[Back]

M. Bachler, C. Mayer, B. Hametner, S. Wassertheurer:
"Automatic detection of QRS complex, P and T wave in the electrocardiogram";
Talk: ASIM 2011, Winterthur, Schweiz; 2011-09-07 - 2011-09-09; in: "ASIM 2011", ZHAW School of Engineering, (2011), ISBN: 978-3-89967-733-1; 10 pages.

Every third death in developed countries is caused by cardiac diseases, which are the
number one cause of death. Duration and dynamic changes of certain intervals of the
ECG are well established indicators in the diagnosis of cardiac diseases. Furthermore,
several agencies require the assessment of the effect of newly developed drugs on the QT
interval.
Automated measurement and annotation of the ECG shows numerous advantages over
manual methods, therefore the long term aim is to develop an all-in-one device for data
acquisition and ECG analysis. The development process is conducted in different stages,
whereas the first step and short term aim described in this paper consists of creating
algorithms in MATLAB® and validating them against ECG signals manually annotated
by medical experts. This early stage is followed by porting all algorithms to the aimed
platform and finally by hardware-in-the-loop simulations coupling the measurement
hardware with the MATLAB® model.
The presented algorithm detects R peaks based on the signals amplitude and first
derivative as well as RR intervals. False positive detections due to artifacts are prevented
by analyzing the signal´s local statistic characteristics. These intermediate results are
automatically classified to distinguish normal heartbeats from potential premature
ventricular contractions. QRS complexes, P and T waves are detected by their first
derivative for each class of heartbeats and are separately refined for each detected
heartbeat.
The algorithm has been verified against four PhysioNet databases and achieved a
sensitivity of 98.5% and a positive predictive value of 98.3%, respectively.
These results are promising, but further work is still required to implement the
algorithm on an embedded system to build an easy to use all-in-one device.