Abstract
Although implantable cardioverter-defibrillators have improved significantly in the past decades, the algorithms used in the identification of life-threatening arrhythmias are still not accurate enough. Conventional methods commonly misclassify tachycardias, sometimes initiating an unnecessary and uncomfortable treatment. In this paper, we proposed a new method for the identification of ventricular tachycardias and fibrillations based on the comparison of simultaneous electro-grams. Our method could successfully separate supraventricular tachycardias and normal sinus rhythm, which do not require any treatment, from ventricular tachycardias and fibrillation, which are life-threatening arrhythmias and must be terminated, with a sensitivity of 93.0% and a specificity of 92.7% from the comparison of ventricular electrograms. In future studies, the classification using electrograms from the right heart must be improved.
Original language | English |
---|---|
Pages (from-to) | 2498-2501 |
Number of pages | 4 |
Journal | Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference |
Publication status | Published - 2009 |
Externally published | Yes |
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Signal Processing
- Biomedical Engineering
- Health Informatics