Using visual attention estimation on videos for automated prediction of autism spectrum disorder and symptom severity in preschool children.
Ontology highlight
ABSTRACT:
SUBMITTER: de Belen RAJ
PROVIDER: S-EPMC10861059 | biostudies-literature | 2024
REPOSITORIES: biostudies-literature
Publications
Using visual attention estimation on videos for automated prediction of autism spectrum disorder and symptom severity in preschool children.
de Belen Ryan Anthony J RAJ Eapen Valsamma V Bednarz Tomasz T Sowmya Arcot A
PloS one 20240212 2
Atypical visual attention in individuals with autism spectrum disorders (ASD) has been utilised as a unique diagnosis criterion in previous research. This paper presents a novel approach to the automatic and quantitative screening of ASD as well as symptom severity prediction in preschool children. We develop a novel computational pipeline that extracts learned features from a dynamic visual stimulus to classify ASD children and predict the level of ASD-related symptoms. Experimental results dem ...[more]
Similar Datasets
Project description:Autism is widely believed to be a heterogeneous disorder; diagnosis is currently based solely on clinical criteria, although genetic, as well as environmental, influences are thought to be prominent factors in the etiology of most forms of autism. Our goal is to determine whether a predictive model based on single-nucleotide polymorphisms (SNPs) can predict symptom severity of autism spectrum disorder (ASD). We divided 118 ASD children into a mild/moderate autism group (n = 65) and a severe autism group (n = 53), based on the Childhood Autism Rating Scale (CARS). For each child, we obtained 29 SNPs of 9 ASD-related genes. To generate predictive models, we employed three machine-learning techniques: decision stumps (DSs), alternating decision trees (ADTrees), and FlexTrees. DS and FlexTree generated modestly better classifiers, with accuracy = 67%, sensitivity = 0.88 and specificity = 0.42. The SNP rs878960 in GABRB3 was selected by all models, and was related associated with CARS assessment. Our results suggest that SNPs have the potential to offer accurate classification of ASD symptom severity.
| S-EPMC3244507 | biostudies-literature
Project description:BackgroundEvidence suggests that there is a robust relationship between altered neuroanatomy and autistic symptoms in individuals with autism spectrum disorder (ASD). Social visual preference, which is regulated by specific brain regions, is also related to symptom severity. However, there were a few studies explored the potential relationships among brain structure, symptom severity, and social visual preference.MethodsThe current study investigated relationships among brain structure, social visual preference, and symptom severity in 43 children with ASD and 26 typically developing (TD) children (aged 2-6 years).ResultsSignificant differences were found in social visual preference and cortical morphometry between the two groups. Decreased percentage of fixation time in digital social images (%DSI) was negatively related to not only the thickness of the left fusiform gyrus (FG) and right insula, but also the Calibrated Severity Scores for the Autism Diagnostic Observation Schedule-Social Affect (ADOS-SA-CSS). Mediation analysis showed that %DSI partially mediated the relationship between neuroanatomical alterations (specifically, thickness of the left FG and right insula) and symptom severity.ConclusionThese findings offer initial evidence that atypical neuroanatomical alterations may not only result in direct effects on symptom severity but also lead to indirect effects on symptom severity through social visual preference. This finding enhances our understanding of the multiple neural mechanisms implicated in ASD.
