Jena Daniels

The potential of accelerating early detection of autism through content analysis of YouTube videos.

Abstract Autism is on the rise, with 1 in 88 children receiving a diagnosis in the United States, yet the process for diagnosis remains cumbersome and time consuming. Research has shown that home videos of children can help increase the accuracy of diagnosis. However the use of videos in the diagnostic process is uncommon. In the present study, we assessed the feasibility of applying a gold-standard diagnostic instrument to brief and unstructured home videos and tested whether video analysis can enable more rapid detection of the core features of autism outside of clinical environments. We collected 100 public videos from YouTube of children ages 1–15 with either a self-reported diagnosis of an ASD (N = 45) or not (N = 55). Four non-clinical raters independently scored all videos using one of the most widely adopted tools for behavioral diagnosis of autism, the Autism Diagnostic Observation Schedule-Generic (ADOS). The classification accuracy was 96.8%, with 94.1% sensitivity and 100% specificity, the inter-rater correlation for the behavioral domains on the ADOS was 0.88, and the diagnoses matched a trained clinician in all but 3 of 22 randomly selected video cases. Despite the diversity of videos and non-clinical raters, our results indicate that it is possible to achieve high classification accuracy, sensitivity, and specificity as well as clinically acceptable inter-rater reliability with nonclinical personnel. Our results also demonstrate the potential for video-based detection of autism in short, unstructured home videos and further suggests that at least a percentage of the effort associated with detection and monitoring of autism may be mobilized and moved outside of traditional clinical environments.

A Wearable Social Interaction Aid for Children with Autism

Over 1 million children under the age of 17 in the US have been identified with Autism Spectrum Disorder (ASD). These children struggle to recognize facial expressions, make eye contact, and engage in social interactions. Gaining these skills requires intensive behavioral interventions that are often expensive, difficult to access, and inconsistently administered.nWe have developed a system to automate facial expression recognition that runs on wearable glasses and delivers real time social cues, with the goal of creating a behavioral aid for children with ASD that maximizes behavioral feedback while minimizing the distractions to the child. This paper describes the design of our system and interface decisions resulting from initial observations gathered during multiple preliminary trials.

Superpower glass: delivering unobtrusive real-time social cues in wearable systems

We have developed a system for automatic facial expression recognition, which runs on Google Glass and delivers real-time social cues to the wearer. We evaluate the system as a behavioral aid for children with Autism Spectrum Disorder (ASD), who can greatly benefit from real-time non-invasive emotional cues and are more sensitive to sensory input than neurotypically developing children. In addition, we present a mobile application that enables users of the wearable aid to review their videos along with auto-curated emotional information on the video playback bar. This integrates our learning aid into the context of behavioral therapy. Expanding on our previous work describing in-lab trials, this paper presents our system and application-level design decisions in depth as well as the interface learnings gathered during the use of the system by multiple children with ASD in an at-home iterative trial.

SuperpowerGlass: A Wearable Aid for the At-Home Therapy of Children with Autism

We have developed a system for automatic facial expression recognition running on Google Glass, delivering real-time social cues to children with Autism Spectrum Disorder (ASD). The system includes multiple mechanisms to engage children and their parents, who administer this technology within the home. We completed an at-home design trial with 14 families that used the learning aid over a 3-month period. We found that children with ASD generally respond well to wearing the system at home and opt for the most expressive feedback choice. We further evaluated app usage, facial engagement, and model accuracy. We found that the device can act as a powerful training aid when used periodically in the home, that interactive video content from wearable therapy sessions should be augmented with sufficient context about the content to produce long-term engagement, and that the design of wearable systems for children with ASD should be heavily dependent on the functioning level of the child. We contribute general design implications for developing wearable aids used by children with ASD and other behavioral disorders as well as their parents during at-home parent-administered therapy sessions.

