Scholarlink

Purpose of review <p>Autism spectrum disorder (ASD) is a neurodevelopmental condition with significant implications for childhood development and public health. Early detection is critical to enable timely intervention, yet access to specialised assessment remains limited in many settings. In this context, artificial intelligence (AI) has gained increasing attention as a potential tool to support early ASD screening. This review summarises recent evidence on the use of AI for the screening and early detection in childhood.</p> Recent findings <p>Recent studies generally report favorable results for AI-based approaches, particularly in pediatric populations. Multimodal models that integrate data from questionnaires, video and audio sources tend to outperform single modality approaches, with reported improvements in accuracy and sensitivity. However, most studies remain experimental, with small sample sizes and limited validation in real world clinical environments.</p> Summary <p>AI shows promise as a supportive tool for early screening, but current evidence supports its use as a complement to, rather than replacement for, clinical assessment. Further validation in routine practice is needed before widespread implementation.</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

From Data to Early Diagnosis: Artificial Intelligence as a Tool to Support Screening and Detection of Autism Spectrum Disorder in Childhood

  • 期刊论文

  • 发表日期：

    2026年7月31日

查看全文
  • Andrea Catalina Mahecha Ballesteros,
  • Juanita Valeria García Bello,
  • Eleaine Scarlet González Zuñiga,
  • Shayra Nicole Peinado Páez,
  • Erwin Hernando Hernández Rincón

摘要

Purpose of review

Autism spectrum disorder (ASD) is a neurodevelopmental condition with significant implications for childhood development and public health. Early detection is critical to enable timely intervention, yet access to specialised assessment remains limited in many settings. In this context, artificial intelligence (AI) has gained increasing attention as a potential tool to support early ASD screening. This review summarises recent evidence on the use of AI for the screening and early detection in childhood.

Recent findings

Recent studies generally report favorable results for AI-based approaches, particularly in pediatric populations. Multimodal models that integrate data from questionnaires, video and audio sources tend to outperform single modality approaches, with reported improvements in accuracy and sensitivity. However, most studies remain experimental, with small sample sizes and limited validation in real world clinical environments.

Summary

AI shows promise as a supportive tool for early screening, but current evidence supports its use as a complement to, rather than replacement for, clinical assessment. Further validation in routine practice is needed before widespread implementation.