Automated movement recognition to predict motor impairment in high‐risk infants: a systematic review of diagnostic test accuracy and meta‐analysis
Bibliographic record
Abstract
Aim To assess the sensitivity and specificity of automated movement recognition in predicting motor impairment in high‐risk infants. Method We searched MEDLINE, Embase, PsycINFO, CINAHL, Web of Science, and Scopus databases and identified additional studies from the references of relevant studies. We included studies that evaluated automated movement recognition in high‐risk infants to predict motor impairment, including cerebral palsy (CP) and non‐CP motor impairments. Two authors independently assessed studies for inclusion, extracted data, and assessed methodological quality using the Quality Assessment of Diagnostic Accuracy Studies‐2. Meta‐analyses were performed using hierarchical summary receiver operating characteristic models. Results Of 6536 articles, 13 articles assessing 59 movement variables in 1248 infants under 5 months corrected age were included. Of these, 143 infants had CP. The overall sensitivity and specificity for motor impairment were 0.73 (95% confidence interval [CI] 0.68–0.77) and 0.70 (95% CI 0.65–0.75) respectively. Comparatively, clinical General Movements Assessment (GMA) was found to have sensitivity and specificity of 98% (95% CI 74–100) and 91% (95% CI 83–93) respectively. Sensor‐based technologies had higher specificity (0.88, 95% CI 0.80–0.93). Interpretation Automated movement recognition technology remains inferior to clinical GMA. The strength of this study is its meta‐analysis to summarize performance, although generalizability of these results is limited by study heterogeneity. What this paper adds Automated movement recognition is sensitive and specific and warrants further investigation. Sensor‐based technologies have higher specificity but are less portable. The performance of automated movement recognition is inferior to clinical General Movements Assessment. Emerging technologies such as 3D video analysis may improve its performance.
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 | 0.002 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.011 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".