Kim Hyelee, Leventhal Bennett L, Koh Yun-Joo, Gennatas Efstathios D, Kim Young Shin
University of California, San Francisco, San Francisco, California.
University of Chicago, Chicago, Illinois.
JAACAP Open. 2024 May 27;3(2):302-312. doi: 10.1016/j.jaacop.2024.03.005. eCollection 2025 Jun.
Delays in autism spectrum disorder (ASD) diagnosis and treatment are significant clinical problems that can be addressed by timely, community-based assessment. This study examined tools for identifying ASD in community settings using machine learning (ML) models.
This study analyzed population-based cross-sectional studies (2005-2017) of ASD in South Korea. A community sample of 62,083 children was screened using the Autism Spectrum Screening Questionnaire (ASSQ) and teacher/caregiver referrals. Caregivers completed the Behavior Assessment System for Children-2nd Edition (BASC-2) and the Social Responsiveness Scale (SRS). Screen positives were offered a comprehensive clinical evaluation. Among the first-graders in regular elementary schools who completed the diagnostic evaluation (N = 746), supervised ML models (generalized linear model with elastic net regularization [GLMNET], classification and regression tree, random forest, and gradient boosting [GB]) were developed and validated for classification of ASD. Models were developed in the single questionnaire and combined questionnaire datasets, using questionnaire responses and demographic and developmental information.
ASD was diagnosed in 46.2% of children (median age, 6.8 years [interquartile range, 6.5-7.1 years]; 71.7% boys). Among single questionnaire models, the BASC GB model demonstrated the best discrimination ability (area under the curve 0.80, 95% CI 0.75-0.83). Area under the curve of the GLMNET model with combined ASSQ, BASC-2, and SRS was the highest, 0.82 (95% CI 0.77-0.89); the predicted risk of ASD by the GB model of combined questionnaires agreed the best with the observed risk of ASD compared with other ML models.
Caregiver questionnaire ML models showed future promise for identifying children with ASD in community settings.
自闭症谱系障碍（ASD）诊断和治疗的延迟是重大临床问题，可通过及时的社区评估来解决。本研究使用机器学习（ML）模型检验了在社区环境中识别ASD的工具。
本研究分析了韩国基于人群的ASD横断面研究（2005 - 2017年）。使用自闭症谱系筛查问卷（ASSQ）以及教师/照顾者转诊对62,083名儿童的社区样本进行筛查。照顾者完成了儿童行为评估系统第二版（BASC - 2）和社会反应量表（SRS）。筛查呈阳性者接受全面临床评估。在完成诊断评估的正规小学一年级学生中（N = 746），开发并验证了监督ML模型（带弹性网正则化的广义线性模型[GLMNET]、分类回归树、随机森林和梯度提升[GB]）用于ASD分类。模型在单一问卷和组合问卷数据集中开发，使用问卷回答以及人口统计学和发育信息。
46.2%的儿童被诊断为ASD（中位年龄6.8岁[四分位间距，6.5 - 7.1岁]；71.7%为男孩）。在单一问卷模型中，BASC GB模型表现出最佳的区分能力（曲线下面积0.80，95%置信区间0.75 - 0.83）。结合ASSQ、BASC - 2和SRS的GLMNET模型的曲线下面积最高，为0.82（95%置信区间0.77 - 0.89）；与其他ML模型相比，组合问卷的GB模型预测的ASD风险与观察到的ASD风险最相符。
照顾者问卷ML模型在社区环境中识别ASD儿童方面显示出未来的应用前景。
