A scalable computational approach to assessing response to name in toddlers with autism

Abstract

Background: This study is part of a larger research program focused on developing objective, scalable tools for digital behavioral phenotyping. We evaluated whether a digital app delivered on a smartphone or tablet using computer vision analysis (CVA) can elicit and accurately measure one of the most common early autism symptoms, namely failure to respond to a name call. Methods: During a pediatric primary care well-child visit, 910 toddlers, 17-37 months old, were administered an app on an iPhone or iPad consisting of brief movies during which the child's name was called three times by an examiner standing behind them. Thirty-seven toddlers were subsequently diagnosed with autism spectrum disorder (ASD). Name calls and children's behavior were recorded by the camera embedded in the device, and children's head turns were coded by both CVA and a human. Results: CVA coding of response to name was found to be comparable to human coding. Based on CVA, children with ASD responded to their name significantly less frequently than children without ASD. CVA also revealed that children with ASD who did orient to their name exhibited a longer latency before turning their head. Combining information about both the frequency and the delay in response to name improved the ability to distinguish toddlers with and without ASD. Conclusions: A digital app delivered on an iPhone or iPad in real-world settings using computer vision analysis to quantify behavior can reliably detect a key early autism symptom-failure to respond to name. Moreover, the higher resolution offered by CVA identified a delay in head turn in toddlers with ASD who did respond to their name. Digital phenotyping is a promising methodology for early assessment of ASD symptoms.

A systematic review of telehealth screening, assessment, and diagnosis of autism spectrum disorder

“…For example, the latest study of Cognoa showed a sensitivity of 0.98 and a specificity of 0.79 for ASD screening in 425 children aged 18–72 months [ 28 , 29 ]. The same pattern was observed with Autism&Beyond, which had an ASD screening sensitivity of 0.96 [ 33 ]. One possible reason for this finding could be interference and a lack of standardization of the observations.…”

“…Autism&Beyond is even more convenient, requiring children to watch a total of approximately 2 min of short videos for facial data collection and only approximately 20 min of questionnaire completion for caregivers. Therefore, a significant amount of time is saved [ 33 ]. In addition, digital health can help address parents’ concerns about contracting COVID-19 during travel to and from clinics given the pandemic circumstances.…”

A multimodal machine learning system in early screening for toddlers with autism spectrum disorders based on the response to name

“…A recent study has revealed that children with ASD responded to their names significantly less frequently than children without ASD using computer vision analysis (CVA). The CVA also exhibited that children with ASD who did orient to name call showed a longer latency before turning their head ( 25 ), which is consistent with our results. The diminished response can be explained by the theory of social motivation and social cognition in ASD.…”

Complexity analysis of head movements in autistic toddlers

“…A computer vision algorithm was used to detect the faces in each frame of the recorded video (King, 2009). Similar to (Chang et al., 2021; Perochon et al., 2021), scarce human supervision was triggered by a face‐tracking algorithm to ensure that we tracked only the participant's face. Then, we extracted 49 facial landmarks consisting of 2D‐positional coordinates (Baltrusaitis et al., 2018) (Figure 2) that were time‐synchronized with the movies.…”