| S-EPMC10311909 | biostudies-literature
Project description:ImportanceStereotypical motor movements (SMMs) are a form of restricted and repetitive behavior, which is a core symptom of autism spectrum disorder (ASD). Current quantification of SMM severity is extremely limited, with studies relying on coarse and subjective caregiver reports or laborious manual annotation of short video recordings.ObjectiveTo assess the utility of a new open-source AI algorithm that can analyze extensive video recordings of children and automatically identify segments with heterogeneous SMMs, thereby enabling their direct and objective quantification.Design, setting, and participantsThis retrospective cohort study included 241 children (aged 1.4 to 8.0 years) with ASD. Video recordings of 319 behavioral assessments carried out at the Azrieli National Centre for Autism and Neurodevelopment Research in Israel between 2017 and 2021 were extracted. Behavioral assessments included cognitive, language, and autism diagnostic observation schedule, 2nd edition (ADOS-2) assessments. Data were analyzed from October 2020 to May 2024.ExposuresEach assessment was recorded with 2 to 4 cameras, yielding 580 hours of video footage. Within these extensive video recordings, manual annotators identified 7352 video segments containing heterogeneous SMMs performed by different children (21.14 hours of video).Main outcomes and measuresA pose estimation algorithm was used to extract skeletal representations of all individuals in each video frame and was trained an object detection algorithm to identify the child in each video. The skeletal representation of the child was then used to train an SMM recognition algorithm using a 3 dimensional convolutional neural network. Data from 220 children were used for training and data from the remaining 21 children were used for testing.ResultsAmong 319 behavioral assessment recordings from 241 children (172 [78%] male; mean [SD] age, 3.97 [1.30] years), the algorithm accurately detected 92.53% (95% CI, 81.09%-95.10%) of manually annotated SMMs in our test data with 66.82% (95% CI, 55.28%-72.05%) precision. Overall number and duration of algorithm-identified SMMs per child were highly correlated with manually annotated number and duration of SMMs (r = 0.8; 95% CI, 0.67-0.93; P < .001; and r = 0.88; 95% CI, 0.74-0.96; P < .001, respectively).Conclusions and relevanceThis study suggests the ability of an algorithm to identify a highly diverse range of SMMs and quantify them with high accuracy, enabling objective and direct estimation of SMM severity in individual children with ASD.
| S-EPMC11393723 | biostudies-literature
Project description:Visual social attention is central to social functioning and learning and may act as a reinforcer. Social rivalry, which occurs when an individual is excluded from dyadic interactions, can promote interspecific learning by triggering attention. We applied it to an animal-assisted intervention, where the behaviour of ASD children was compared between an experimental (attention shift of the animal trainer from the dog-child to the dog only) and a control (attention maintained on the dyad) groups (study 1). The results show that ASD children are sensitive to the direction of (visual) social attention and may act, physically and visually, in order to regain it. When the animal trainer concentrated on the dog, the overall visual attention of the ASD children increased, suggesting a heightened awareness towards their environment. They oriented more towards the animal trainer and the dog, contrarily to the control group. The repetition of the procedure was even associated with increased joint attention with the animal trainer (study 2). Thus, ASD children do care about and seek human visual attention. They show an ability to adapt their social behaviour, which questions whether their known deficits in social competencies are hard wired or whether the deficits are in their expression.
| S-EPMC5577136 | biostudies-literature
Project description:Children with autism spectrum disorders (ASD) show atypical attention, particularly for social events. The new Multisensory Attention Assessment Protocol (MAAP) assesses fine-grained individual differences in attention disengagement, maintenance, and audiovisual matching for social and nonsocial events. We investigated the role of competing stimulation on attention, and relations with language and symptomatology in children with ASD and typical controls. Findings revealed: (1) the MAAP differentiated children with ASD from controls, (2) greater attention to social events predicted better language for both groups and lower symptom severity in children with ASD, (3) different pathways from attention to language were evident in children with ASD versus controls. The MAAP provides an ideal attention assessment for revealing diagnostic group differences and relations with outcomes.
| S-EPMC10065966 | biostudies-literature
