AI-Assisted Dynamic Postural Control Screening to Improve Functional Mobility in Older Adult Populations: Quasi-Experimental Study
Bibliographic record
Abstract
Background: Falls are a major cause of disability among older adults, and early identification of functional decline is essential for prevention. Artificial intelligence (AI) systems may enhance mobility screening by providing objective, real-time feedback. Objective: This study aimed to evaluate whether AI-assisted dynamic postural control screening combined with adaptive training improves functional mobility outcomes in older adult populations. Methods: A quasi-experimental study was conducted with 2005 older adults recruited from community centers and health care institutions in Keelung, Taiwan. Participants were assigned to either an experimental group (n=1451), which underwent AI-assisted screening with adaptive exercise prescriptions, or a control group (n=554), which completed follow-ups through regular physical assessments with standard care without AI-tailored training. The AI system integrated skeletal tracking with the Short Physical Performance Battery to assess balance, gait speed (4-m walk), and sit-to-stand performance. Independent-samples 2-tailed t tests and repeated-measures ANOVA were applied, and effect sizes (Cohen d and η²) with 95% CIs were reported. Results: The experimental group demonstrated significantly greater improvements compared with the control group in Short Physical Performance Battery scores (Δ=0.8 vs 0.3; t2003=3.41; P=.001; Cohen d=0.45, 95% CI 0.18-0.72), gait speed (Δ=15 cm/s vs 5 cm/s; t2003=4.85; P<.001; Cohen d=0.62, 95% CI 0.35-0.88), and sit-to-stand time (Δ=-1.4 s vs -0.6 s; t2003=3.12; P=.002; Cohen d=0.39, 95% CI 0.12-0.65). Here "Δ" refers to the change score, calculated as post-intervention minus baseline (ie, the amount of improvement during the study period). Participation rate was strongly associated with outcomes, with 1-way ANOVA showing significant group differences (F2,1448=8.74-12.21; P<.001; η²=0.07-0.10). Conclusions: AI-assisted dynamic postural control screening combined with adaptive training substantially improved functional performance in mobility, balance, and gait among older adults. While fall incidence was not directly measured, these functional gains may have implications for fall risk reduction. Future longitudinal studies with extended follow-up (12-24 mo) and prospective fall incidence tracking across diverse populations are required to validate whether these improvements translate into actual reductions in fall risk.
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 | 0.001 | 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 | 0.001 | 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) | 0.000 | 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".