Clinical Evaluation of the Measurement Performance of the Philips Health Watch: A Within-Person Comparative Study
Bibliographic record
Abstract
BACKGROUND: Physical inactivity is an important modifiable risk factor for chronic diseases. A new wrist-worn heart rate and activity monitor has been developed for unobtrusive data collection to aid prevention and management of lifestyle-related chronic diseases by means of behavioral change programs. OBJECTIVE: The objective of the study was to evaluate the performance of total energy expenditure and resting heart rate measures of the Philips health watch. Secondary objectives included the assessment of accuracy of other output parameters of the monitor: heart rate, respiration rate at rest, step count, and activity type recognition. METHODS: A within-person comparative study was performed to assess the performance of the health watch against (medical) reference measures. Participants executed a protocol including 15 minutes of rest and various activities of daily life. A two one-sided tests approach was adopted for testing equivalence. In addition, error metrics such as mean error and mean absolute percentage error (MAPE) were calculated. RESULTS: ) completed the 81-minute protocol. Their mean resting heart rate in beats per minute (bpm) was 64 (SD 7.3). With a mean error of -10 (SD 38.9) kcal and a MAPE of 10% (SD 8.7%), total energy expenditure estimation of the health watch was found to be within the 15% predefined equivalence margin in reference to a portable indirect calorimeter. Resting heart rate determined during a 15-minute rest protocol was found to be within a 10% equivalence margin in reference to a wearable electrocardiogram (ECG) monitor, with a mean deviation of 0 bpm and a maximum deviation of 3 bpm. Heart rate was within 10 bpm and 10% of the ECG monitor reference for 93% of the duration of the protocol. Step count estimates were on average 21 counts lower than a waist-mounted step counter over all walking activities combined, with a MAPE of 3.5% (SD 2.4%). Resting respiration rate was on average 0.7 (SD 1.1) breaths per minute lower than the reference measurement by the spirometer embedded in the indirect calorimeter during the 15-minute rest, resulting in a MAPE of 8.3% (SD 7.0%). Activity type recognition of walking, running, cycling, or other was overall 90% accurate in reference to the activities performed. CONCLUSIONS: The health watch can serve its medical purpose of measuring resting heart rate and total energy expenditure over time in an unobtrusive manner, thereby providing valuable data for the prevention and management of lifestyle-related chronic diseases. TRIAL REGISTRATION: Netherlands trial register NTR5552; http://www.trialregister.nl/trialreg/admin/rctview.asp?TC=5552 (Archived by WebCite at http://www.webcitation.org/6neYJgysl).
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 | 0.009 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 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".