Project description:ImportanceJoint attention, composed of complex behaviors, is an early-emerging social function that is deficient in children with autism spectrum disorder (ASD). Currently, no methods are available for objectively quantifying joint attention.ObjectiveTo train deep learning (DL) models to distinguish ASD from typical development (TD) and to differentiate ASD symptom severities using video data of joint attention behaviors.Design, setting, and participantsIn this diagnostic study, joint attention tasks were administered to children with and without ASD, and video data were collected from multiple institutions from August 5, 2021, to July 18, 2022. Of 110 children, 95 (86.4%) completed study measures. Enrollment criteria were 24 to 72 months of age and ability to sit with no history of visual or auditory deficits.ExposuresChildren were screened using the Childhood Autism Rating Scale. Forty-five children were diagnosed with ASD. Three types of joint attention were assessed using a specific protocol.Main outcomes and measuresCorrectly distinguishing ASD from TD and different levels of ASD symptom severity using the DL model area under the receiver operating characteristic curve (AUROC), accuracy, precision, and recall.ResultsThe analytical population consisted of 45 children with ASD (mean [SD] age, 48.0 [13.4] months; 24 [53.3%] boys) vs 50 with TD (mean [SD] age, 47.9 [12.5] months; 27 [54.0%] boys). The DL ASD vs TD models showed good predictive performance for initiation of joint attention (IJA) (AUROC, 99.6% [95% CI, 99.4%-99.7%]; accuracy, 97.6% [95% CI, 97.1%-98.1%]; precision, 95.5% [95% CI, 94.4%-96.5%]; and recall, 99.2% [95% CI, 98.7%-99.6%]), low-level response to joint attention (RJA) (AUROC, 99.8% [95% CI, 99.6%-99.9%]; accuracy, 98.8% [95% CI, 98.4%-99.2%]; precision, 98.9% [95% CI, 98.3%-99.4%]; and recall, 99.1% [95% CI, 98.6%-99.5%]), and high-level RJA (AUROC, 99.5% [95% CI, 99.2%-99.8%]; accuracy, 98.4% [95% CI, 97.9%-98.9%]; precision, 98.8% [95% CI, 98.2%-99.4%]; and recall, 98.6% [95% CI, 97.9%-99.2%]). The DL-based ASD symptom severity models showed reasonable predictive performance for IJA (AUROC, 90.3% [95% CI, 88.8%-91.8%]; accuracy, 84.8% [95% CI, 82.3%-87.2%]; precision, 76.2% [95% CI, 72.9%-79.6%]; and recall, 84.8% [95% CI, 82.3%-87.2%]), low-level RJA (AUROC, 84.4% [95% CI, 82.0%-86.7%]; accuracy, 78.4% [95% CI, 75.0%-81.7%]; precision, 74.7% [95% CI, 70.4%-78.8%]; and recall, 78.4% [95% CI, 75.0%-81.7%]), and high-level RJA (AUROC, 84.2% [95% CI, 81.8%-86.6%]; accuracy, 81.0% [95% CI, 77.3%-84.4%]; precision, 68.6% [95% CI, 63.8%-73.6%]; and recall, 81.0% [95% CI, 77.3%-84.4%]).Conclusions and relevanceIn this diagnostic study, DL models for identifying ASD and differentiating levels of ASD symptom severity were developed and the premises for DL-based predictions were visualized. The findings suggest that this method may allow digital measurement of joint attention; however, follow-up studies are necessary for further validation.
| S-EPMC10214037 | biostudies-literature
Project description:Study objectivesWhile caregiver-reported sleep disturbances are common in children and adolescents with autism spectrum disorder (['), few studies have measured objective sleep in ASD compared to controls, and their findings are mixed. We investigated (1) differences in sleep architecture, specifically slow-wave sleep (SWS) and rapid eye movement (REM) sleep, between ASD and typically developing controls (TD); and (2) if any observed differences in sleep were associated with core ASD symptoms.MethodsWe used ambulatory polysomnography (PSG) in 53 participants with ASD (ages 4-18) and 66 age-matched TD in their home sleeping environment. The primary outcome measures were SWS and REM sleep. Core behavioral ASD symptoms were assessed using the Autism Diagnostic Interview-Revised (ADI-R). Spectral power bands during sleep, and additional behavioral measures, were examined in exploratory analyses.ResultsCompared to TD, participants with ASD exhibited a higher SWS ratio and lower REM sleep ratio. Within the ASD group, higher SWS was associated with more severe symptoms on the Restricted, Repetitive, and Stereotyped Behaviors subscale of the ADI-R. No association was observed between REM sleep ratio and any ASD symptom.ConclusionsIncreased SWS and reduced REM sleep ratio differentiated ASD from TD. However, only increased SWS was associated with more severe core ASD symptoms. Increased SWS may reflect neuronal immaturity specific to ASD in this age group. These findings may inform the underlying mechanisms of clinical symptoms observed in children and adolescents with ASD.
| S-EPMC9995925 | biostudies-literature
Project description:The neurobiology of heterogeneous neurodevelopmental disorders such as autism spectrum disorders (ASD) are still unclear. Despite extensive efforts, most findings are difficult to reproduce due to high levels of individual variance in phenotypic expression. To quantify individual differences in brain morphometry in ASD, we implemented a novel subject-level, distance-based method on subject-specific attributes. In a large multi-cohort sample, each subject with ASD (n = 100; n = 84 males; mean age: 11.43 years; mean IQ: 110.58) was strictly matched to a control participant (n = 100; n = 84 males; mean age: 11.43 years; mean IQ: 110.70). Intrapair Euclidean distance of MRI brain morphometry and symptom severity measures (Social Responsiveness Scale) were entered into a regularised machine learning pipeline for feature selection, with rigorous out-of-sample validation and permutation testing. Subject-specific structural morphometry features significantly predicted individual variation in ASD symptom severity (19 cortical thickness features, p = 0.01, n = 5000 permutations; 10 surface area features, p = 0.006, n = 5000 permutations). Findings remained robust across subjects and were replicated in validation samples. Identified cortical regions implicate key hubs of the salience and default mode networks as neuroanatomical features of social impairment in ASD. Present results highlight the importance of subject-level markers in ASD, and offer an important step forward in understanding the neurobiology of heterogeneous disorders.
