Real-World Wrist-Derived Digital Mobility Outcomes in People with Multiple Long-Term Conditions: A Comparison of Algorithms
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Digital Mobility outcomes can serve as objective biomarkers of health, but their validation in populations with multiple long-term conditions (MLTCs) based on wrist-worn devices remains unexplored. We refined, improved, and introduced novel algorithms, specifically tailored and adapted for (i) gait sequence detection, (ii) initial contact identification, and (iii) stride length estimation from a single wrist-worn device. Validation was performed using data from 28 participants with co-occurring MLTCs performing a 2.5 h real-world monitoring session. Reference data from an established multi-sensor system were used to assess algorithm performance across diverse gait patterns of co-occurring MLTCs. Twenty-eight participants (mean age 70.4 years, 43% females) had a median of three co-occurring MLTCs. Among six gait sequence detection methods, improved versions of the Kheirkhahan algorithm performed best (accuracy = 0.92, specificity = 0.96). For initial contact detection (nine methods tested), Shin's algorithm achieved the highest performance index (0.85) followed by McCamley (0.84). Stride length estimation was most accurate using novel approaches based on the Weinberg method (performance index > 0.70). The proposed fine-tuned algorithms, the newly developed adaptive variants, and the foot-length augmented versions demonstrated robust performance, surpassing many existing methods and addressing the complexity of gait patterns in MLTCs. These findings enable scalable, real-time mobility monitoring in complex clinical populations using accessible wearable technology.
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.
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 it