Multisensor fusion for atrial and ventricular activity detection in coronary care monitoring

Information management for critical care monitoring is still a very difficu lt task. Medical staff is often overwhelmed by the amount of data provided by the increased number of specific monitoring devices and instrumentation, and the lack of an effective automated system. Specifically, a basic task such as arrhythmia detection still produce an important amount of undesirab le alarms, due in part to the mechanistic approach of current monitoring sy stems. In this work, multisensor and multisource data fusion schemes to imp rove atrial and ventricular activity detection in critical care environment s are presented. Applications of these schemes are quantitatively evaluated and compared with current methods, showing the potential advantages of dat a fusion techniques for event detection in noise corrupted signals.