← CHI 2026 map

CHI '26 · Honorable mention · full-paper review · confidence medium-high

AV-Play: Co-Designing VR Games to Study Audiovisual Integration in Children with ADHD

Huadong Zhang , Nishant Joshi Dinesha , Ziming Li , Roshan L Peiris , Emily J Knight , Chao Peng

DOI PDF Program page Page JSON

AV-Play is a credible CHI-style artifact paper: the contribution is a co-designed VR game plus an exploratory multimodal study, not a finished intervention claim. Its strongest value is showing how to frame the engagement-versus-validity tradeoff as a design problem rather than a post hoc limitation, while keeping the clinical measurement story visible throughout.

Axes Lens

Rare contribution shape, typical evidence profile. The point here is not a score. It is to show what kind of claim the paper makes, and whether the evidence pattern is unusual or baseline in this 268 -review set.

Review Summary

AV-Play reads as a solid honorable-mention-level contribution because it tackles a real and underexplored design problem with a concrete artifact and a plausible evaluation strategy. The paper’s main intellectual move is not to claim a breakthrough clinical effect, but to argue that VR games for children with ADHD must be designed so that engagement does not distort the very audiovisual and attentional constructs being studied. That is a sensible and useful reframing for CHI: it turns a familiar “make it fun” instinct into a more disciplined co-design problem grounded in clinical expertise and child-centered interaction. The contribution is therefore strongest as an artifact-plus-process paper. The evidence packet supports that framing: the authors describe a stakeholder-informed co-design process, a VR game with interaction and difficulty variations, and an exploratory study with 11 children spanning neurotypical and ADHD participants. That is enough to justify early-stage insights about task performance and user experience, but not enough to support strong claims about efficacy, generalizability, or clinical impact. The limitations are appropriately explicit: the sample is modest, the age range is limited to under 12, and the authors themselves say the results should be interpreted as indicative rather than definitive. In field terms, this is a useful bridge between clinical fidelity and playful interaction, but it remains a prototype validated in a narrow exploratory setting rather than a deployable therapeutic system. I also think the paper’s most valuable design lesson is methodological: it shows that measurement constraints, child engagement, and interaction simplicity can be negotiated together rather than treated as competing afterthoughts. That makes the work especially relevant to CHI readers interested in therapeutic games, neurodivergence, and multimodal evaluation.

What Changed

Canon before

Prior CHI work on VR for children and clinical populations often separates engagement-oriented game design from clinically grounded measurement, and ADHD-related audiovisual integration interventions remain comparatively sparse. The default pattern in this area is either a playful system that is hard to interpret clinically or a tightly controlled assessment that children may not want to repeat. AV-Play is interesting because it explicitly tries to collapse that split by making the measurement logic part of the game design itself, rather than treating measurement as an external add-on.

Departure from common sense

The paper’s core tension is that the features usually treated as strengths in VR games—immersion, multimodal feedback, and playful interaction—can become liabilities for clinical study unless they are tightly grounded in evidence-based design. That is a useful corrective to the common assumption that more engagement is always better. The authors also argue that interaction simplicity can be a virtue for assessment, because it helps isolate attentional performance from motor complexity and other confounds.

Actual novelty

AV-Play is positioned as a novel VR therapeutic game for studying audiovisual integration in children with ADHD, developed through stakeholder-informed co-design and paired with multimodal data capture to connect clinical mechanisms with playable interaction. The novelty is less a new theory than a concrete artifact and design process that tries to reconcile clinical rigor with child-centered engagement. The paper’s contribution is strongest in showing how to translate mechanistic goals into adjustable gameplay parameters, child-friendly interaction modes, and synchronized EEG/eye-tracking measurement within one coherent prototype.

Evidence

The paper presents a co-designed VR game and reports an exploratory mixed-methods study with 11 children, including neurotypical and ADHD participants. Evidence supports a prototype-level contribution, design rationale, and early user-study observations, but not strong causal or comparative claims about efficacy or clinical impact. The strongest support is for the design argument: the system can be tuned across interaction modes and difficulty levels, and the resulting behavior, gaze, and EEG signals are used to motivate design implications rather than therapeutic conclusions.

Limits

Method limits

The study is exploratory and based on a modest sample, which limits group-level comparison and broader inference. The paper also restricts participants to children under 12, narrowing developmental coverage and making age-general claims inappropriate. In addition, the evaluation is short-horizon and lab-centered, so it cannot establish durability of effects, learning transfer, or intervention efficacy over time.

Deployment limits

The work is not yet validated as a deployable intervention; it remains a prototype evaluated in a controlled exploratory setting with researcher assistance, instrumented hardware, and lab-based EEG/eye-tracking setup. The authors themselves frame future work as longitudinal, home-based, and adaptive, which underscores that the current system is still a research platform rather than a ready-to-ship therapeutic product.

Boundary conditions

Interpretation is bounded by the under-12 participant pool, the small sample size, and the fact that results are indicative rather than definitive. Any extension to older children, larger cohorts, or home-based use would require additional validation and likely different interaction/difficulty tuning. The strongest claims are therefore about design feasibility and measurement alignment in a constrained lab context, not about broad clinical generalization.

Manual check: no

Position in field

This sits at the intersection of child-computer interaction, VR game design, and clinical/educational intervention research. Its main value is as a design-and-evaluation exemplar for balancing engagement with measurement fidelity in ADHD-related audiovisual integration work. In field terms, it is a bridge paper: more concrete than a conceptual framework, but more exploratory than a validated intervention trial.

Abstract

Processing speech in noisy environments is a core challenge for children with attention deficit hyperactivity disorder (ADHD), and few studies investigated evidence-based interventions. Disrupted visual attention and audiovisual integration are key contributors to these difficulties. Virtual reality (VR) games offer potential to support attention and audiovisual integration training, yet few are designed for this purpose. Current approaches using VR games emphasize either clinical fidelity or entertainment, creating an imbalance between neural engagement and sustained motivation. We developed a VR game through a co-design approach, informed by neural mechanisms and clinical expertise, and embedding child-centered interaction to sustain engagement. The game includes variations in interaction modes and difficulty levels, iteratively refined with neurodevelopmental specialists and children. We conducted an exploratory study with 11 participants, including neurotypical and ADHD children. Findings highlight task performance and insights from the target user group, while also suggesting implications for balancing clinical potential with user engagement.