Related Experiment Video
Updated: Jun 3, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Developing a simplified measure to predict the risk of autism spectrum disorders: Abbreviating the M-CHAT-R using a
Ning Pan1, Lifeng Chen1, Bocheng Wu1
1Key Laboratory of Brain, Cognition and Education Sciences, Ministry of Education, Institute for Brain Research and Rehabilitation, Guangdong Key Laboratory of Mental Health and Cognitive Science, South China Normal University, Guangzhou 510630, China.
Insights
Machine learning effectively screened autism spectrum disorder (ASD) in toddlers using a reduced Modified Checklist for Autism in Toddlers, revised (M-CHAT-R) item set, improving early detection in primary care.
Area of Science:
- Developmental Pediatrics
- Computational Psychiatry
- Public Health Screening
Background:
- Early identification of autism spectrum disorder (ASD) is critical for timely intervention.
- Current screening tools in Chinese primary child care settings have limitations in accuracy and efficiency.
Purpose of the Study:
- To develop a machine learning model for improved ASD screening in toddlers.
- To identify key indicators from the M-CHAT-R and sociodemographic factors for distinguishing ASD from typical development.
Main Methods:
- Utilized data from a validation study of the Chinese M-CHAT-R (n=6,049 toddlers).
- Integrated 17 sociodemographic and environmental risk factors with M-CHAT-R data.
- Applied five feature selection methods and six machine learning algorithms to identify optimal screening subsets.
Main Results:
- Identified three feature subsets, with the optimal classifier using seven items from subset 2.
- The top-performing model achieved 92.5% sensitivity and 90.1% specificity.
- The seven-item classifier included M-CHAT-R items related to social interaction and attention, plus child's age.
Conclusions:
- Machine learning models can effectively differentiate toddlers with ASD from typically developing toddlers using a condensed M-CHAT-R item set.
- Optimized machine learning models hold significant clinical value for ASD screening in primary healthcare and beyond.
Background:
Early screening for autism spectrum disorder (ASD) is crucial, yet current assessment tools in Chinese primary child care are limited in efficacy.
Objective:
This study aims to employ machine learning algorithms to identify key indicators from the 20-item Modified Checklist for Autism in Toddlers, revised (M-CHAT-R) combining with ASD-related sociodemographic and environmental factors, to distinguish ASD from typically developing children.
Methods:
Data from our prior validation study of the Chinese M-CHAT-R (August 2016-March 2017, n = 6,049 toddlers) were reviewed. We extracted the 20-item M-CHAT-R data and integrated 17 sociodemographic and environmental risk factors associated with ASD development to strengthen M-CHAT-R's machine learning screening. Five feature selection methods were used to extract subsets from the original set. Six machine learning algorithms were applied to identify the optimal subset distinguishing clinically diagnosed ASD toddlers from typically developing toddlers.
Findings:
Nine features were grouped into three subsets: subset 1 contained unanimously recommended items (A1 [Follows point], A3 [Pretend play], A9 [Brings objects to show], A10 [Response to name] and A16 [Gazing following]). Subset 2 added two items (A17 [Gaining parent's attention] and A18 [Understands what is said]), and subset 3 included two more items (A8 [Interest in other children] and child's age). The top-performing algorithm resulted in a seven-item classifier of subset 2 with 92.5 % sensitivity, 90.1 % specificity, and 10.0 % positive predictive value.
Conclusions:
Machine learning classifiers effectively differentiate ASD toddlers from typically developing toddlers using a reduced M-CHAT-R item set.
Clinical Implications:
This highlights the clinical significance of machine learning-optimized models for ASD screening in primary health care centers and broader applications.
More Related Videos
Related Concept Videos
01:19Autism Spectrum Disorder
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
01:26Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...