Improving the detection algorithm for life-threatening arrhythmias: Implementation in implantable cardioverter-defibrillators

The implantable cardioverter-defibrillator (ICD) is an effective therapeutic device for preventing mortality in patients with cardiac diseases caused by life-threatening arrhythmias. The authors previously proposed an algorithm for the detection of life-threatening arrhythmias using a multiple regression model. To enhance the classification accuracy, we have now incorporated a moving average filter and a multiple detection process into the original detection algorithm. The experimental results showed that the proposed method could attain sufficiently high accuracy for all ventricular fibrillation rhythms to be detected precisely. In addition, the cases of false detection of sinus rhythm or supraventricular tachyarrhythmias, which could cause ICD malfunction, have been reduced.