AI-assisted early screening, diagnosis, and intervention for autism in young children.

Emotion dysregulation (ED) is common and severe in older autistic youth, but is rarely the focus of early autism screening or intervention. Moreover, research characterizing ED in the preschool years (when autism is typically diagnosed) is limited. This study aimed to characterize ED in autistic children by examining (1) prevalence and severity of ED as compared to children without an autism diagnosis; and (2) correlates of ED in autistic children. A sample of 1864 parents (Mean child age = 4.21 years, SD = 1.16 years; 37% female) of 2-5 year-old children with (1) autism; (2) developmental concerns, but no autism; and (3) no developmental concerns or autism completed measures via an online questionnaire. ED was measured using the Emotion Dysregulation Inventory-Young Child, a parent report measure characterizing ED across two dimensions: Reactivity (fast, intense emotional reactions) and dysphoria (low positive affect, sadness, unease). Autistic preschoolers, compared to peers without developmental concerns, had more severe ED (+1.12 SD for reactivity; +0.60 SD for dysphoria) and were nearly four and three times more likely to have clinically significant reactivity and dysphoria, respectively. Autistic traits, sleep problems, speaking ability, and parent depression were the strongest correlates of ED in the autism sample. While more work is needed to establish the prevalence, severity, and correlates of ED in young autistic children, this study represents an important first step. Results highlight a critical need for more high-quality research in this area as well as the potential value of screening and intervention for ED in young autistic children.

Starting early in life, autistics are characterized as having atypical facial expressions, as well as decreased positive and increased negative affect. The literature on autistic facial expressions remains small, however, with disparate methods and results suggesting limited understanding of common autistic emotions. Furthermore, unlike non-autistics’ emotions, autistics’ emotions have been assessed without considering this population’s characteristics. In this study, the valence of young children’s facial expressions was thus rated as positive, negative, neutral, or “unknown”—a term for perceived emotions observers do not understand. Facial expressions were assessed using the Montreal Stimulating Play Situation, a context incorporating potential autistic interests. Comparing 37 autistic and 39 typical young (27–56 months) age-matched children, we found no group differences in expressed positive, negative, and neutral emotions. We did find differences in unknown emotions, which were unique to the autistic group. Preliminary data also showed that autistic children’s repetitive behaviors co-occurred with positive, neutral, and unknown emotions, but not with negative emotions. In a novel context that considers their characteristics, we did not find decreased positive or increased negative emotions in young autistic children. Instead, they uniquely expressed emotions perceived as unknown, showing the need to improve our understanding of their full emotional repertoire.Lay abstractAutistic people are believed to have emotions that are too negative and not positive enough, starting early in life. Their facial expressions are also persistently judged to be unusual, as reflected in criteria used to identify autism. But it is possible that common autistic facial expressions are poorly understood by observers, as suggested by a range of findings from research. Another issue is that autistic emotions have always been assessed in contexts suited to non-autistics. In our study, the facial expressions of young autistic and typical children were rated as positive, negative, neutral, or “unknown”—a category we created for emotions that observers notice but do not understand. These emotions were assessed using a context suited to autistic children, including objects of potential interest to them. We found that in this context, autistic and typical children did not differ in positive, negative, or neutral facial emotions. They did differ in unknown emotions, which were found only in autistic children. We also found that repetitive behaviors in autistic children co-occurred with positive, neutral, and unknown emotions, but not with negative emotions. In a context which suits their characteristics, autistic children do not show emotions that are too negative or not positive enough. They do show emotions perceived as unknown, which means we need to improve our understanding of their full emotional repertoire.

