QRS detection for pacemakers in a noisy environment using a time lagged artificial neural network

A time lagged feedforward artificial neural network (TLFN) is used to detect QRS complexes for pacemakers in a noisy environment. The TLFN reduces the influence of lower frequencies in the invasive electrogram (EG) signals, such as the P and T waves. The TLFN output is then subjected to matched filtering with a dynamically updated impulse response. Detector performance is studied by means of databases containing electrograms and noise such that different types of noise and interferences from electronic appliances are added to the electrograms. Results show that the detector performs well in many different noisy environments by considerably improving the signal-to-noise ratio (SNR)