TD‐P‐017: LONGITUDINAL, VISION‐BASED MONITORING OF CHANGES OF GAIT IN DEMENTIA: A PILOT STUDY
Bibliographic record
Abstract
Impairments of gait and balance often progress through the course of dementia, and are associated with increased risk of falls. Regular assessment of gait and balance could therefore be informative in tracking changes in functional status, and identifying individuals at a high risk of falling to allow for preventative measures. We have developed a technology, called AMBIENT, which enables the frequent, accurate, unobtrusive, and cost-effective measurement of gait and balance parameters. The objective of this study was to demonstrate the feasibility of using AMBIENT for frequent assessment of mobility in people with dementia in a residential facility. We conducted a pilot longitudinal study with 20 participants (age: 76.9 ± 6.7 years, female: 50%) in the geriatric psychiatry unit at the Toronto Rehabilitation Institute, an eighteen-bed inpatient dementia care unit for older adults with behavioral symptoms. The AMBIENT setup included radio frequency identification to identify study participants and a Microsoft Kinect sensor to track body posture. The system automatically monitored participants’ gait as they walked within the view of the sensor during their daily routine and computed the spatiotemporal parameters of gait. Demographic and baseline descriptive measures were collected and falls events tracked. On average, 97 walking sequences per person were collected over a length of stay of 46 ± 37 days. There were 14 falls among study participants: 12 participants did not fall during their length of stay, 4 fell once, 2 fell twice, and 2 fell 3 times. Quantitative measures of gait were stride length (0.8 ± 0.1 m), stride time (1.4 ± 0.2 s), cadence (89.3 ± 18.1 steps/min), velocity (0.6 ± 0.1 m/s), step length asymmetry (1.2 ± 0.6), and step time asymmetry (1.2 ± 0.5).
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".