EUVIMEDEUVIMED entdecken
QuerschnittstudieOpen Access

Two-Stage Gamified Digital Assessment for Autism Spectrum Disorder Screening and the Limits of Differentiating Social Communication Disorder in Children and Adolescents: Cross-Sectional Diagnostic Accuracy Study Using Explainable Machine Learning

Minyoung Jung, Ju Ran, Ennyoung Lee, Youngkyung Sunwoo, SooYeon Kim, Ji-Hoon Kim, Sungja Cho

JMIR Serious Games · 23.09.2026 · 14 · e102714-e102714

DOI: 10.2196/102714 ↗

Kurz gefasst

Querschnittstudie in der Zeitschrift JMIR Serious Games, online erschienen am 23.09.2026. Verfasst von Minyoung Jung und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Brain Convergence, Korea Brain Research Institute, 61 Cheomdan-ro, Dong-gu, Daegu, 41062, Republic of Korea, +82-53-980-8126. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Distinguishing autism spectrum disorder (ASD) from social communication disorder (SCD) is clinically challenging because both conditions present with overlapping social communication deficits. Standard caregiver-reported instruments capture surface-level behavioral similarities rather than underlying cognitive differences, motivating the development of digital gamified assessments that measure social cognitive processes directly.

Objective

This study developed and evaluated a 2-stage gamified digital pipeline: stage 1 (Buddy Plan, a self-report module) for high-sensitivity ASD screening, and stage 2 (Buddy Drill, story-based social-judgment scenarios), which was examined with a leakage-controlled analysis, for assessing whether ASD can be differentiated from SCD.

Methods

In this cross-sectional diagnostic accuracy study, 275 children and adolescents aged 6‐18 years (mean 11.07, SD 3.13 years; 175/275, 63.6% male) were recruited by convenience sampling from 5 clinical and community sites in the Republic of Korea (May 2024 to February 2025) across 5 Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) groups: ASD (n=51), SCD (n=54), attention-deficit/hyperactivity disorder (n=23), high risk (n=52), and neurotypically developing (ND; n=95). Diagnoses were established by board-certified child psychiatrists. Participants completed 2 tablet-based modules: Buddy Plan (52 self-report items; stage 1) and Buddy Drill (153 story-based scenarios; stage 2). The primary outcome was diagnostic accuracy (area under the receiver operating characteristic curve [AUC], sensitivity, and specificity). Four machine learning algorithms were trained with nested cross-validation (5×5 folds). For stage 2, item selection and imputation were performed within each training fold. Explainability used Shapley Additive Explanations (SHAP). Significance was set at α=.05 (2-sided) with bootstrap 95% CIs.

Results

Group differences were tested by 1-way ANOVA. For stage 1 (ASD vs ND; n=146), random forest achieved a nested AUC of 0.912 (95% CI 0.856‐0.953). At a threshold of 0.200, sensitivity was 96.1% (49/51; 95% CI 86.8%‐99.5%) and specificity was 58.9% (56/95; 95% CI 48.4%‐68.9%), with 2 false negatives. For stage 2 (ASD vs SCD; n=100), the fully nested pipeline yielded only chance-level discrimination: regularized logistic regression achieved a nested AUC of 0.62 (95% CI 0.51‐0.74), and no feature configuration (self-report: 0.55, objective: 0.62, combined: 0.63) exceeded chance. SHAP identified 5 cross-algorithm stage 1 biomarkers with significant ASD-versus-ND differences (all P

Schlagwörter

Stichwörter der Autor:innen

autism spectrum disorderdiagnostic screeningdifferential diagnosisdigital biomarkerexplainable artificial intelligencefeature-selection leakagegamificationmachine learningnested cross-validationsocial communication disorder

Autor:innen und Institutionen

  • Department of Brain Convergence, Korea Brain Research Institute, 61 Cheomdan-ro, Dong-gu, Daegu, 41062, Republic of Korea, +82-53-980-8126.
  • Neudive Inc, Seoul, Republic of Korea.
  • Department of Psychiatry, Incheon Medical Center, Incheon, Republic of Korea.
  • Department of Psychiatry, Purme Foundation Nexon Children's Rehabilitation Hospital, Seoul, Republic of Korea.
  • Department of Psychiatry, Pusan National University Yangsan Hospital, Yangsan, Republic of Korea.

Zitieren

APA

Jung, M., Ran, J., Lee, E., Sunwoo, Y., Kim, S., Kim, J. H., & Cho, S. (2026). Two-Stage Gamified Digital Assessment for Autism Spectrum Disorder Screening and the Limits of Differentiating Social Communication Disorder in Children and Adolescents: Cross-Sectional Diagnostic Accuracy Study Using Explainable Machine Learning. JMIR Serious Games, 14, e102714-e102714. https://doi.org/10.2196/102714

Vancouver

Jung M, Ran J, Lee E, Sunwoo Y, Kim S, Kim JH, et al. Two-Stage Gamified Digital Assessment for Autism Spectrum Disorder Screening and the Limits of Differentiating Social Communication Disorder in Children and Adolescents: Cross-Sectional Diagnostic Accuracy Study Using Explainable Machine Learning. JMIR Serious Games. 2026;14:e102714-e102714. doi:10.2196/102714

BibTeX
@article{Jung2026,
  author = {Jung, Minyoung and Ran, Ju and Lee, Ennyoung and Sunwoo, Youngkyung and Kim, SooYeon and Kim, Ji-Hoon and Cho, Sungja},
  title = {Two-Stage Gamified Digital Assessment for Autism Spectrum Disorder Screening and the Limits of Differentiating Social Communication Disorder in Children and Adolescents: Cross-Sectional Diagnostic Accuracy Study Using Explainable Machine Learning},
  journal = {JMIR Serious Games},
  year = {2026},
  volume = {14},
  pages = {e102714--e102714},
  doi = {10.2196/102714}
}
Kostenlos starten →