Autism Spectrum Disorder (ASD or Autism) is a neurodevelopmental disorder that is characterized by challenges in social communication skills and the presence of restricted and repetitive behaviors during early childhood. ASD poses a significant public health challenge with increasing prevalence rates worldwide. Early diagnosis and intervention are critical for improving outcomes in children with ASD. However, current diagnostic methods often involve subjective assessments and are time-consuming. Currently, there are no known biomarkers for ASD, and the diagnosis is based on phenotypic manifestations observed by trained clinicians over time. Additionally, the heterogeneity of Autism and associated co-occurring conditions pose further challenges for screening and early detection. Recent advances in Artificial Intelligence (AI) and Machine Learning (ML) are transforming ASD screening and diagnosis. These computational technologies are capable of analyzing complex datasets and multiple modalities, including multi-omics, brain images, behavior assessments, medical and background information, and registry data to identify patterns that may not be evident to clinicians or parents. This article reviews recent developments in the application of AI/ML for ASD screening and early diagnosis. It also covers the use of AI/ML in understanding the biological underpinnings of ASD.

Early signs of autism can be identified in children as young as 6–9 months; however, screening tools to identify characteristics of autism in young children are underutilized by pediatricians. This qualitative study aimed to 1) understand the role of occupational therapists (OTs) in early intervention teams when identifying and intervening with infants and toddlers demonstrating early markers of autism, and 2) determine the readiness and capability of OTs within early intervention to utilize autism screening tools in practice. Two semi-structured 90-minute focus groups were conducted with 13 OTs with current or past work experience in early intervention settings across Los Angeles, California. Participants expressed pride in their versatile role on early intervention teams; however, they had mixed feelings about the value of formal autism screening. Even when they were confident about their ability to detect early autism signs, participants cited numerous barriers related to knowledge of screening, stigma related to autism, and reliance on other providers such as pediatricians. These qualitative findings illuminate a need for mitigating expressed barriers to service delivery, bolstering education on screening procedures, and capitalizing on the adaptability of OTs in early intervention practice in order to advance the role of OTs in initiating the early autism screening process.

Autism in the UK for Birth Cohorts 1988–2001

Autistic children and children with attention-deficit/hyperactivity disorder (ADHD) may have more frequent visits to the emergency department (ED). We aim to identify the primary reasons for ED visits among autistic children and children with ADHD, compared to a random sample of visits. Using 2008 to 2017 Nationwide Emergency Department Sample data, we assessed the most frequent primary diagnoses for ED visits among children (ages 3-12 and 13-18 years, separately) (1) with an autism diagnosis, (2) with ADHD, and (3) a random sample (1 000 000 visits). We regressed primary reasons for visits on autism or ADHD diagnosis, controlling for individual characteristics, to assess the odds of presenting for these reasons. Although the 10 most frequent diagnoses among the random sample were physical health conditions, autistic children and children with ADHD often presented for psychiatric conditions. Older children with autism and with ADHD more frequently presented for mood disorders (10%-15% of visits; odds ratios [ORs] = 5.2-8.5) and intentional self-harm (ORs = 3.2-5.0). Younger children with ADHD more commonly presented with mood disorders (6.6% of visits; OR = 18.3) and younger autistic children more often presented with attention-deficit, conduct, and disruptive behavior disorders (9.7% of visits; OR = 9.7). Autistic children and children with ADHD have higher odds of presenting to the ED for psychiatric conditions than a random sample, including for self-harm. Clinicians should treat these populations sensitively, recognize and assess the risk for self-harm, and facilitate continuing psychiatric care.

Previous research links resting frontal gamma power to key developmental outcomes in young neurotypical (NT) children and infants at risk for language impairment. However, it remains unclear whether gamma power is specifically associated with language or with more general cognitive abilities among young children diagnosedwith autism spectrum disorder (ASD). The current study evaluates differences in resting frontal gamma power between young autistic and NT children and tests whether gamma power is uniquely associated with individual differences in expressive language, receptive language and non-verbal cognitive abilities in autistic and NT children. Participants included 48 autistic children and 58 age- and sex-matched NT children (ages 22-60months). Baseline electroencephalography (EEG) recordings were acquired from each participant. Children also completed the Mullen Scales of Early Learning (MSEL). We found thatfrontal gamma power at rest did not differ between autistic and NT children. Among autistic children, reduced frontal gamma power was significantly associated with both higher expressive language skills and higher non-verbal cognitive skills, controlling for age and sex. The interaction between frontal gamma power and diagnostic status no longer explained unique variance in expressive language skills after controlling for variance associated with non-verbal cognitive skills across autistic and NT children. Together, these findings suggest that reduced gamma power is associated with both better expressive language and non-verbal cognitive skills among young autistic children. Moreover, associations between high frequency neural activity and cognition are not specific to verbal abilities but reflect neural mechanisms associated with general higher-order cognitive abilities in ASD.

