A Clinical Guide to Evaluate Heart Rate Related Smartphone Applications
|
If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL). |
Abstract
Background
Smartphone applications are widely used among consumers and patients, and a large variety of health-related apps are easily accessible in the various mobile app-stores. The medical world is rather reluctant in using these healthcare-related applications since there is no standardization, guidelines or quality label available.
Objectives
The aim of this study is to compose a guide for clinicians that maps and evaluates various healthcare apps to obtain an objective evaluation. As proof-of-principle, apps with heart-rate detection were targeted.
Methods
The existing literature and marketplaces of healthcare apps were examined and heart rate-related apps were selected based on popularity/number of downloads and functionality for qualitative testing, clinical validation and in-depth analysis. This will include areas such as data acquisition methods, design, security and privacy measures, clinical accuracy, remote monitoring capabilities, data storage and personal health record integration.
Results
Evaluation of both iOS and Android marketplaces resulted in (n=189) heart rate measuring apps. Four categories could be identified based on the method of data acquisition: (1) heart rate recording based on front facing camera to measure blood flow based on changes in face color (n=14), (2) placing a finger on the rear camera to record the photoplethysmogram (n=99), (3) using an external recording device (n=69) or (4) based on sound by placing the microphone on the chest (n=7). Only one application was able to provide a diagnosis on the heart rhythm of the patient (i.e. atrial fibrillation diagnosis). In (n=17) applications there was sufficient patient education. In (n=4) applications HIPAA compliant security protocols were in place and only a fragment (n=3) supported the possibility for remote monitoring. No application enabled the integration of data into a personal health record.
A subset of these heart rate apps have been selected and extensively tested to obtain insight in their clinical validation and usability. The applications were compared to the gold standard ECG. Apps based on recording the heart rate using external recording devices and finger placement on the camera showed in all settings no significant differences compared to the gold standard (p=0.267 and p=0.825 respectively). Apps with other acquisition techniques lacked accuracy in bad illuminated or noisy environments. The only smartphone application that could provide a diagnosis for heart rhythm disorders, was highly inaccurate and showed sensitivities and specificities below 25%.
Conclusion
Healthcare-related apps should be screened before usage and regulatory requirements and quality labels are important to assess the clinical value and accuracy. To tackle these issues, a clear protocol and checklist was created and despite some good clinical correlations, there was no heart rate-based smartphone application, nor the ones compliant to the FDA regulations, that passed our test bench. There is definitely a clear need to establish a quality label that should prove the clinical and technical validation besides other parameters such as security, remote monitoring capabilities, storage, and education.
Smartphone applications are widely used among consumers and patients, and a large variety of health-related apps are easily accessible in the various mobile app-stores. The medical world is rather reluctant in using these healthcare-related applications since there is no standardization, guidelines or quality label available.
Objectives
The aim of this study is to compose a guide for clinicians that maps and evaluates various healthcare apps to obtain an objective evaluation. As proof-of-principle, apps with heart-rate detection were targeted.
Methods
The existing literature and marketplaces of healthcare apps were examined and heart rate-related apps were selected based on popularity/number of downloads and functionality for qualitative testing, clinical validation and in-depth analysis. This will include areas such as data acquisition methods, design, security and privacy measures, clinical accuracy, remote monitoring capabilities, data storage and personal health record integration.
Results
Evaluation of both iOS and Android marketplaces resulted in (n=189) heart rate measuring apps. Four categories could be identified based on the method of data acquisition: (1) heart rate recording based on front facing camera to measure blood flow based on changes in face color (n=14), (2) placing a finger on the rear camera to record the photoplethysmogram (n=99), (3) using an external recording device (n=69) or (4) based on sound by placing the microphone on the chest (n=7). Only one application was able to provide a diagnosis on the heart rhythm of the patient (i.e. atrial fibrillation diagnosis). In (n=17) applications there was sufficient patient education. In (n=4) applications HIPAA compliant security protocols were in place and only a fragment (n=3) supported the possibility for remote monitoring. No application enabled the integration of data into a personal health record.
A subset of these heart rate apps have been selected and extensively tested to obtain insight in their clinical validation and usability. The applications were compared to the gold standard ECG. Apps based on recording the heart rate using external recording devices and finger placement on the camera showed in all settings no significant differences compared to the gold standard (p=0.267 and p=0.825 respectively). Apps with other acquisition techniques lacked accuracy in bad illuminated or noisy environments. The only smartphone application that could provide a diagnosis for heart rhythm disorders, was highly inaccurate and showed sensitivities and specificities below 25%.
Conclusion
Healthcare-related apps should be screened before usage and regulatory requirements and quality labels are important to assess the clinical value and accuracy. To tackle these issues, a clear protocol and checklist was created and despite some good clinical correlations, there was no heart rate-based smartphone application, nor the ones compliant to the FDA regulations, that passed our test bench. There is definitely a clear need to establish a quality label that should prove the clinical and technical validation besides other parameters such as security, remote monitoring capabilities, storage, and education.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
This work is licensed under a Creative Commons Attribution 3.0 License.