Research on the severity of symptoms in children with ASD based on integrated machine learning and structural equation modeling: age-specific predictive features and mediation effect path analysis - Takeaways - MDSpire

Research on the severity of symptoms in children with ASD based on integrated machine learning and structural equation modeling: age-specific predictive features and mediation effect path analysis

  • By

  • Shimei Lu

  • Liangqiong Deng

  • Daoqing Gong

  • Xinyi Jia

  • Xiya Lang

  • Lianghui Diao

  • Liqin Ma

  • Pingjing Wen

  • June 17, 2026

  • 0 min

Share

  • 1

    The study recruited 608 children with ASD, stratifying them into low-age and high-age groups for analysis.

  • 2

    Machine learning identified language as the core predictive feature for the low-age group, while personal-social and motor skills were more significant in the high-age group.

  • 3

    Structural equation modeling revealed a masking effect of age at first diagnosis on symptom severity, with a non-significant total effect.

  • 4

    Developmental level significantly mediated the relationship between age at first diagnosis and symptom severity, especially in the low-age group.

  • 5

    Findings suggest age-stratified interventions may improve clinical management of ASD by addressing specific developmental and physical factors.

Original Source(s)

Research on the severity of symptoms in children with ASD based on integrated machine learning and structural equation modeling: age-specific predictive features and mediation effect path analysis

  • by Shimei Lu, Liangqiong Deng, Daoqing Gong, Xinyi Jia, Xiya Lang, Lianghui Diao, Liqin Ma, Pingjing Wen

  • June 17, 2026

Related Content

Neuroinflammatory mechanisms and pharmacological advances in autism spectrum disorder: from inflammatory pathways to targeted interventions

Case Report: MECP2 and SH3KBP1 variants associated with autism spectrum disorder and immune dysregulation

Getting the timing right. Autistic adolescents reflect on the value of an early diagnosis