AI for Childhood Neurodevelopmental Disorder Diagnosis: An Umbrella Review

An umbrella review synthesizing evidence from 64 systematic reviews and meta-analyses on the use of artificial intelligence to diagnose neurodevelopmental disorders in children. The review, authored by Alejandro Alberca-González and published on figshare in March 2026, covers studies from 2015 to 2025, focusing on conditions like autism spectrum disorder and ADHD. It analyzes AI model performance across data modalities including neuroimaging, electrophysiological, and clinical data.

Use Cases

• Benchmarking AI model diagnostic accuracy based on reported performance metrics ranging from 66% to 99%.
• Analyzing the distribution of AI applications across different data modalities like neuroimaging and electrophysiological signals.
• Assessing the methodological quality of existing research based on the AMSTAR-2 criteria ratings provided.
• Identifying research gaps for specific disorders like intellectual disability or communication disorders based on the review's coverage.

Strengths

• Systematically reviews 64 studies, providing a consolidated evidence base.
• Reports specific diagnostic accuracy ranges (66% to 99%) for different AI models and data types.
• Quantifies the distribution of reviewed studies by disorder (e.g., 31 on ASD, 14 on ADHD) and data modality (e.g., 59 using neuroimaging).
• Includes a PROSPERO systematic review registration identifier (CRD420251110825) for traceability.

Limitations

• The underlying data is a 25.7 KB DOCX file containing a review article, not a primary dataset for direct analysis.
• The methodological quality of most included studies (80%) was rated as critically low.
• Column-level documentation for any extracted data is absent; the file is a narrative review document.

Provenance

Source

Alejandro Alberca-González via figshare.

Collection Method

Systematic search on Web of Science, PsycINFO, and PubMed, following umbrella review methodology.

Time Range

Studies published from January 2015 to August 2025.

Freshness

Last updated 2026-03-18.