Currently submitted to: JMIR Research Protocols
Date Submitted: Oct 6, 2026
Open Peer Review Period: Oct 7, 2026 - Dec 2, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Scaling Early Childhood Mental Health Consultation Through Artificial Intelligence and Human Support: Protocol for a Type 1 Hybrid Effectiveness-Implementation Cluster Randomized Trial
ABSTRACT
Background:
Early childhood mental health consultation (ECMHC) improves teacher and child outcomes, but workforce shortages, cost, and limited access constrain widespread implementation. Jump Start on the Go (JS Go) is a bilingual, AI-enhanced adaptation of an established ECMHC model that combines on-demand digital support with human mental health consultation.
Objective:
This paper describes the protocol for the JS Go study, which aims to evaluate whether JS Go improves young children’s psychosocial functioning relative to an attention-matched control, determine whether JS Go outcomes are comparable to traditional consultation delivered entirely by humans, and evaluate the mechanisms, implementation, and sustainability of a hybrid human-AI consultation model in childcare settings.
Methods:
This 3-arm Type 1 hybrid effectiveness-implementation cluster randomized trial will enroll 24 childcare centers, approximately 120 teachers, and 480 children ages 2–2.5 years old. Centers will be block randomized to: (1) JS Go, combining AI-enhanced digital support with human consultation; (2) traditional Jump Start, delivered through human consultation; or (3) an attention-matched active control. Child, teacher, and center outcomes will be assessed at baseline and 6, 12, 18, and 24 months. The primary outcome is child psychosocial functioning. Multilevel analyses will also examine teacher practices, self-efficacy, and beliefs as mechanisms of change. Implementation outcomes will include Reach, Effectiveness, Adoption, Implementation, and Maintenance, supplemented by objective app analytics and qualitative interviews.
Results:
This protocol describes a planned trial. Recruitment is expected to begin in 2027 and final follow-up completed in 2029.
Conclusions:
This trial will determine whether AI-enhanced ECMHC can improve child psychosocial outcomes while extending the reach of a limited mental health workforce. Findings will inform the effectiveness, implementation, and sustainability of hybrid human-AI approaches in early childhood settings.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.