Personalized physical activity recommendations for people with axial spondyloarthritis using wearable activity tracker data: an exploratory study
Bibliographic record
Abstract
OBJECTIVE: Benefits of physical activity (PA) on sleep in people with axial SpondyloArthritis (axSpA) are largely unknown. Our aim is to explore the relationships between PA and sleep on both a group level and an individual level using Wearable Activity Trackers (WATs) and machine learning. METHODS: A sample of 64 axSpA participants received a WAT to monitor their PA and sleep. Participants with more than 30 days data of PA and sleep duration were included in the analyses. Spearman's correlation and the machine learning technique Subgroup Discovery were used to determine relationships between PA during the three prior days and light and deep sleep duration. RESULTS: Number of daily steps (n = 64) was (median (first quartile (Q1) - third quartile (Q3) )) 4026 (1915 - 6549), total sleep (daily light and deep sleep) duration of the participants was 7 h 29 min (6 h 41 min - 8 h 8 min). Nearly 30% (n = 18) of the participants were eligible for inclusion in analyses (> 30 days of data). No significant relationships between prior PA and sleep were obtained on a group level. On an individual level, for 8 of the 18 included participants, significant relationships (p < 0.05) could be identified between PA during the three prior days and daily sleep duration. These significant relationships differed from participant to participant with a varying qualification of PA (number of steps, intensity level PA) and relevant time window (previous one, two or three days). CONCLUSION: Significant relationships between PA and daily sleep duration could be obtained on an individual level with details of the significant relationships varying between participants. REGISTRATION NUMBER: Netherlands Trial Register NL8238, included in the International Clinical Trial Registry Platform (ICTRP) ( https://trialsearch.who.int/Trial2.aspx?TrialID=NL8238 ).
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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 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".