Scholarlink

Purpose <p>To construct and evaluate a LightGBM prediction model for intellectual disabilities in children with Autism Spectrum Disorder (ASD).</p> Methods <p>A total of 384 ASD children who completed the Wechsler Intelligence Test and Adaptive Behavioral Assessment System were included in the analysis. The LightGBM model was trained using behavioral observation data and underwent hyperparameter tuning and feature selection.</p> Results <p>Among the ASD children, 32.9% had comorbid ID. The LightGBM model exhibited the highest sensitivity and accuracy, with values of 0.793 and 0.760, respectively. It also achieved an AUC of 0.747, with overall quality of relationships, unusual sensory interests, and gestures/postures being the top predictive features.</p> Conclusion <p>The LightGBM model demonstrated strong predictive performance, enabling early identification of comorbid ID in preschool children with ASD and facilitating personalized intervention strategies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-based prediction of intellectual disability in children with autism spectrum disorder: using behavioral observation techniques

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月30日

查看全文
  • Xiaolin Liu,
  • Ting Han,
  • Zhongquan Jiang,
  • Lifei Hu,
  • Wenhao Li,
  • Chao Song

摘要

Purpose

To construct and evaluate a LightGBM prediction model for intellectual disabilities in children with Autism Spectrum Disorder (ASD).

Methods

A total of 384 ASD children who completed the Wechsler Intelligence Test and Adaptive Behavioral Assessment System were included in the analysis. The LightGBM model was trained using behavioral observation data and underwent hyperparameter tuning and feature selection.

Results

Among the ASD children, 32.9% had comorbid ID. The LightGBM model exhibited the highest sensitivity and accuracy, with values of 0.793 and 0.760, respectively. It also achieved an AUC of 0.747, with overall quality of relationships, unusual sensory interests, and gestures/postures being the top predictive features.

Conclusion

The LightGBM model demonstrated strong predictive performance, enabling early identification of comorbid ID in preschool children with ASD and facilitating personalized intervention strategies.