Application of spatio-temporal filtering for atrial activity waveforms enhancement
Fecha
2019Registro en:
ACM International Conference Proceeding Series; pp. 67-72
9781450372435
10.1145/3365245.3365262
Universidad Tecnológica de Bolívar
Repositorio UTB
56520286300
55985160800
57202468264
7003612212
7004127726
57213685902
Autor
Giraldo-Guzmán J.
Kotas, Marian
Piela M.
Castells F.
Łęski J.M.
Contreras Ortiz, Sonia Helena
Resumen
In this paper, we propose to apply spatio-temporal filtering to atrial activity enhancement, prior to the detection of possible atrial arrhythmias. During normal sinus rhythm, the atrial activity is well synchronized with the ventricular one. The distances between ventricular QRS complexes and the preceding atrial P waves are approximately constant. However, during atrial arrhythmias such a synchronization does not exist. Although both atrial fibrillation (AF) and atrial flutter (AFL) are also characterized by irregularity of RR intervals, nevertheless it is this lack of atrioventricular synchronization and the associated irregularity of atrial activity (AA) that is the most straightforward symptom of atrial arrhythmias. In AFL episodes, the atrial activity tends to be more regular, whereas in AF it is almost completely unpredictable. Our objective is to enhance this activity to facilitate discrimination between the two arrhythmias. Spatio-temporal filtering (STF) was developed for detection of fetal QRS complexes in an ECG signal recorded from the abdomen of a pregnant woman. The filter can easily be applied to enhance the P waves in regular ECG signals. In this paper, however, we modify the learning phase of STF, to make it useful also for enhancement of abnormal atrial activity. The STF ability to enhance the atrial flutter waves is presented. An algorithm is proposed that allows for simple but effective discrimination between the two types of atrial irregular activity: AFL and AF. Tested on a database containing the cases of both atrial arrhythmias, the algorithm allows for their almost faultless recognition. © 2019 Association for Computing Machinery.