Automatic Identification of High-Risk Autism Spectrum Disorder: A Feasibility Study Using Video and Audio Data Under the Still-Face Paradigm

A survey study on early detection of young children with disabilities in urban and rural areas of China

AIM

This study aimed to understand how children and families access early intervention in China.

BACKGROUND

Timely identification and high-quality intervention is expected to prevent and reduce the occurrence and severity of chronic functional impairment for children with disability and is of great significance to individuals and the society. The current study recruited 1129 caregivers of children with disabilities from rural and urban areas of China were recruited to participate in a survey.

RESULTS

(a) The first concern about development was raised, usually by the parents, when a child with disabilities was 26 months of age, (b) developmental screening took place 4 months after the first concern and diagnostic evaluation happened 7 months after, (c) the types of early intervention programme varied across urban and rural areas and (d) child and family factors were found associating with age of detection.

CONCLUSIONS

Findings highlight the concerningly late age of children being identified for early intervention and disparities in services between urban and rural areas in China. Implications are provided for practitioners, policy makers and future research.

Machine learning-based ABA treatment recommendation and personalization for autism spectrum disorder: an exploratory study

Autism spectrum is a brain development condition that impairs an individual's capacity to communicate socially and manifests through strict routines and obsessive-compulsive behavior. Applied behavior analysis (ABA) is the gold-standard treatment for autism spectrum disorder (ASD). However, as the number of ASD cases increases, there is a substantial shortage of licensed ABA practitioners, limiting the timely formulation, revision, and implementation of treatment plans and goals. Additionally, the subjectivity of the clinician and a lack of data-driven decision-making affect treatment quality. We address these obstacles by applying two machine learning algorithms to recommend and personalize ABA treatment goals for 29 study participants with ASD. The patient similarity and collaborative filtering methods predicted ABA treatment with an average accuracy of 81-84%, with a normalized discounted cumulative gain of 79-81% (NDCG) compared to clinician-prepared ABA treatment recommendations. Additionally, we assess the two models' treatment efficacy (TE) by measuring the percentage of recommended treatment goals mastered by the study participants. The proposed treatment recommendation and personalization strategy are generalizable to other intervention methods in addition to ABA and for other brain disorders. This study was registered as a clinical trial on November 5, 2020 with trial registration number CTRI/2020/11/028933.