Step Count Accuracy of the Life Plus Connected Watch at Different Localizations and Speeds in Healthy Adults, Patients With Cardiovascular Disease, and Patients With Peripheral Artery Disease: Step Count Validation Study in Laboratory Settings
Bibliographic record
Abstract
Background: Smartwatches are increasingly used to monitor and motivate physical activity. Patients with cardiovascular disease (CVD) and peripheral artery disease (PAD) often do not meet national physical activity recommendations. They may, thus, benefit from a physical activity program using smartwatches. The Life Plus smartwatch is designed to facilitate activity monitoring by counting steps, but its validity needs to be determined, particularly in patients who may not have a normal gait, such as those with cardiovascular pathology. Objective: This study evaluates the accuracy of the Life Plus smartwatch (versions 2 and 3) in healthy adults, patients with CVD, and patients with PAD at different walking speeds (1.8, 2.5, 3.2, and 4 km/h) and different localizations (wrists, hips, and ankles) to determine best accuracy. Methods: In total, 34 participants, comprising healthy individuals (n=10), patients with CVD (n=14), and patients with PAD (n=10), wore 6 Life Plus watches simultaneously (3 of version 2 and 3 of version 3), located on wrists, hips, and ankles. Participants walked on a treadmill for 3-minute sessions at speeds of 1.8, 2.5, 3.2, and 4 km/h; they then performed a 10-minute free walking on the ground and again walked for 3-minute sessions on a treadmill at the same speeds. Actual step counts were recorded through video footage. Results: When worn at the wrist, no significant difference between the actual number of steps and step count by version 2 watches was found in each group independently (healthy group: P=.25; CVD group: P=.50; and PAD group: P=.37). Significant differences were found with the version 2 watches at the wrist in the healthy group at 3.2 (-5.26%; P=.01) and 4 km/h (-6.13%; P=.008) and in the CVD group at 2.5 (-5.94%; P=.008), 3.2(-13.1%; P=.008), and 4 km/h (-13.96%; P=.004). When worn at the wrist, no significant difference between actual number of steps and step count by version 3 watches was found in the healthy group (P=.02) and the PAD group (P=.90). Significant differences were found with the version 3 watches at the wrist in the CVD group at 3.2 (-6.43%; P=.001) and 4 km/h (-7.3%; P=.01) and in the PAD group at 4 km/h (-5.77%; P=.04). Conclusions: For optimized counting when worn at the wrist, healthy individuals should prefer version 2 watches for slow walking (1.8 and 2.5 km/h) and version 3 for higher speeds (3.2 and 4 km/h). Patients (CVD and PAD) should prefer version 2 watches at 1.8 km/h and version 3 watches for higher speeds (2.5, 3.2, and 4 km/h).
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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".