In 2017, Vandenberk et al. compared the results of FibriCheck’s heart rate analysis with two FDA-approved heart rate devices - Nonin (Nonin Medical Inc.) and KardiaMobile (AliveCor Inc.). The results of this study demonstrate that FibriCheck can accurately determine the heart rate as there were no significant differences between the results from the FibriCheck app (PPG), Nonin device (PPG), and AliveCor device (ECG). In a second study, Vandenberk et al. (2017) evaluated the beat-to-beat accuracy in simultaneous measurements from the FibriCheck app (PPG) and a single-lead wearable ECG patch. The results of this study show a positive correlation of 99.3% between synchronized beat-to-beat intervals (PPG) and RR-intervals (ECG). No significant differences in beat-to-beat intervals were found between the FibriCheck app and the ECG device (P=0.92). These findings demonstrate that FibriCheck can be used as a clinically validated app for measuring heart rate.
Various studies were performed to clinically validate the performance of the FibriCheck algorithm to accurately differentiate AF from non-AF recordings in adults. These validation studies demonstrated that cardiac rhythm analysis via a smartphone-based PPG signal, combined with the FibriCheck algorithm yielded high sensitivity and specificity to detect or rule out AF. Performance metrics from these validation studies are consolidated in the table below:
|
Title |
Sensitivity |
Specificity |
Accuracy |
PPV |
NPV |
|---|---|---|---|---|---|
| Comparative evaluation of consumer wearable devices for atrial fibrillation detection: A validation study |
100% |
98.9% |
99.2% |
- |
- |
|
98.3% |
99.9% |
- |
99.6% |
99.6% |
|
|
98% (cohort 1) 97% (cohort 2) |
96% (cohort 1) 100% (cohort 2) |
97% (cohort 1) 99% (cohort 2) |
96% (cohort 1) 100% (cohort 2) |
99% (cohort 1) 97% (cohort 2) |
|
|
93% |
98% |
98% |
- |
- |
|
|
98% |
94% |
96% |
- |
- |
|
|
Evaluation of the device independent nature of a photoplethysmography-deriving smartphone app |
91% to 100% |
95% to 100% |
94% to 99% |
- |
- |
|
Measurement level: 79% Subject level: 100% |
Measurement level: 98% Subject level: 96% |
Measurement level: 96% Subject level: 85% |
Measurement level: 85% Subject level: 98% |
Measurement level: 98% Subject level: 97% |
|
|
Measurement level: 95% Subject level: 96% |
Measurement level: 96% Subject level: 97% |
Measurement level: 96% Subject level: 96% |
Measurement level: 95% Subject level: 96% |
Measurement level: 97% Subject level: 97% |
|
|
81% |
97% |
91% |
95% |
89% |
|
|
100% |
98% |
98% |
- |
- |
|
|
100% |
96% |
- |
- |
- |
|
|
100% |
97% |
- |
- |
- |
The majority of these studies compared the performance of the FibriCheck algorithm with the results from (single-lead) ECG devices and demonstrated a substantial equivalence between the performance of the FIbriCheck algorithm and (single-lead) ECG devices such as KardiaMobile.
In addition to these studies, Elnur et al. (2021) assessed the use of FibriCheck for the early detection of AF and initiation of appropriate treatment. Interestingly, FibriCheck identified 11 patients (5.5%) with possible AF based on the longitudinal PPG measurements, and all these patients underwent a confirmatory 24h Holter examination, resulting in 100% confirmation of the FibriCheck results.
Find a full overview of all publications on our algorithm here. |
Information retrieved from the following peer-reviewed publications
-
Clinical Validation of Heart Rate Apps- Mixed-Methods Evaluation Study - Vandenberk et al, 2017
-
Evaluating smartphone-based photoplethysmography as a screening solution for atrial fibrillation A digital tool to detect AF? - Grieten et al, 2017
-
Screening for atrial fibrillation using only a smartphone application - a new tool to unlock digital screening - Grieten et al, 2017
-
Evaluation of screening technologies and assessments in a voluntary screening programme in the general belgian population - Proesmans et al, 2018
-
Mobile Phone–Based Use of the Photoplethysmography Technique to Detect Atrial Fibrillation in Primary Care- Diagnostic Accuracy Study of the FibriCheck App - Proesmans et al, 2019
-
The diagnostic accuracy of a pulse-deriving smartphone application is device independent - Smeets et al, 2019
-
Assessment of a standalone photoplethysmography (PPG) algorithm for detection of atrial fibrillation on wristband-derived data - Selder et al, 2020
-
Evaluation of the device independent nature of a photoplethysmography-deriving smartphone app - Gruwez et al, 2021
-
Head-to-head comparison of proprietary PPG and single-lead ECG algorithms for atrial fibrillation detection - Gruwez et al, 2021
-
The use of a photoplethymography-deriving smartphone app to screen for atrial fibrillation in primary stroke prevention during the covid pandemic - Elnur et al, 2021
-
Smartphone-Based Screening for Atrial Fibrillation – Experiences from Bosnia and Herzegovina - Elnur et al, 2022
-
Performance of an artificial intelligence algorithm to detect atrial fibrillation on a 24-hour continuous photoplethysmography recording using a smartwatch: ACURATE study - Gruwez et al, 2021
-
Real-world validation of smartphone-based photoplethysmography for rate and rhythm monitoring in atrial fibrillation - Gruwez et al, 2024
Comments
0 comments
Please sign in to leave a comment.