CNN Based ASD Early Screening for Chinese Children

DOI

10.2991/978-2-38476-230-9_26How to use a DOI?

Keywords

ASD screening; Behavioral data; Q-CHAT-10; CNN

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental condition that can result in significant healthcare costs, with early diagnosis being crucial in reducing these costs. Behavioral data-based early screening for ASD is an easily implemented, time-efficient, and cost-effective method that can aid health professionals in informing individuals whether they should pursue formal clinical diagnosis. In this study, a Convolutional Neural Network (CNN) classifier and a support vector machine (SVM) classifier were compiled and trained on an open dataset of 1–18-year-old children and teenagers collected by the Computer Science Department of the University of Arkansas. The dataset included 10 behavioral features (Q-CHAT-10), age, gender, history of jaundice, and family history of ASD. Results showed that the CNN model outperformed the SVM model on indicators such as accuracy, precision, and recall. The validity of the trained model was further tested using data collected from Chinese children and teenagers through a questionnaire. The research exhibits the potential for the development of an accurate, low-cost, widely applicable, and easy-to-operate tool for early screening of ASD for Chinese children and teenagers especially for those in regions with limited medical resources, promoting early intervention..

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Liangyu Sun
AU  - Yong Mao
PY  - 2024
DA  - 2024/04/29
TI  - CNN Based ASD Early Screening for Chinese Children
BT  - Proceedings of the 4th International Conference on New Computational Social Science (ICNCSS 2024)
PB  - Atlantis Press
SP  - 211
EP  - 221
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-230-9_26
DO  - 10.2991/978-2-38476-230-9_26
ID  - Sun2024
ER  -