Dataset Information

Automatic emotion and attention analysis of young children at home: a ResearchKit autism feasibility study.

ABSTRACT: Current tools for objectively measuring young children's observed behaviors are expensive, time-consuming, and require extensive training and professional administration. The lack of scalable, reliable, and validated tools impacts access to evidence-based knowledge and limits our capacity to collect population-level data in non-clinical settings. To address this gap, we developed mobile technology to collect videos of young children while they watched movies designed to elicit autism-related behaviors and then used automatic behavioral coding of these videos to quantify children's emotions and behaviors. We present results from our iPhone study Autism & Beyond, built on ResearchKit's open-source platform. The entire study-from an e-Consent process to stimuli presentation and data collection-was conducted within an iPhone-based app available in the Apple Store. Over 1 year, 1756 families with children aged 12-72 months old participated in the study, completing 5618 caregiver-reported surveys and uploading 4441 videos recorded in the child's natural settings. Usable data were collected on 87.6% of the uploaded videos. Automatic coding identified significant differences in emotion and attention by age, sex, and autism risk status. This study demonstrates the acceptability of an app-based tool to caregivers, their willingness to upload videos of their children, the feasibility of caregiver-collected data in the home, and the application of automatic behavioral encoding to quantify emotions and attention variables that are clinically meaningful and may be refined to screen children for autism and developmental disorders outside of clinical settings. This technology has the potential to transform how we screen and monitor children's development.

SUBMITTER: Egger HL

PROVIDER: S-EPMC6550157 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic emotion and attention analysis of young children at home: a ResearchKit autism feasibility study.

Egger Helen L HL Dawson Geraldine G Hashemi Jordan J Carpenter Kimberly L H KLH Espinosa Steven S Campbell Kathleen K Brotkin Samuel S Schaich-Borg Jana J Qiu Qiang Q Tepper Mariano M Baker Jeffrey P JP Bloomfield Richard A RA Sapiro Guillermo G

NPJ digital medicine 20180601

Current tools for objectively measuring young children's observed behaviors are expensive, time-consuming, and require extensive training and professional administration. The lack of scalable, reliable, and validated tools impacts access to evidence-based knowledge and limits our capacity to collect population-level data in non-clinical settings. To address this gap, we developed mobile technology to collect videos of young children while they watched movies designed to elicit autism-related beh ...[more]

PMID: 31304303

Similar Datasets

Project description:BACKGROUND:Autism spectrum disorder (ASD) is a developmental disorder characterized by deficits in social communication and interaction, and restricted and repetitive behaviors and interests. The incidence of ASD has increased in recent years; it is now estimated that approximately 1 in 40 children in the United States are affected. Due in part to increasing prevalence, access to treatment has become constrained. Hope lies in mobile solutions that provide therapy through artificial intelligence (AI) approaches, including facial and emotion detection AI models developed by mainstream cloud providers, available directly to consumers. However, these solutions may not be sufficiently trained for use in pediatric populations. OBJECTIVE:Emotion classifiers available off-the-shelf to the general public through Microsoft, Amazon, Google, and Sighthound are well-suited to the pediatric population, and could be used for developing mobile therapies targeting aspects of social communication and interaction, perhaps accelerating innovation in this space. This study aimed to test these classifiers directly with image data from children with parent-reported ASD recruited through crowdsourcing. METHODS:We used a mobile game called Guess What? that challenges a child to act out a series of prompts displayed on the screen of the smartphone held on the forehead of his or her care provider. The game is intended to be a fun and engaging way for the child and parent to interact socially, for example, the parent attempting to guess what emotion the child is acting out (eg, surprised, scared, or disgusted). During a 90-second game session, as many as 50 prompts are shown while the child acts, and the video records the actions and expressions of the child. Due in part to the fun nature of the game, it is a viable way to remotely engage pediatric populations, including the autism population through crowdsourcing. We recruited 21 children with ASD to play the game and gathered 2602 emotive frames following their game sessions. These data were used to evaluate the accuracy and performance of four state-of-the-art facial emotion classifiers to develop an understanding of the feasibility of these platforms for pediatric research. RESULTS:All classifiers performed poorly for every evaluated emotion except happy. None of the classifiers correctly labeled over 60.18% (1566/2602) of the evaluated frames. Moreover, none of the classifiers correctly identified more than 11% (6/51) of the angry frames and 14% (10/69) of the disgust frames. CONCLUSIONS:The findings suggest that commercial emotion classifiers may be insufficiently trained for use in digital approaches to autism treatment and treatment tracking. Secure, privacy-preserving methods to increase labeled training data are needed to boost the models' performance before they can be used in AI-enabled approaches to social therapy of the kind that is common in autism treatments.

