Validation of heart rate measurement of Fitbit Charge 4 and Xiaomi Mi Band 5 (Preprint)

2021 ◽  
Author(s):  
Magdalena Jachymek ◽  
Michał Tomasz Jachymek ◽  
Radosław Marek Kiedrowicz ◽  
Jarosław Kaźmierczak ◽  
Małgorzata Peregud-Pogorzelska
Keyword(s):  
Heart Rate ◽  
Stress Test ◽  
Absolute Error ◽  
Sensor Technology ◽  
Concordance Correlation ◽  
Accuracy And Precision ◽  
Validation Criteria ◽  
Precision And Accuracy ◽  
Fitness Trackers ◽  
Error Percentage

BACKGROUND Recent advances in mobile sensor technology have led to increased popularity of wrist-worn fitness trackers. The possibility to use a smartwatch as a rehabilitation tool to monitor patients’ heart rate during exercise has won the attention of many researchers. OBJECTIVE The aim of the study was to evaluate the accuracy and precision of HR measurement performed by two wrist monitors: Fitbit Charge 4 (Fitbit) and Xiaomi Mi Band 5 (Xiaomi). METHODS 31 healthy volunteers were asked to perform a stress test on a treadmill. During the test their heart rate was recorded simultaneously by both wristbands and ECG at 1minute intervals. The mean absolute error percentage (MAPE), Lin’s concordance correlation coefficient (LCCC) and Bland-Altman were calculated to compare precision and accuracy of heart rate measurements. The estimated validation criteria were MAPE < 10% and LCCC < .8 RESULTS The overall MAPE of the Fitbit device was 10.19% (±11.79%) and the MAPE of Xiaomi was (6.89 % ± 9.75). LCCC of Fitbit HR measurements was .753 (95% CI:0.717-0.785) and of Xiaomi – .903 (0.886-0.917). In both devices the precision and accuracy were decreasing with the increasing exercise intensity. Age, sex, height, weight, BMI did not influence the accuracy of both devices. CONCLUSIONS The accuracy of a wearable wrist-worn heart rate monitor varies and depends on the intensity of training. The decision concerning the application of such a device as a monitor during in-home rehabilitation should be taken with caution, as it may prove not reliable enough.

scholarly journals Wristbands in Home-Based Rehabilitation—Validation of Heart Rate Measurement

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 60
Author(s):  
Magdalena Jachymek ◽  
Michał T. Jachymek ◽  
Radosław M. Kiedrowicz ◽  
Jarosław Kaźmierczak ◽  
Edyta Płońska-Gościniak ◽  
...  
Keyword(s):  
Heart Rate ◽  
Stress Test ◽  
Absolute Error ◽  
Concordance Correlation ◽  
Heart Rates ◽  
Home Based ◽  
Accuracy And Precision ◽  
Validation Criteria ◽  
Precision And Accuracy ◽  
Electrocardiogram Ecg

The possibility of using a smartwatch as a rehabilitation tool to monitor patients’ heart rates during exercise has gained the attention of many researchers. This study aimed to evaluate the accuracy and precision of the HR measurement performed by two wrist monitors: the Fitbit Charge 4 and the Xiaomi Mi Band 5. Thirty-one healthy volunteers were asked to perform a stress test on a treadmill. Their heart rates were recorded simultaneously by the wristbands and an electrocardiogram (ECG) at 1 min intervals. The mean absolute error percentage (MAPE), Lin’s concordance correlation coefficient (LCCC), and Bland–Altman analysis were calculated to compare the precision and accuracy of heart rate measurements. The estimated validation criteria were MAPE < 10% and LCCC < 0.8. The overall MAPE and LCCC of the Fitbit were 10.19% (±11.79%) and 0.753 (95% CI: 0.717–0.785), respectively. The MAPE and LCCC of the Xiaomi were 6.89% (±9.75) and 0.903 (0.886–0.917), respectively. The precision and accuracy of both devices decreased with the increased exercise intensity. The accuracy of wearable wrist-worn heart rate monitors varies and depends on the intensity of training. Therefore, the decision to use such a device as a heart rate monitor during in-home rehabilitation should be made with caution.

scholarly journals CardiacProfileR: An R package for extraction and visualisation of heart rate profiles from wearable fitness trackers

2018 ◽  
Author(s):  
Djordje Djordjevic ◽  
Beni K. Cawood ◽  
Sabrina K. Rispin ◽  
Anushi Shah ◽  
Leo H. H. Yim ◽  
...  
Keyword(s):  
Physical Activity ◽  
Heart Rate ◽  
Stress Test ◽  
R Package ◽  
Exercise Stress ◽  
Stress Tests ◽  
Activity Data ◽  
Physical Activity Data ◽  
Rate Profile ◽  
Fitness Trackers

