Voice as a predictive signal: protocol for a scoping review of AI in early childhood development.

Authors

Mehrdad Amir-Behghadami, Seifollah Heidarabadi

Published in

BMJ open. Volume 16. Issue 6. Pages e117473. Jun 19, 2026. Epub Jun 19, 2026.

Abstract

Early childhood development (ECD) interventions support children aged 0-5 years, including those typically developing, at risk of delays or diagnosed with motor, cognitive, language or social-emotional disorders. Current assessments face barriers like limited access, high costs, intermittent evaluations and invasive methods. Voice offers a non-invasive digital biomarker, with artificial intelligence (AI) and machine learning (ML) enabling analysis of vocal features linked to developmental trajectories. This scoping review protocol synthesises evidence on AI-driven voice biomarkers for early detection, monitoring and management of ECD outcomes in healthy, at-risk or impaired children under five.
This scoping review protocol adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines and the Arksey and O'Malley framework, enhanced by Joanna Briggs Institute recommendations. Eligibility criteria follow the Population, Concept and Context framework: population (children 0-5 years), concept (AI/ML voice biomarker analysis), context (early detection, monitoring, management of developmental outcomes). Comprehensive searches target PubMed/MEDLINE, Scopus, Web of Science, Embase, IEEE Xplore, CINAHL and grey literature sources for peer-reviewed English/Persian articles from January 2015 onwards. Two independent reviewers screen titles/abstracts/full texts and extract data on clinical applications, recording protocols, acoustic features, AI models, demographics and implementation factors. Discrepancies were resolved via discussion or a third reviewer. Results were presented narratively with tables, charts and figures addressing research questions on voice as a predictive signal.
The Research Ethics Committee of Tabriz University of Medical Sciences approved this protocol, confirming ethical compliance absent patient involvement. Findings were disseminated via peer-reviewed journals, conferences and institutional seminars to inform AI integration in paediatric health informatics for equitable child development support.
Not registered.

PMID:
42320959
Bibliographic data and abstract were imported from PubMed on 20 Jun 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.