Project description:Importance:Enhanced selective attention toward nonsocial objects and impaired attention to social stimuli constitute key clinical features of autism spectrum disorder (ASD). Yet, the mechanisms associated with atypical selective attention in ASD are poorly understood, which limits the development of more effective interventions. In typically developing individuals, selective attention to social and nonsocial stimuli is associated with the informational value of the stimuli, which is typically learned over the course of repeated interactions with the stimuli. Objective:To examine value learning (VL) of social and nonsocial stimuli and its association with selective attention in preschoolers with and without ASD. Design, Setting, and Participants:This case-control study compared children with ASD vs children with developmental delay (DD) and children with typical development (TD) recruited between March 3, 2017, and June 13, 2018, at a university-based research laboratory. Participants were preschoolers with ASD, DD, or TD. Main Outcomes and Measures:Procedure consisted of an eye-tracking gaze-contingent VL task involving social (faces) and nonsocial (fractals) stimuli and consisting of baseline, training, and choice test phases. Outcome measures were preferential attention to stimuli reinforced (high value) vs not reinforced (low value) during training. The hypotheses were stated before data collection. Results:Included were 115 preschoolers with ASD (n?=?48; mean [SD] age, 38.30 [15.55] months; 37 [77%] boys), DD (n?=?31; mean [SD] age, 45.73 [19.49] months; 19 [61%] boys), or TD (n?=?36; mean [SD] age, 36.53 [12.39] months; 22 [61%] boys). The groups did not differ in sex distribution; participants with ASD or TD had similar chronological age; and participants with ASD or DD had similar verbal IQ and nonverbal IQ. After training, the ASD group showed preference for the high-value nonsocial stimuli (mean proportion, 0.61 [95% CI, 0.56-0.65]; P?<?.001) but not for the high-value social stimuli (mean proportion, 0.51 [95% CI, 0.46-0.56]; P?=?.58). In contrast, the DD and TD groups demonstrated preference for the high-value social stimuli (DD mean proportion, 0.59 [95% CI, 0.54-0.64]; P?=?.001 and TD mean proportion, 0.57 [95% CI, 0.53-0.61]; P?=?.002) but not for the high-value nonsocial stimuli (DD mean proportion, 0.52 [95% CI, 0.44-0.59]; P?=?.64 and TD mean proportion, 0.50 [95% CI, 0.44-0.57]; P?=?.91). Controlling for age and nonverbal IQ, autism severity was positively correlated with enhanced learning in the nonsocial domain (r?=?0.22; P?=?.03) and with poorer learning in the social domain (r?=?-0.26; P?=?.01). Conclusions and Relevance:Increased attention to objects in preschoolers with ASD may be associated with enhanced VL in the nonsocial domain. When paired with poor VL in the social domain, enhanced value-driven attention to objects may play a formative role in the emergence of autism symptoms by altering attentional priorities and thus learning opportunities in affected children.

Dataset Information

Automatic emotion and attention analysis of young children at home: a ResearchKit autism feasibility study.

Publications

Automatic emotion and attention analysis of young children at home: a ResearchKit autism feasibility study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets