Abstract
Diagnoses of autism spectrum disorders (ASD) are typically made after toddlerhood by examining behavioural patterns. Earlier identification of ASD enables earlier intervention and better outcomes. Machine learning provides a data-driven approach of diagnosing autism at an earlier age. This review aims to summarize recent studies and technologies utilizing machine learning based strategies to screen infants and children under the age of 18 months for ASD, and identify gaps that can be addressed in the future. We reviewed nine studies based on our search criteria, which includes primary studies and technologies conducted within the last 10 years that examine children with ASD or at high risk of ASD with a mean age of less than 18 months old. The studies must use machine learning analysis of behavioural features of ASD as major methodology. A total of nine studies were reviewed, of which the sensitivity ranges from 60.7% to 95.6%, the specificity ranges from 50% to 100%, and the accuracy ranges from 60.9% to 97.7%. Factors that contribute to the inconsistent findings include the varied presentation of ASD among patients and study design differences. Previous studies have shown moderate accuracy, sensitivity and specificity in the differentiation of ASD and non-ASD individuals under the age of 18 months. The application of machine learning and artificial intelligence in the screening of ASD in infants is still in its infancy, as observed by the granularity of data available for review. As such, much work needs to be done before the aforementioned technologies can be applied into clinical practice to facilitate early screening of ASD.
Highlights
BackgroundAutism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by persistent deficits in social communication and social interaction across multiple contexts, as well as restricted repetitive patterns of behavior, interests or activities [1]
A literature review of studies using machine learning technology in the early screening of autism spectrum disorders (ASD) was conducted on peer-reviewed primary journal articles listed in PubMed and Medline from the last 10 years (February 2011 to February 2021)
We describe our findings by introducing how machine learning can be utilized to complement existing ASD assessment tools and new behavioral components, with the potential to improve early screening of ASD
Summary
Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by persistent deficits in social communication and social interaction across multiple contexts, as well as restricted repetitive patterns of behavior, interests or activities [1]. The prevalence of ASD has increased worldwide in recent years. The CDC released a report citing a prevalence of ASD of 16.8 per 1000 in 2014, a significant increase from 14.7 per 1000 in 2010 [2]. The American Academy of Pediatrics recommends that all children receive screening tests for ASD and language development, conducted at 18- and 24-month well-child visits [3]. Zuckerman et al concluded that children who were diagnosed late were more likely to be treated with medications or alternative medication, whereas children diagnosed early responded well to conventional ASD therapy such as speech therapy, and monitoring by a pediatric psychiatrist [5]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
