Clinical Validation of Heart Rate Apps: Mixed-Methods Evaluation Study
Bibliographic record
Abstract
BACKGROUND: Photoplethysmography (PPG) is a proven way to measure heart rate (HR). This technology is already available in smartphones, which allows measuring HR only by using the smartphone. Given the widespread availability of smartphones, this creates a scalable way to enable mobile HR monitoring. An essential precondition is that these technologies are as reliable and accurate as the current clinical (gold) standards. At this moment, there is no consensus on a gold standard method for the validation of HR apps. This results in different validation processes that do not always reflect the veracious outcome of comparison. OBJECTIVE: The aim of this paper was to investigate and describe the necessary elements in validating and comparing HR apps versus standard technology. METHODS: The FibriCheck (Qompium) app was used in two separate prospective nonrandomized studies. In the first study, the HR of the FibriCheck app was consecutively compared with 2 different Food and Drug Administration (FDA)-cleared HR devices: the Nonin oximeter and the AliveCor Mobile ECG. In the second study, a next step in validation was performed by comparing the beat-to-beat intervals of the FibriCheck app to a synchronized ECG recording. RESULTS: In the first study, the HR (BPM, beats per minute) of 88 random subjects consecutively measured with the 3 devices showed a correlation coefficient of .834 between FibriCheck and Nonin, .88 between FibriCheck and AliveCor, and .897 between Nonin and AliveCor. A single way analysis of variance (ANOVA; P=.61 was executed to test the hypothesis that there were no significant differences between the HRs as measured by the 3 devices. In the second study, 20,298 (ms) R-R intervals (RRI)-peak-to-peak intervals (PPI) from 229 subjects were analyzed. This resulted in a positive correlation (rs=.993, root mean square deviation [RMSE]=23.04 ms, and normalized root mean square error [NRMSE]=0.012) between the PPI from FibriCheck and the RRI from the wearable ECG. There was no significant difference (P=.92) between these intervals. CONCLUSIONS: Our findings suggest that the most suitable method for the validation of an HR app is a simultaneous measurement of the HR by the smartphone app and an ECG system, compared on the basis of beat-to-beat analysis. This approach could lead to more correct assessments of the accuracy of HR apps.
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 | 0.076 | 0.101 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.005 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".