| S-EPMC6617442 | biostudies-literature
Project description:People with autism spectrum disorders (ASD) have pervasive impairments in social interactions, a diagnostic component that may have its roots in atypical social motivation and attention. One of the brain structures implicated in the social abnormalities seen in ASD is the amygdala. To further characterize the impairment of people with ASD in social attention, and to explore the possible role of the amygdala, we employed a series of visual search tasks with both social (faces and people with different postures, emotions, ages, and genders) and non-social stimuli (e.g., electronics, food, and utensils). We first conducted trial-wise analyses of fixation properties and elucidated visual search mechanisms. We found that an attentional mechanism of initial orientation could explain the detection advantage of non-social targets. We then zoomed into fixation-wise analyses. We defined target-relevant effects as the difference in the percentage of fixations that fell on target-congruent vs. target-incongruent items in the array. In Experiment 1, we tested 8 high-functioning adults with ASD, 3 adults with focal bilateral amygdala lesions, and 19 controls. Controls rapidly oriented to target-congruent items and showed a strong and sustained preference for fixating them. Strikingly, people with ASD oriented significantly less and more slowly to target-congruent items, an attentional deficit especially with social targets. By contrast, patients with amygdala lesions performed indistinguishably from controls. In Experiment 2, we recruited a different sample of 13 people with ASD and 8 healthy controls, and tested them on the same search arrays but with all array items equalized for low-level saliency. The results replicated those of Experiment 1. In Experiment 3, we recruited 13 people with ASD, 8 healthy controls, 3 amygdala lesion patients and another group of 11 controls and tested them on a simpler array. Here our group effect for ASD strongly diminished and all four subject groups showed similar target-relevant effects. These findings argue for an attentional deficit in ASD that is disproportionate for social stimuli, cannot be explained by low-level visual properties of the stimuli, and is more severe with high-load top-down task demands. Furthermore, this deficit appears to be independent of the amygdala, and not evident from general social bias independent of the target-directed search.
| S-EPMC4317264 | biostudies-literature
Project description:BackgroundAutism spectrum disorder (ASD) is a heterogeneous neurodevelopmental condition. The degree to which the brain development in ASD deviates from typical brain development, and how this deviation relates to observed behavioral outcomes at the individual level are not well-studied. We hypothesize that the degree of deviation from typical brain development of an individual with ASD would relate to observed symptom severity.MethodsThe developmental changes in anatomical (cortical thickness, surface area, and volume) and diffusion metrics (fractional anisotropy and apparent diffusion coefficient) were compared between a sample of ASD (n = 247) and typically developing children (TDC) (n = 220) aged 6-25. Machine learning was used to predict age (brain age) from these metrics in the TDC sample, to define a normative model of brain development. This model was then used to compute brain age in the ASD sample. The difference between chronological age and brain age was considered a developmental deviation index (DDI), which was then correlated with ASD symptom severity.ResultsMachine learning model trained on all five metrics accurately predicted age in the TDC (r = 0.88) and the ASD (r = 0.85) samples, with dominant contributions to the model from the diffusion metrics. Within the ASD group, the DDI derived from fractional anisotropy was correlated with ASD symptom severity (r = - 0.2), such that individuals with the most advanced brain age showing the lowest severity, and individuals with the most delayed brain age showing the highest severity.LimitationsThis work investigated only linear relationships between five specific brain metrics and only one measure of ASD symptom severity in a limited age range. Reported effect sizes are moderate. Further work is needed to investigate developmental differences in other age ranges, other aspects of behavior, other neurobiological measures, and in an independent sample before results can be clinically applicable.ConclusionsFindings demonstrate that the degree of deviation from typical brain development relates to ASD symptom severity, partially accounting for the observed heterogeneity in ASD. Our approach enables characterization of each individual with reference to normative brain development and identification of distinct developmental subtypes, facilitating a better understanding of developmental heterogeneity in ASD.
| S-EPMC6907209 | biostudies-literature