Doctorado en Ingeniería
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12585/10668
Browse
Browsing Doctorado en Ingeniería by Subject "Atrial fibrillation"
Now showing 1 - 1 of 1
- Results Per Page
- Sort Options
Item Spatio-Temporal Filtering for Automatic Detection of Atrial Arrhythmias(25/07/2021) Giraldo Guzmán, Jader Alexander; Contreras Ortiz, Sonia Helena; Kotas, MarianAtrial fibrillation is the most common arrhythmia in the world affecting up to 2% of the world population. Atrial fibrillation and atrial flutter increase the risk of serious diseases such as, heart failure, renal disease and sudden death, in addition atrial fibrillation increases up to 5 times the probability of suffering a stroke which is the third cause of death in the world. The main challenge related to these diseases is the lack of diagnosis, since in early stage of these conditions events are random and self-terminated. Because of this, it is estimated that approximately 33% of the population are undiagnosed. In this work we propose the use of spatio-temporal filtering to perform a robust characterization of the atrial activity in ECG records. Spatio-temporal filter has been adapted using two configurations of this. In on of the configurations the filter is trained to detect the position of the P wave and then PQ distances are computed and their variability. This configuration is called spatio-temporal detection filter and allows to distinguish normal sinus rhythm signals from atrial fibrillation. The proposed method allowed for AF detection with the accuracy of 98:75% on the basis of both 8–channel and 2–channel signals of 12s length. When the signals length was decreased to 6s, the accuracy varied in the range of 95% to 97:5% depending on the number of channels and the dispersion measure applied. In the second configuration, spatio-temporal filter is used to enhance atrial waveform, this configuration is called spatio-temporal enhacing filter. The ability of spatio-temporal filter to enhance the atrial flutter waves is presented. The proposed algorithm allows simple but effective classification of the two types of atrial arrhythmias: Atrial flutter and atrial fibrillation. Tested on a database containing the cases of both atrial arrhythmias, the algorithm achieved 98% of accuracy.