AbstractA person’s heart rate profile, which consists of resting heart rate, increase of heart rate upon exercise and recovery of heart rate after exercise, is traditionally measured by electrocardiography during a controlled exercise stress test. A heart rate profile is a useful clinical tool to identify individuals at risk of sudden death and other cardiovascular conditions. Nonetheless, conducting such exercise stress tests routinely is often inconvenient and logistically challenging for patients. The widespread availability of affordable wearable fitness trackers, such as Fitbit and Apple Watch, provides an exciting new means to collect longitudinal heart rate and physical activity data. We reason that by combining the heart rate and physical activity data from these devices, we can construct a person’s heart rate profile. Here we present an open source R package CardiacProfileR for extraction, analysis and visualisation of heart rate dynamics during physical activities from data generated from common wearable heart rate monitors. This package represents a step towards quantitative deep phenotyping in humans. CardiacProfileR is available via an MIT license at https://github.com/VCCRI/CardiacProfileR.

scholarly journals Standard Area Diagram Set for Scab Evaluation in Fruits of sour Passion Fruit

2019 ◽  
Vol 11 (14) ◽  
pp. 298 ◽  
Author(s):  
Anne Pinheiro Costa ◽  
José Ricardo Peixoto ◽  
Luiz Eduardo Bassay Blum ◽  
Márcio de Carvalho Pires
Keyword(s):  
Absolute Error ◽  
Passion Fruit ◽  
Coefficient Of Determination ◽  
Concordance Correlation Coefficient ◽  
Simple Linear Regression ◽  
Concordance Correlation ◽  
Passiflora Edulis ◽  
Accuracy And Precision ◽  
Variation Range ◽  
Sour Passion Fruit

Scab (Cladosporium spp.) significantly comprises the commercial acceptance of sour passion fruit (Passiflora edulis) because of the deformed and atrophied fruit appearance resulting from the development of the lesions. Therefore, the objective of this study was to elaborate and validate a standard area diagram set (SADs) for the severity evaluation of scab in fruits of sour passion fruit. The SADs comprised eight severity levels (0.6; 1; 2; 4; 8; 16; 37; and 46%) and was validated by 20 raters (G1 and G3, inexperienced; G2 and G4, experienced). Initially, all raters performed a non-aided SADs evaluation of the scab severity. Afterward, G1 and G2 completed the second evaluation without the proposed SADs, whereas G3 and G4 performed a SADs-aided assessment of the disease severity. The accuracy and precision of the evaluations were determined by simple linear regression and by the Lin&rsquo;s concordance correlation coefficient. Constant and systematic errors decreased with the use of the SADs, demonstrating an approximation between the estimated and the actual values. Precision increased with an increase in the coefficient of determination. Also, the absolute error reduced by 66% (G3) and 47% (G4). Therefore, 94.4% (G3) and 98.8% (G4) of the estimates had up to &plusmn;10% of errors, which corresponds to a 20.4% (G3) and 5.6% (G4) increment in the estimates with errors within this variation range. As a result, accuracy and precision were higher in the SADs-aided groups. Inexperienced raters were the most benefited by the use of the SADs. The accuracy and precision of the non-aided groups had a slight or no increase when compared with the SADs-aided groups.

scholarly journals A Review of Deep Learning-Based Contactless Heart Rate Measurement Methods

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3719
Author(s):  
Aoxin Ni ◽  
Arian Azarang ◽  
Nasser Kehtarnavaz
Keyword(s):  
Heart Rate ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Video Camera ◽  
Measurement Methods ◽  
Rate Measurement ◽  
Learning Methods ◽  
The Public ◽  
Heart Rate Measurement

The interest in contactless or remote heart rate measurement has been steadily growing in healthcare and sports applications. Contactless methods involve the utilization of a video camera and image processing algorithms. Recently, deep learning methods have been used to improve the performance of conventional contactless methods for heart rate measurement. After providing a review of the related literature, a comparison of the deep learning methods whose codes are publicly available is conducted in this paper. The public domain UBFC dataset is used to compare the performance of these deep learning methods for heart rate measurement. The results obtained show that the deep learning method PhysNet generates the best heart rate measurement outcome among these methods, with a mean absolute error value of 2.57 beats per minute and a mean square error value of 7.56 beats per minute.

