Using Accelerometer Data to Identify Physical Activity Profiles in the Osteoarthritis Initiative
Bibliographic record
Abstract
Introduction: Osteoarthritis is a chronic joint disease with no current cure, affecting around 500 million people worldwide. Evidence suggests that physical activity has beneficial effects, but the ideal “prescription” of exercise remains unknown. The Osteoarthritis Initiative is a longitudinal, prospective, observational study with over 10 years of follow-up with accelerometer data from 2712 subjects. In this project, we used a data-driven approach to identify physical activity patterns based on daily accelerometer information. Using these patterns, we established profiles and determined if associations exist between the created profiles and known correlates and symptomatic outcomes of osteoarthritis such as pain. Methods: Physical activity curves for subjects with accelerometer data from the Osteoarthritis Initiative were aligned using curve registration methods. Once curves were aligned, subjects were grouped into profiles using k-medoid clustering. The outcome of pain was measured by the total Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score. A linear regression model was used to determine if an association exists between the defined profiles and the total WOMAC score. Results: K-medoid clustering of physical activity curves resulted in two profiles. However, there was no association between the defined profiles and the total WOMAC score at the alpha level of 0.05. Discussion: The developed profiles are not associated with the total WOMAC score. While the created profiles are not associated with symptomatic outcomes, it is of interest to explore if they provide prediction abilities for structural outcomes such as joint space width and radiographic classification of osteoarthritis such as the Kellgren-Lawrence score.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".