neural systems, including functional gastrointestinal disturbances, minor anomalies in neural crest–derived tissues, and variation in epithelial patterning outcomes, raise the possibility of a broader vulnerability in coordination-dependent biological processes. Here, we propose a framework in which developmental systems distinguish between spatial patterning mechanisms that establish tissue geometry and a calcium-dependent execution layer that stabilizes coordinated behavior across time. Patterning systems, including planar cell polarity signaling, morphogen gradients, and neural crest guidance cues, specify directional organization and spatial relationships among cells. Their realization, however, requires intracellular processes capable of synchronizing cytoskeletal remodeling, adhesion dynamics, excitability, and metabolic coupling across cells and networks. Within this framework, intracellular Ca²+ signaling – and particularly endoplasmic reticulum Ca²+ release mediated by inositol 1,4,5-trisphosphate receptors (ITPRs) – represents a candidate mechanism for stabilizing coordinated execution across biological systems. Partial disruption of this coordination layer could degrade synchronization, propagation, and temporal integration without abolishing underlying structural organization. This perspective provides a potential basis for linking altered cortical synchronization with coordination-dependent processes in enteric function, neural crest development, and epithelial patterning outcomes observed in ASD.This framework is not proposed as a universal explanation for ASD, but as a testable organizing model for coordination-related phenotypes across systems. By distinguishing spatial developmental instruction from the mechanisms that stabilize coordinated execution, this perspective generates experimentally tractable predictions across cellular, organoid, and systems-level models and offers a unifying framework for investigating coordination-dependent biology in ASD.