Altered patterns of visual social attention preference detected using eye-tracking and a variety of different paradigms are increasingly proposed as sensitive biomarkers for autism spectrum disorder. However, few eye-tracking studies have compared the relative efficacy of different paradigms to discriminate between autistic compared with typically developing children and their sensitivity to specific symptoms. To target this issue, the current study used three common eye-tracking protocols contrasting social versus nonsocial stimuli in young (2-7 years old) Chinese autistic (n = 35) and typically developing (n = 34) children matched for age and gender. Protocols included dancing people versus dynamic geometrical images, biological motion (dynamic light point walking human or cat) versus nonbiological motion (scrambled controls), and child playing with toy versus toy alone. Although all three paradigms differentiated autistic and typically developing children, the dancing people versus dynamic geometry pattern paradigm was the most effective, with autistic children showing marked reductions in visual preference for dancing people and correspondingly increased one for geometric patterns. Furthermore, this altered visual preference in autistic children was correlated with the Autism Diagnostic Observation Schedule social affect score and had the highest discrimination accuracy. Our results therefore indicate that decreased visual preference for dynamic social stimuli may be the most effective visual attention-based paradigm for use as a biomarker for autism in Chinese children. Clinical trial ID: NCT03286621 (clinicaltrials.gov); Clinical trial name: Development of Eye-tracking Based Markers for Autism in Young Children. Autism Res 2019, 12: 1529-1540. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: Eye-tracking measures may be useful in aiding diagnosis and treatment of autism, although it is unclear which specific tasks are optimal. Here we compare the ability of three different social eye-gaze tasks to discriminate between autistic and typically developing young Chinese children and their sensitivity to specific autistic symptoms. Our results show that a dynamic task comparing visual preference for social (individuals dancing) versus geometric patterns is the most effective both for diagnosing autism and sensitivity to its social affect symptoms.

The ability to identify children who require specialist assessment for the possibility of autism at as early an age as possible has become a growing area of research. A number of measures have been developed as potential screening tools for autism. The reliability and validity of one of these measures for screening for autism in young children with developmental problems was evaluated. The parents of 207 children aged 20-51 months completed the Developmental Checklist-Early Screen (DBC-ES), prior to their child undergoing assessment. Good interrater agreement and internal consistency was found, along with significant correlations with a clinician completed measure of autism symptomatology. High sensitivity was found, with lower specificity for the originally proposed 17-item screening tool and a five-item version.

Recent theories propose that domain-general deficits in prediction (i.e., the ability to anticipate upcoming information) underlie the behavioral characteristics associated with autism spectrum disorder (ASD). If these theories are correct, autistic children might be expected to demonstrate difficulties on linguistic tasks that rely on predictive processing. Previous research has largely focused on older autistic children and adolescents with average language and cognition. The present study used an eye-gaze task to evaluate predictive language processing among 3- to 4-year-old autistic children (n= 34) and 1.5- to 3-year-old, language-matched neurotypical (NT) children (n= 34). Children viewed images (e.g., a cake and a ball) and heard sentences with informative verbs (e.g., Eat the cake) or neutral verbs (e.g., Find the cake). Analyses of children's looking behaviors indicated that young autistic children, like their language-matched NT peers, engaged in predictive language processing. Regression results revealed a significant effect of diagnostic group, when statistically controlling for age differences. The NT group displayed larger difference scores between the informative and neutral verb conditions (in looks to target nouns) compared to the ASD group. Receptive language measures were predictive of looking behavior across time for both groups, such that children with stronger language skills were more efficient in making use of informative verbs to process upcoming information. Taken together, these results suggest that young autistic children can engage in predictive processing though further research is warranted to explore the developmental trajectory relative to NT development. LAY SUMMARY: This study found that 3- to 4-year-old autistic children and younger, language-matched neurotypical (NT) children both used verbs to predict upcoming nouns in sentences like "Eat the cake." For both autistic and NT children, those with stronger language skills were able to predict upcoming nouns more quickly.