Crowdsourced validation of a machine-learning classification system for autism and ADHD

Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) together affect >10% of the children in the United States, but considerable behavioral overlaps between the two disorders can often complicate differential diagnosis. Currently, there is no screening test designed to differentiate between the two disorders, and with waiting times from initial suspicion to diagnosis upwards of a year, methods to quickly and accurately assess risk for these and other developmental disorders are desperately needed. In a previous study, we found that four machine-learning algorithms were able to accurately (area under the curve (AUC)>0.96) distinguish ASD from ADHD using only a small subset of items from the Social Responsiveness Scale (SRS). Here, we expand upon our prior work by including a novel crowdsourced data set of responses to our predefined top 15 SRS-derived questions from parents of children with ASD (n=248) or ADHD (n=174) to improve our model’s capability to generalize to new, ‘real-world’ data. By mixing these novel survey data with our initial archival sample (n=3417) and performing repeated cross-validation with subsampling, we created a classification algorithm that performs with AUC=0.89±0.01 using only 15 questions.

Comorbid Analysis of Genes Associated with Autism Spectrum Disorders Reveals Differential Evolutionary Constraints

The burden of comorbidity in Autism Spectrum Disorder (ASD) is substantial. The symptoms of autism overlap with many other human conditions, reflecting common molecular pathologies suggesting that cross-disorder analysis will help prioritize autism gene candidates. Genes in the intersection between autism and related conditions may represent nonspecific indicators of dysregulation while genes unique to autism may play a more causal role. Thorough literature review allowed us to extract 125 ICD-9 codes comorbid to ASD that we mapped to 30 specific human disorders. In the present work, we performed an automated extraction of genes associated with ASD and its comorbid disorders, and found 1031 genes involved in ASD, among which 262 are involved in ASD only, with the remaining 779 involved in ASD and at least one comorbid disorder. A pathway analysis revealed 13 pathways not involved in any other comorbid disorders and therefore unique to ASD, all associated with basal cellular functions. These pathways differ from the pathways associated with both ASD and its comorbid conditions, with the latter being more specific to neural function. To determine whether the sequence of these genes have been subjected to differential evolutionary constraints, we studied long term constraints by looking into Genomic Evolutionary Rate Profiling, and showed that genes involved in several comorbid disorders seem to have undergone more purifying selection than the genes involved in ASD only. This result was corroborated by a higher dN/dS ratio for genes unique to ASD as compare to those that are shared between ASD and its comorbid disorders. Short-term evolutionary constraints showed the same trend as the pN/pS ratio indicates that genes unique to ASD were under significantly less evolutionary constraint than the genes associated with all other disorders.

Exploratory study examining the at-home feasibility of a wearable tool for social-affective learning in children with autism

Although standard behavioral interventions for autism spectrum disorder (ASD) are effective therapies for social deficits, they face criticism for being time-intensive and overdependent on specialists. Earlier starting age of therapy is a strong predictor of later success, but waitlists for therapies can be 18 months long. To address these complications, we developed Superpower Glass, a machine-learning-assisted software system that runs on Google Glass and an Android smartphone, designed for use during social interactions. This pilot exploratory study examines our prototype tool’s potential for social-affective learning for children with autism. We sent our tool home with 14 families and assessed changes from intake to conclusion through the Social Responsiveness Scale (SRS-2), a facial affect recognition task (EGG), and qualitative parent reports. A repeated-measures one-way ANOVA demonstrated a decrease in SRS-2 total scores by an average 7.14 points (F(1,13) = 33.20, p = <.001, higher scores indicate higher ASD severity). EGG scores also increased by an average 9.55 correct responses (F(1,10) = 11.89, p = <.01). Parents reported increased eye contact and greater social acuity. This feasibility study supports using mobile technologies for potential therapeutic purposes.

Feasibility Testing of a Wearable Behavioral Aid for Social Learning in Children with Autism

BACKGROUND Recent advances in computer vision and wearable technology have created an opportunity to introduce mobile therapy systems for autism spectrum disorders (ASD) that can respond to the increasing demand for therapeutic interventions; however, feasibility questions must be answered first. OBJECTIVE We studied the feasibility of a prototype therapeutic tool for children with ASD using Google Glass, examining whether children with ASD would wear such a device, if providing the emotion classification will improve emotion recognition, and how emotion recognition differs between ASD participants and neurotypical controls (NC). METHODS We ran a controlled laboratory experiment with 43 children: 23 with ASD and 20 NC. Children identified static facial images on a computer screen with one of 7 emotions in 3 successive batches: the first with no information about emotion provided to the child, the second with the correct classification from the Glass labeling the emotion, and the third again without emotion information. We then trained a logistic regression classifier on the emotion confusion matrices generated by the two information-free batches to predict ASD versus NC. RESULTS All 43 children were comfortable wearing the Glass. ASD and NC participants who completed the computer task with Glass providing audible emotion labeling (n = 33) showed increased accuracies in emotion labeling, and the logistic regression classifier achieved an accuracy of 72.7%. Further analysis suggests that the ability to recognize surprise, fear, and neutrality may distinguish ASD cases from NC. CONCLUSION This feasibility study supports the utility of a wearable device for social affective learning in ASD children and demonstrates subtle differences in how ASD and NC children perform on an emotion recognition task.

