Sensory Based Feeding Intervention for Toddlers With Food Refusal: A Randomized Controlled Trial

Objective To investigate the effect of sensory-based feeding treatment for toddlers with food refusal compared with only providing nutrition education.Methods Thirty-two toddlers with food refusal were randomly assigned to an intervention group or the control group. Toddlers in the intervention group received the sensory-based feeding intervention and the duration was for 1 hour for 5 days per week for 4 weeks, and then 1 hour, once a week for 8 weeks. Subjects in both the intervention and control groups received nutritional education once every 4 weeks for 12 weeks. The participants were evaluated at their entry into the study and 12 weeks later based on height, weight, behavior at mealtime using the Behavioral Pediatrics Feeding Assessment Scale (BPFAS), and sensory processing ability using the Infant/Toddler Sensory Profile.Results Sixteen toddlers were included in each group. Two subjects in the intervention group and four toddlers in the control group were excluded from the final analysis. Significant improvements in child or parent subscales of the BPFAS were observed in the intervention group. In contrast, there were no significant improvements in any BPFAS scores in the control group.Conclusion Sensory-based feeding intervention was effective for improving mealtime behavior in toddlers with food refusal. Therefore, a sensory-based feeding intervention could be considered as an intervention approach to address feeding disorders in toddlers.

Parent Education Class for Children With Feeding Difficulties

Date Presented Accepted for AOTA INSPIRE 2021 but unable to be presented due to online event limitations. The purpose of this study was to determine the feasibility and effectiveness of a multidisciplinary educational class for parents in improving child feeding behaviors and reducing caregiver distress associated with feeding difficulties. This class has proven to be effective in educating parents about the intricate and dynamic nature of feeding per positive responses on Behavioral Pediatrics Feeding Assessment Scale, Parent Mealtime Action Scale, and parent survey. Primary Author and Speaker: Adina P. Schwartz Additional Authors and Speakers: Judy Hopkins

Crowd Annotations Can Approximate Clinical Autism Impressions from Short Home Videos with Privacy Protections

Artificial Intelligence (A.I.) solutions are increasingly considered for telemedicine. For these methods to adapt to the field of behavioral pediatrics, serving children and their families in home settings, it will be crucial to ensure the privacy of the child and parent subjects in the videos. To address this challenge in A.I. for healthcare, we explore the potential for global image transformations to provide privacy while preserving behavioral annotation quality. Crowd workers have previously been shown to reliably annotate behavioral features in unstructured home videos, allowing machine learning classifiers to detect autism using the annotations as input. We evaluate this method with videos altered via pixelation, dense optical flow, and Gaussian blurring. On a balanced test set of 30 videos of children with autism and 30 neurotypical controls, we find that the visual privacy alterations do not drastically alter any individual behavioral annotation at the item level. The AUROC on the evaluation set was 90.0% +/- 7.5% for the unaltered condition, 85.0% +/- 9.0% for pixelation, 85.0% +/- 9.0% for optical flow, and 83.3% +/- 9.3% for blurring, demonstrating that an aggregation of small changes across multiple behavioral questions can collectively result in increased misdiagnosis rates. We also compare crowd answers against clinicians who provided the same annotations on the same videos and find that clinicians are more sensitive to autism-related symptoms. We also find that there is a linear correlation (r=0.75, p<0.0001) between the mean Clinical Global Impression (CGI) score provided by professional clinicians and the corresponding classifier score emitted by the logistic regression classifier with crowd inputs, indicating that the classifier's output probability is a reliable estimate of clinical impression of autism from home videos. A significant correlation is maintained with privacy alterations, indicating that crowd annotations can approximate clinician-provided autism impression from home videos in a privacy-preserved manner.