Sleep problems and behavioural challenges are examined rarely in very young autistic children. We investigated sleep in 173 autistic children, close to their autism diagnosis (Mage = 2.49 years at diagnosis), focussing on sleep's relationship with daytime behaviour and vice versa, and examining if there were specific sleep problem-behaviour relationships in this very young cohort. Caregivers of 173 autistic children (Mage = 2.58 years at data collection) provided information on their children's sleep (CSHQ; written descriptions) and behaviour (BASC-3, VABS-3). Demographic, ADOS-2 and developmental (MSEL) information were also available. Using parents' written descriptions and normative sleep data, children were categorized as severe (SSP) or typical (TSP) problems sleepers, or good sleepers (NSP) (Roussis et al., 2021). Kruskal-Wallis, correlation and regression analyses examined sleep and behavioural relationships among these three sleep groups. Most children (71.9%) had two or more sleep problems. The TSP and NSP groups did not differ on behaviour, showing significantly less hyperactivity, aggression, attention, and atypicality than the SSP group. Night waking/parasomnias, daytime alertness, and sleep initiation/duration for both sleep problem groups strongly correlated with increased hyperactivity, attention, anxiety, depression, and aggression. Sleep explained 38.4% of variance and 61.8% variance in behaviour, and behaviour explained 22.4% of variance and 32.1% of variance in sleep, for the TSP and SSP groups respectively. Reciprocal relationships between sleep and behaviour in autism emphasise the importance of addressing sleep problems in young autistic children, at the time of diagnosis, as they can negatively impact behaviour and well-being.

Restricted and repetitive behavior (RRB) is a core diagnostic feature of autism spectrum disorder (ASD). Previous research shows that RRB is prevalent early in life and observed in neurotypical development as well. Less is known, however, about early RRB patterns, developmental trajectories, and the relation to outcomes for autistic children. The purpose of this systematic review was to synthesize findings from studies examining RRB in autistic children from birth through age 3. A detailed protocol was designed a priori based on PRISMA guidelines for systematic reviews. From the published literature, 41 peer reviewed journal articles were identified and included in this review. Our synthesis of the literature suggests that differences in RRB are evident prior to age 2 in children with or who go onto be diagnosed with autism. These differences were evident for both frequency and intensity of RRB across multiple topographies. There were mixed results regarding functional outcomes associated with early RRB, such as cognitive and adaptive behavior, though relations appeared to become stronger as children aged beyond toddlerhood. Notably, level of RRB appears unrelated to autism severity in young autistic children. A wide range of RRB have been reported to be elevated in autistic children during the first years of life, including repetitive motor behaviors, atypical sensory behaviors, insistence on sameness (IS), and self-injurious behaviors (SIBs). In contrast to studies of older children, RRB in very young autistic children do not appear to be associated with functional outcomes but may be valuable to include in early screening efforts.Systematic review registrationhttps://osf.io/huzf3, unique identifier: doi: 10.17605/OSF.IO/HUZF3.

Autism spectrum disorder (ASD) is a neurological illness characterized by challenges with repetitive tasks, social interaction, and communication. Even if genetics is the primary cause, early detection is vital, and using ML presents a promising way to diagnose the condition more quickly and affordably. In an effort to improve and automate the diagnostic process, this research uses a variety of machine-learning techniques to pinpoint important ASD features. With the rapid growth of artificial intelligence techniques, it has become possible to use intelligent methods to carry out early large-scale senseless screening and diagnosis of autism. In the future, research should focus on building an intelligent medical screening and diagnosis system for autism patients, developing screening tools and constructing an intelligent identification model for patients that integrates multimode data.