A new modification of the homotopy perturbation method

2021 ◽  
pp. 095745652199987
Author(s):  
Magaji Yunbunga Adamu ◽  
Peter Ogenyi
Keyword(s):  
Comparative Analysis ◽  
Error Analysis ◽  
Perturbation Method ◽  
Homotopy Perturbation Method ◽  
Nonlinear Oscillators ◽  
Absolute Error ◽  
New Method ◽  
Optimal Analysis ◽  
Homotopy Perturbation ◽  
Accuracy And Precision

This study proposes a new modification of the homotopy perturbation method. A new parameter alpha is introduced into the homotopy equation in order to improve the results and accuracy. An optimal analysis identifies the parameter alpha, aimed at improving the solutions. A comparative analysis of the proposed method reveals that the new method presents results with higher degree of accuracy and precision than the classic homotopy perturbation method. Absolute error analysis shows the convenience of the proposed method, providing much smaller errors. Two examples are presented: Duffing and Van der pol’s nonlinear oscillators to demonstrate the efficiency, accuracy, and applicability of the new method.

scholarly journals Contactless Video-Based Heart Rate Monitoring of a Resting and an Anesthetized Pig

Animals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 442
Author(s):  
Meiqing Wang ◽  
Ali Youssef ◽  
Mona Larsen ◽  
Jean-Loup Rault ◽  
Daniel Berckmans ◽  
...  
Keyword(s):  
Heart Rate ◽  
Estimation Error ◽  
Well Being ◽  
Absolute Error ◽  
Mean Value ◽  
Video Data ◽  
Window Functions ◽  
The Face ◽  
Short Time ◽  
Better Than

Heart rate (HR) is a vital bio-signal that is relatively easy to monitor with contact sensors and is related to a living organism’s state of health, stress and well-being. The objective of this study was to develop an algorithm to extract HR (in beats per minute) of an anesthetized and a resting pig from raw video data as a first step towards continuous monitoring of health and welfare of pigs. Data were obtained from two experiments, wherein the pigs were video recorded whilst wearing an electrocardiography (ECG) monitoring system as gold standard (GS). In order to develop the algorithm, this study used a bandpass filter to remove noise. Then, a short-time Fourier transform (STFT) method was tested by evaluating different window sizes and window functions to accurately identify the HR. The resulting algorithm was first tested on videos of an anesthetized pig that maintained a relatively constant HR. The GS HR measurements for the anesthetized pig had a mean value of 71.76 bpm and standard deviation (SD) of 3.57 bpm. The developed algorithm had 2.33 bpm in mean absolute error (MAE), 3.09 bpm in root mean square error (RMSE) and 67% in HR estimation error below 3.5 bpm (PE3.5). The sensitivity of the algorithm was then tested on the video of a non-anaesthetized resting pig, as an animal in this state has more fluctuations in HR than an anaesthetized pig, while motion artefacts are still minimized due to resting. The GS HR measurements for the resting pig had a mean value of 161.43 bpm and SD of 10.11 bpm. The video-extracted HR showed a performance of 4.69 bpm in MAE, 6.43 bpm in RMSE and 57% in PE3.5. The results showed that HR monitoring using only the green channel of the video signal was better than using three color channels, which reduces computing complexity. By comparing different regions of interest (ROI), the region around the abdomen was found physiologically better than the face and front leg parts. In summary, the developed algorithm based on video data has potential to be used for contactless HR measurement and may be applied on resting pigs for real-time monitoring of their health and welfare status, which is of significant interest for veterinarians and farmers.

scholarly journals Influence of a Suggestive Placebo Intervention on Psychobiological Responses to Social Stress

2015 ◽  
Vol 21 (1) ◽  
pp. 3-9 ◽  
Author(s):  
Frank Zimmermann-Viehoff ◽  
Nico Steckhan ◽  
Karin Meissner ◽  
Hans-Christian Deter ◽  
Clemens Kirschbaum
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Salivary Cortisol ◽  
Psychosocial Stress ◽  
Social Stress ◽  
Stress Test ◽  
Alpha Amylase ◽  
Subjective Stress ◽  
Psychological Variables ◽  
Placebo Intervention

We tested the hypothesis that a suggestive placebo intervention can reduce the subjective and neurobiological stress response to psychosocial stress. Fifty-four healthy male subjects with elevated levels of trait anxiety were randomly assigned in a 4:4:1 fashion to receive either no treatment (n = 24), a placebo pill (n = 24), or a herbal drug (n = 6) before undergoing a stress test. We repeatedly measured psychological variables as well as salivary cortisol, alpha-amylase, and heart rate variability prior to and following the stress test. The stressor increased subjective stress and anxiety, salivary cortisol, and alpha-amylase, and decreased heart rate variability (all P < .001). However, no significant differences between subjects receiving placebo or no treatment were found. Subjects receiving placebo showed increased wakefulness during the stress test compared with no-treatment controls ( P < .001). Thus, the suggestive placebo intervention increased alertness, but modulated neither subjective stress and anxiety nor the physiological response to psychosocial stress.

