Analyzability of Photoplethysmographic Smartwatch Data by the Preventicus Heartbeats Algorithm During Everyday Life: Feasibility Study
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
Background Continuous heart rate monitoring via mobile health technologies based on photoplethysmography (PPG) has great potential for the early detection of sustained cardiac arrhythmias such as atrial fibrillation. However, PPG measurements are impaired by motion artifacts. Objective The aim of this investigation was to evaluate the analyzability of smartwatch-derived PPG data during everyday life and to determine the relationship between the analyzability of the data and the activity level of the participant. Methods A total of 41 (19 female and 22 male) adults in good cardiovascular health (aged 19-79 years) continuously wore a smartwatch equipped with a PPG sensor and a 3D accelerometer (Cardio Watch 287, Corsano Health BV) for a period of 24 hours that represented their individual daily routine. For each participant, smartwatch data were analyzed on a 1-minute basis by an algorithm designed for heart rhythm analysis (Preventicus Heartbeats, Preventicus GmbH). As outcomes, the percentage of analyzable data (PAD) and the mean acceleration (ACC) were calculated. To map changes of the ACC and PAD over the course of one day, the 24-hour period was divided into 8 subintervals comprising 3 hours each. Results Univariate analysis of variance showed a large effect (ηp2> 0.6; P<.001) of time interval (phase) on the ACC and PAD. The PAD ranged between 34% and 100%, with an average of 71.5% for the whole day, which is equivalent to a period of 17.2 hours. Between midnight and 6 AM, the mean values were the highest for the PAD (>94%) and the lowest for the ACC (<6×10-3 m/s2). Regardless of the time of the day, the correlation between the PAD and ACC was strong (r=–0.64). A linear regression analysis for the averaged data resulted in an almost perfect coefficient of determination (r2=0.99). Conclusions This study showed a large relationship between the activity level and the analyzability of smartwatch-derived PPG data. Given the high yield of analyzable data during the nighttime, continuous arrhythmia screening seems particularly effective during sleep phases.
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 | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| 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