Monitoring of child-specific activities in ambulatory children with and without developmental disabilities
Bibliographic record
Abstract
BACKGROUND: Pediatric healthcare professionals facilitate children to enhance and maintain a physically active lifestyle. Activity monitors (AM) can help pediatric healthcare professionals assess physical activity in everyday life. However, validation research of activity monitors has often been conducted in laboratories and insight into physical activity of children in their own everyday environment is lacking. Our goal was to study the criterion validity of a prototype AM (AM-p) model in a natural setting. METHODS: Cross-sectional community-based study with ambulatory children (2-19 years) with and without developmental disability. Children wore the AM-p on the ankle and were filmed (gold standard) while performing an activity protocol in a natural setting. We labelled all videos per 5-second epoch with individual activity labels. Raw AM-p data were synchronized with activity labels. Using machine learning techniques, activity labels were subdivided in three pre-defined categories. Accuracy, recall, precision, and F1 score were calculated per category. RESULTS: We analyzed data of 93 children, of which 28 had a developmental disability. Mean age was 11 years (SD 4.5) with 55% girls. The AM-p model differentiated between 'stationary', 'cycling' and 'locomotion' activities with an accuracy of 82%, recall of 78%, precision of 75%, and F1 score of 75%, respectively. Children older than 13 years with typical development can be assessed more accurately than younger children (2-12 years) with and without developmental disabilities. CONCLUSION: The single ankle-worn AM-p model can differentiate between three activity categories in children with and without developmental disabilities with good accuracy (82%). Because the AM-p can be used for a heterogenous group of ambulatory children with and without developmental disabilities, it may support the clinical assessment for pediatric healthcare professionals in the future.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".