"Hot" or reward-based executive function describes the regulatory skills needed to suppress or delay actions in emotionally salient contexts. These delay-based executive function skills impact social development, mental health, and academic achievement. Accumulating evidence indicates that autistic children (3 years or older) show reduced delay-based executive function relative to neurotypical counterparts. The primary aim of this study was to determine whether these findings extend to younger children (younger than 3 years). Our secondary aim was to determine whether the strategies employed during delay-based executive function tasks differed between autistic and neurotypical toddlers, to understand why autistic children often experience difficulty in this domain. A behavioral battery was administered to measure delay-based executive function in autistic and neurotypical children, aged 2 and 4 years. Consistent with evidence in older children, delay-based executive function was reduced in autistic toddlers. Autistic 2-year-olds waited less during tasks that utilized food rewards, whereas autistic 4-year-olds waited less during tasks using both food- and non-food-based incentives. Autistic children also used significantly less adaptive strategies during tasks. These results are the first to indicate diagnostic differences in delay-based executive function among children as young as 2 years and may inform interventions that target these skills to improve related developmental outcomes.Lay Abstract"Hot" executive function involves the ability to control actions when emotions are involved. For example, a situation when an individual must resist a temptation requires hot executive function. These skills are important for social growth, mental health, and doing well in school. Research shows that autistic children over 3 years of age are less likely to use these skills compared to other children. This study examined whether autistic children under 3 years of age show similar difficulties. We also examined whether autistic children use different strategies than neurotypical children. To find out, we asked both autistic and neurotypical children, ages 2 and 4 years, to complete tasks that required them to delay their responses. The study found that, like older autistic children, younger autistic children also delayed their responses less than neurotypical children. Autistic 2-year-olds waited less for rewards, like food, compared to their neurotypical peers. Similarly, autistic 4-year-olds waited less for both food and other types of rewards, compared to their neurotypical peers. Relative to their neurotypical peers, autistic children also used fewer effective strategies during these tasks. These findings suggest that even very young autistic children have differences in impulse control, which might help in creating better support and interventions for them.

ObjectiveTo explore the application of quantitative magnetic resonance imaging in the diagnosis of autism in children.MethodsSixty autistic children aged 2–3 years and 60 age- and sex-matched healthy children participated in the study. All the children were scanned using head MRI conventional sequences, 3D-T1, diffusion kurtosis imaging (DKI), enhanced T2*- weighted magnetic resonance angiography (ESWAN) and 3D-pseudo continuous Arterial Spin-Labeled (3D-pcASL) sequences. The quantitative susceptibility mapping (QSM), cerebral blood flow (CBF), and brain microstructure of each brain area were compared between the groups, and correlations were analyzed.ResultsThe iron content and cerebral blood flow in the frontal lobe, temporal lobe, hippocampus, caudate nucleus, substantia nigra, and red nucleus of the study group were lower than those in the corresponding brain areas of the control group (P < 0.05). The mean kurtosis (MK), radial kurtosis (RK), and axial kurtosis (AK) values of the frontal lobe, temporal lobe, putamen, hippocampus, caudate nucleus, substantia nigra, and red nucleus in the study group were lower than those of the corresponding brain areas in the control group (P < 0.05). The mean diffusivity (MD) and fractional anisotropy of kurtosis (FAK) values of the frontal lobe, temporal lobe and hippocampus in the control group were lower than those in the corresponding brain areas in the study group (P < 0.05). The values of CBF, QSM, and DKI in frontal lobe, temporal lobe and hippocampus could distinguish ASD children (AUC > 0.5, P < 0.05), among which multimodal technology (QSM, CBF, DKI) had the highest AUC (0.917) and DKI had the lowest AUC (0.642).ConclusionQuantitative magnetic resonance imaging (including QSM, 3D-pcASL, and DKI) can detect abnormalities in the iron content, cerebral blood flow and brain microstructure in young autistic children, multimodal technology (QSM, CBF, DKI) could be considered as the first choice of imaging diagnostic technology.Clinical Trial Registration[http://www.chictr.org.cn/searchprojen.aspx], identifier [ChiCTR2000029699].