Fuzzy beat labeling for intelligent arrhythmia monitoring.

The performance in automatic diagnosis of cardiac rhythm based on the analysis of the electrocardiographic signal (ECG) is strongly conditioned by the correct classification of each beat detected. In this work we present a fuzzy classifier of beats that applies empiric criteria and that permits it to ignore the frequent lack of clarity in the information coming from previous stages within ECG processing. The classification of each beat is performed applying diffuse conditional statements which represent the knowledge of the cardiologist expert and that use a set of descriptions of the temporal and morphological attributes of the analyzed beat. The process of classification is completed with information derived from the consideration of "families," which group beats that have QRSs of similar morphology, and with information brought in by the user himself in the monitoring process. The modularity of the classifier that has been developed facilitates the incorporation of new descriptions and classification criteria in order to increase its reliability. The design process proposed has a structure that is transferable to other analysis and event classification processes.