The Combination Of Force Plate Posturography And Machine Learning Predicts Fall Risk In Older Adults
Bibliographic record
Abstract
Falls remain the leading cause of injury related hospitalizations, morbidity, and mortality amongst seniors. Additionally, postural instability increases as one ages. As such, a sensitive, reliable, and convenient method for predicting falls among older adults is crucial. Measuring centre of pressure deviation from force plate posturography has been shown to be an effective tool in predicting falls among older adults; however, the addition of machine-learning algorithms have not been directly evaluated. PURPOSE: To develop machine-learning models that can provide clinicians with rapid, objective decision support metrics for fall risk among older adults using force plate posturography. METHODS: Fifty community dwelling older adults completed a two-part test consisting of a Timed up & Go (TUG) portion and a force plate portion. Participants stood on a force plate with their centre of pressure (CoP) displayed on a screen in front of them. They were then prompted to shift their centre of pressure left and right to a box displayed on the screen, aiming to reach and maintain a stable position within the box for approximately 3 seconds. Participants were classified as Fallers (F, TUG≥13.5 s) or Non-Fallers (NF, TUG<13.5 s) and balance metrics were compared between groups. RESULTS: Multiscale vertical entropy (F: 43.9 ± 9.4; NF: 50.0 ± 8.9, p = 0.037), multivariate multiscale entropy (F: 42.2 ± 7.0; NF: 47.2 ± 8.7, p = 0.037), and phase angle variability about the frontal plane (F: 24.0 ± 3.0 rad; NF: 26.2 ± 3.5, p = 0.033) were significantly lower in F compared to NF. No other calculated balance metrics were significantly different between groups. The developed machine-learning algorithm was able to correctly classify fallers and non-fallers (AUC = 0.73). CONCLUSION: Fallers may have a reduced ability to make fine adjustments in their movement in order to maintain balance compared to non-fallers. F can be classified based on three metrics largely related to the complexity of movement and the inability to control small, complex movements of the centre of pressure. Individuals at risk of falls can be classified objectively using machine-learning analysis of force plate posturography. Supported by Mount Royal University's Innovation Fund Grant
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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 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".