Mechanisms Underlying QT Interval Adaptation Behind Heart Rate During Stress Test

2021 ◽  
Author(s):  
Ruben Cebollada ◽  
Cristina Perez ◽  
Konstantinos A Mountris ◽  
Juan Pablo Martinez ◽  
Pablo Laguna ◽  
...  
Keyword(s):  
Heart Rate ◽  
Qt Interval ◽  
Stress Test

Impaired heart rate recovery may predict radial artery spasm in patients undergoing coronary angiography via radial access

2021 ◽  
Author(s):  
İsmail Gürbak ◽  
Arda Güler ◽  
Cafer Panç ◽  
Ahmet Güner ◽  
Mehmet Ertürk
Keyword(s):  
Heart Rate ◽  
Coronary Angiography ◽  
Radial Artery ◽  
Autonomic Dysfunction ◽  
Heart Rate Recovery ◽  
Stress Test ◽  
Female Gender ◽  
Current Data ◽  
Autonomic Nervous System Dysfunction ◽  
Procedural Time

Objectives: Radial artery spasm (RAS) is associated with several pathophysiological pathways, including endothelial and autonomic dysfunction, and causes failed coronary interventions. Heart rate recovery (HRR) is a simple measurement of autonomic nervous system dysfunction. We aimed to investigate the relationship between HRR and RAS during coronary angiography (CA) in the present study. Patients and Methods: This study included 167 patients (mean age 54.6 ± 8.2, 131 males) who underwent a treadmill stress test (TST) according to the Bruce protocol before trans-radial CA. HRR in the first minute (HRR1) was calculated as the difference between peak heart rate and heart rate one minute after the TST. Patients were divided into two groups according to the presence of RAS. Results: Among the study population, RAS developed in 26 patients (15.5%). HRR1 and HRR in the third minute (HRR3) were lower in the RAS group. Also, the abnormal HRR1 rate was higher in the RAS group (35.5% vs. 76.9%, p < 0.001). Total procedural time, more than one puncture attempt, more than one catheter use, fluoroscopy time, radiation exposure, contrast volume was higher in the RAS group. Female gender, total procedural time, more than one catheter use, and abnormal HRR1 were independent predictors of RAS. Conclusion: The current data suggest that a significant relationship was found between abnormal HRR1 and RAS. HRR, a simple autonomic dysfunction parameter, can provide additional information regarding the success of radial procedures.

scholarly journals Estimating Resting Core Temperature Using Heart Rate

2018 ◽  
Vol 1 (2) ◽  
pp. 79-86 ◽  
Author(s):  
David P. Looney ◽  
Mark J. Buller ◽  
Andrei V. Gribok ◽  
Jayme L. Leger ◽  
Adam W. Potter ◽  
...  
Keyword(s):  
Heart Rate ◽  
Core Temperature ◽  
Estimation Algorithm ◽  
Quadratic Equation ◽  
Estimation Accuracy ◽  
Future Research ◽  
Accuracy And Precision ◽  
Military Populations ◽  
Thermal Work ◽  
Ct Data

ECTemp™ is a heart rate (HR)-based core temperature (CT) estimation algorithm mainly used as a real-time thermal-work strain indicator in military populations. ECTemp™ may also be valuable for resting CT estimation, which is critical for circadian rhythm research. This investigation developed and incorporated a sigmoid equation into ECTemp™ to better estimate resting CT. HR and CT data were collected over two calorimeter test trials from 16 volunteers (age, 23 ± 3 yrs; height, 1.72 ± 0.07 m; body mass, 68.5 ± 8.1 kg) during periods of sleep and inactivity. Half of the test trials were combined with ECTemp™’s original development dataset to train the new sigmoid model while the other was used for model validation. Models were compared by their estimation accuracy and precision. While both models produced accurate CT estimates, the sigmoid model had a smaller bias (−0.04 ± 0.26°C vs. −0.19 ± 0.29°C) and root mean square error (RMSE; 0.26°C vs. 0.35°C). ECTemp™ is a validated HR-based resting CT estimation algorithm. The new sigmoid equation corrects lower CT estimates while producing nearly identical estimates to the original quadratic equation at higher CT. The demonstrated accuracy of ECTemp™ encourages future research to explore the algorithm’s potential as a non-invasive means of tracking CT circadian rhythms.

Sign in / Sign up

Export Citation Format

Share Document