Case-control accuracy study for TOY8 digital developmental screening tool for detecting delays among children aged 3–5 years
Bibliographic record
Abstract
Background: Developmental delays affect up to 18% of children worldwide, particularly in disadvantaged populations. Early identification is critical; however, existing tools are often resource-intensive, language-dependent, and unsuitable for large-scale use in low- and middle-income countries. TOY8 is a smartphone-based, play-oriented developmental screening tool developed in Malaysia for children aged 3-5 years, available in Malay and English. Purpose: To validate TOY8 against the Griffiths Scales of Child Development, 3rd Edition (Griffiths III), determine optimal cut-offs, and assess parental perceptions of feasibility and acceptability. Methods: We conducted a case-control study in Sarawak, Malaysia. Participants underwent TOY8 screening followed by Griffiths III assessment. Screening performance was evaluated using sensitivity, specificity, likelihood ratios, and receiver operating characteristic (ROC) analyses. Optimal cut-offs were derived by maximizing sensitivity while maintaining specificity at ≥0.6. Parental perceptions were measured using questionnaires. Results: We recruited 127 children (64 with developmental delay, 63 without). TOY8 demonstrated good sensitivity (0.77) for detecting any developmental delay and higher sensitivity for severe delay (0.84). Cognitive, speech-language, and fine motor domains demonstrated excellent discrimination (AUC 0.82-0.84), but lower sensitivity for gross motor (0.41-0.54) and personal-adaptive domains (0.59-0.64). Refined domain-specific cut-offs (ROC: 44-50) improve screening accuracy. Parents rated TOY8 highly: 98.4% found it easy/very easy to use, 99.2% useful, and 96.9% acceptable. Conclusion: TOY8, the first digital developmental screening tool validated in Malaysia, demonstrated good accuracy, particularly in domains predictive of school readiness. Its brevity, ease of use, and strong parental acceptability support its feasibility for community and preschool settings. TOY8 offers a scalable solution for early detection in resource-limited contexts, directly advancing United Nations Sustainable Development Goal (SDG) 3 on health and well-being, and SDG 10 on reducing inequalities by improving access to developmental screening in underserved populations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".