The Role of Intelligent Technologies in Early Detection of Autism Spectrum Disorder (ASD): A Scoping Review

Abstract

Background: Two-year delay is reported between the first developmental concern raised by the parents and the diagnosis of ASD (Autism Spectrum Disorder), delaying the start of early intervention programs most beneficial within the first three years. Aim: Evaluate the role of technology in ASD detection by answering four research questions analyzing 1) evolution of technology, 2) use of various bio-behavioral data sources, 3) demographic categories, databases, controls, comparators, and assessment instruments, and 4) data collection, processing, and outcomes of the technology-based methods in ASD detection. Methods: Scoping review included behavioral-based ASD screening and diagnostic studies, published between 1st January 2011 to 31st December 2021 in PUBMED, SCOPUS, and IEEE Xplore databases for children under six years. The studies were assessed using the Critical Appraisal Skills Programm (CASP) and the PRISMA scoping review checklist (PRISMA-ScR). Results: The shortlisted 35 studies were categorized into seven bio-behavioral categories. The review suggested extensive use of machine learning (ML) and Deep Learning (DL) technologies with multimodal structured and unstructured data to detect infants at risk of ASD and Other developmental delays (ODD) as early as 9 to 12 months. However, the review reported various internal and external validity threats. Conclusion: Technology can significantly improve the current ASD detection process. The validation and adoption of technology can be fast-tracked by 1) designing robust study protocols, 2) executing multicultural field trials, 3) standardizing datasets, data quality and feature engineering methods, 4) recruiting statistically significant participants from ASD, typically developing (TD) and other developmental disorders (ODD) groups to ensure technological generalization, validation, and adoption outside laboratory settings.

Computer Vision-Based Assessment of Autistic Children: Analyzing Interactions, Emotions, Human Pose, and Life Skills

“…Three independent vision-based paradigms are designed as follows: a model for Activity Comprehension for childtherapist interaction, a model for FER of children, and a real-time approach for automatic joint attention recognition. The demand for low-cost diagnostics, universal screening guidelines, and research funding availability have prompted endeavors to create technology-based ASD screening [40], [42], [50]. Technological advances and the availability of low-cost cloud infrastructure have motivated researchers to automate the creation and processing of video data by constructing data pipelines.…”

“…Recently, the clinical study of multi-modular ML-based ASD diagnosis based on questionnaires and home videos has demonstrated a sensitivity of 90% towards ASD detection [40]. Some of the other improvements that have been witnessed with the application of AI are; 1) Detection of ASD at an early age, 2) Reduction in the number of assessment items as a result of implementing the feature reduction method, 3) Effective classification between different ASD, Typically Developing (TD), and other neurodevelopmental disorders, 4) Automatic feature extraction of bio-behaviors from multimodal data [41], [42].…”

“…Due to the availability of multimodal data from diverse bio-behavioral sources, such as videos including ASD behavioral features [12], [43], audio [44], facial expressions [45], and Electronic Health Record (EHR) data [46], DL applications trained on unstructured data have accelerated the detection and management of ASD and can be implemented at the point of care [12], [42], [43], [47]- [49].…”

“…However, most studies focus on one of the seven key data categories, such as stereotyped behaviors, eye gaze, facial expressions, postural analyses, motor movements, auditory, and electronic health records (EHRs) [42] adopting ML and DL techniques with GPU (Graphical Processing Units) and high processing cloud capabilities [9]. To the best of our knowledge, this is the first study to employ computer vision to extract data from various bio-behaviors, including play, engagement, facial expression, and joint-attention abilities.…”

“…Therefore, new technological methods for rapid and automatic data collection and analysis can enhance clinician capacity and improve quality, affordability, and accessibility in ASD detection and assessments. Technology has demonstrated significant benefits by employing ML (Machine Learning) and DL (Deep Learning) for early diagnosis and functional assessments of ASD [9], [10]. ML has uncovered essential and minimal features [11], [12] of ASD diagnostic instruments such as The Autism Diagnostic Observation Schedule (ADOS) [2], and The Autism Diagnostic Interview-Revised (ADI-R) [13], thereby accelerating the diagnosis procedure without compromising accuracy [14], [15].…”