Crowdsourced study of children with autism and their typically developing siblings identifies differences in taxonomic and predicted function for stool-associated microbes using exact sequence variant analysis.

Background The existence of a link between the gut microbiome and autism spectrum disorder (ASD) is well established in mice, but in human populations efforts to identify microbial biomarkers have been limited due to problems stratifying participants within the broad phenotype of ASD and a lack of appropriately matched controls. To overcome these limitations and investigate the relationship between ASD and the gut microbiome, we ran a crowdsourced study of families 2-7 year old sibling pairs, where one child of the pair had a diagnosis of ASD and the other child did not. Methods Parents of age-matched sibling pairs electronically consented and completed study procedures via a secure web portal (microbiome.stanford.edu). Parents collected stool samples from each child, responded to behavioral questionnaires about the ASD child’s typical behavior, and whenever possible provided a home video of their ASD child’s natural social behavior. We performed DNA extraction and 16S rRNA amplicon sequencing on 117 stool samples (60 ASD and 57 NT) that met all study design eligibility criteria,. Using DADA2, Exact Sequence Variants (ESVs) were identified as taxonomic units, and three statistical tests were performed on ESV abundance counts: (1) permutation test to determine differences between sibling pairs, (2) differential abundance test using a zero-inflated gaussian mixture model to account for the sparse abundance matrix, and (3) differential abundance test after modeling under a negative binomial distribution. The potential functional gene abundance for each sample was also inferred from the 16S rRNA data, providing KEGG Ortholog (KO), which were analyzed for differential abundance. Results In total, 21 ESVs had significantly differentially proportions in stool of children with ASD and their neurotypical siblings. Of these 21 ESVs, 11 were enriched in neurotypical children and ten were enriched in children with ASD. ESVs enriched in the ASD cohort were predominantly associated with Ruminococcaceae and Bacteroidaceae; while those enriched in controls were more diverse including taxa associated with Bifidobacterium, Porphyromonas, Slackia, Desulfovibrio, Acinetobacter johnsonii, and Lachnospiraceae. Exact Variant Analysis suggested that Lachnospiraceae was specific to the control cohort, while Ruminococcaceae, Tissierellaceae and Bacteroidaceae were significantly enriched in children with ASD. Metabolic gene predictions determined that while both cohorts harbor the butyrogenic pathway, the ASD cohort was more likely to use the 4-aminobutanoate (4Ab) pathway, while the control cohort was more likely to use the pyruvate pathway. The 4Ab pathway releases harmful by-products like ammonia and can shunt glutamate, affecting its availability as an excitatory neurotransmitter. Finally, we observed differences in the carbohydrate uptake capabilities of various ESVs identified between the two cohorts.

The GapMap project: a mobile surveillance system to map diagnosed autism cases and gaps in autism services globally

Although the number of autism diagnoses is on the rise, we have no evidence-based tracking of size and severity of gaps in access to autism-related resources, nor do we have methods to geographically triangulate the locations of the widest gaps in either the US or elsewhere across the globe. To combat these related issues of (1) mapping diagnosed cases of autism and (2) quantifying gaps in access to key intervention services, we have constructed a crowd-based mobile platform called “GapMap” (http://gapmap.stanford.edu) for real-time tracking of autism prevalence and autism-related resources that can be accessed from any mobile device with cellular or wireless connectivity. Now in beta, our aim is for this Android/iOS compatible mobile tool to simultaneously crowd-enroll the massive and growing community of families with autism to capture geographic, diagnostic, and resource usage information while automatically computing prevalence at granular geographical scales to yield a more complete and dynamic understanding of autism resource epidemiology.