JMIR Publications

ABSTRACT

Background:

Developmental disabilities are a set of heterogeneous delays or difficulties in one or more developmental areas. Considering that childhood is an essential stage of brain development and developmental delays lead to personal or social burdens, the early detection of childhood developmental disabilities is important. However, the early screening for developmental disability has been a challenge because of fear of positive results, expensive tests, differences in diagnosis depending on the ability of the examiner, and difficulty in diagnosis arising from the need for long-term follow-up observation.

Objective:

This study aimed to assess the feasibility of using the game-derived index (GDI) from serious game to identify heterogeneous developmental disabilities. This study also aims to clarify the correlation between GDI and existing neuro-psychological test (NPT) results.

Methods:

The randomized clinical trial consisted of 48 children with normal developmental and developmental disabilities. The intervention of the trial was based on a serious game and will be continued for 12 weeks for 40 minutes twice a week. There were no human interventions other than early game usage training. The intervention was based on mobile serious game play at home, and the assessment was done in face-to-face test. In this clinical trial, we used 19 features (6 Korean-Wechsler Preschool and Primary Scale of Intelligence: K-WPPSI-IV, 8 Psychoeducational Profile Revised: PEP-R, 2 Bruininks-Oseretsky Test of Motor Proficiency, Second Edition: BOT-2, and 3 Pediatric Evaluation of Disability Inventory: PEDI) from NPT and 9 (7 Game Scores, Path Accuracy, and Completion Rate) from the serious game, DoBrain. The following analysis was conducted based on participants’ baseline information and NPT and GDI data for one week: 1) We compared the baseline information between ND (Normal Development) and DD groups (Developmental Disabilities). 2) We measured the correlation between GDI and a child’s NPT for each group. 3) Lastly, we built a classifier based on GDI, with a Gaussian process method, and compared the area under the curve (AUC) with a model based on NPT test results.

Results:

Sixteen children (ND, n=9; DD, n=7) participated in this study. Their developmental abilities had been assessed before they started to use a serious game. Statistically significant differences were found in both groups. Specifically, ND group was more developed than DD group in the order of social function, gross motor, full scale IQ, and visual motor imitation. Similarly, in the GDI, ND group obtained a higher score than DD group. In the correlation analysis between GDI and NPT, ND group showed greater correlation with most variables than DD group did. The GDI-based model had an AUC=0.9, which showed a similar detection value compared with the NPT-based model’s AUC=0.86.

Conclusions:

A GDI from serious game can detect children with heterogenous developmental disabilities. This suggests that serious games can be used as a potential screening tool for developmental disabilities. Clinical Trial: The trial has been registered at Clinical Research Information Service (ref number: KCT0003247).