Previously submitted to: JMIR Medical Informatics (no longer under consideration since Apr 02, 2026)
Date Submitted: Mar 5, 2026
Open Peer Review Period: Apr 2, 2026 - Apr 2, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited.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.
Identifying Key Predictors of Language Difficulties in Children with ADHD Using Interpretable Machine Learning: Toward a Clinical Decision Support System: A retrospective study
ABSTRACT
Background:
Nearly half of children with ADHD experience comorbid language difficulties. While SNAP-IV behavioral assessment is routinely administered to all children with ADHD, comprehensive language evaluation is not universally conducted due to time and resource constraints, resulting in many children with language difficulties going undetected.
Objective:
To develop a clinical screening tool that leverages routinely collected SNAP-IV data to identify ADHD children at risk for language difficulties, thereby reducing missed cases. We used interpretable machine learning to identify key predictors and designed a two-tier screening workflow.
Methods:
We analyzed data from 188 children with ADHD (88.3% male, mean age 10.47 years). Language difficulty was defined as GCC < 86 (48.4% prevalence). Random Forest models were developed using SNAP-IV items, executive function measures, and demographics. SHAP (SHapley Additive exPlanations) analysis quantified feature contributions. A two-tier screening workflow was designed and evaluated.
Results:
The model achieved AUC 0.853. SHAP analysis revealed that inattention symptoms were substantially more predictive than hyperactivity symptoms. The top predictors were: SNAP-3 ("mind elsewhere during conversation"), planning ability, and SNAP-5 ("difficulty organizing"). A two-tier workflow combining quick rule-out (4-item score) with ML-based risk stratification achieved 90.1% sensitivity while reducing unnecessary referrals by 24.5%.
Conclusions:
Inattention symptoms and planning deficits are key predictors of language difficulties in ADHD. A clinical decision support system integrating ML-based screening can systematically identify at-risk children while optimizing clinical resources. A web-based application is under development for prospective validation.
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.