We developed an application for AndroidTM-based
mobile devices that allows real-time electrocardiogram (ECG)
monitoring and automated arrhythmia detection by analyzing
ECG parameters. ECG data provided by pre-recorded files
or acquired live by accessing a ShimmerTM sensor node via
BluetoothTM can be processed and evaluated. The application is
based on the Pan-Tompkins algorithm for QRS-detection and
contains further algorithm blocks to detect abnormal heartbeats.
The algorithm was validated using the MIT-BIH Arrhythmia
and MIT-BIH Supraventricular Arrhythmia databases. More
than 99% of all QRS complexes were detected correctly by the
algorithm. Overall sensitivity for abnormal beat detection was
89.5% with a specificity of 80.6%. The application is available
for download and may be used for real-time ECG-monitoring
on mobile devices.