PROJECT TITLE :

ECG Signal Quality During Arrhythmia and Its_(new) - 2015

ABSTRACT:

An automated algorithm to assess electrocardiogram (ECG) quality for each traditional and abnormal rhythms is presented for false arrhythmia alarm suppression of intensive care unit (ICU) monitors. A explicit focus is given to the quality assessment of a wide range of arrhythmias. Data from 3 databases were used: the Physionet Challenge 2011 dataset, the MIT-BIH arrhythmia database, and also the MIMIC II database. The quality of additional than 33 00zero single-lead 10 s ECG segments were manually assessed and another twelve 000 dangerous-quality single-lead ECG segments were generated using the Physionet noise stress check database. Signal quality indices (SQIs) were derived from the ECGs segments and used because the inputs to a support vector machine classifier with a Gaussian kernel. This classifier was trained to estimate the quality of an ECG phase. Classification accuracies of up to 99% on the coaching and check set were obtained for traditional sinus rhythm and up to 95percent for arrhythmias, though performance varied greatly relying on the kind of rhythm. Additionally, the association between 4050 ICU alarms from the MIMIC II database and therefore the signal quality, as evaluated by the classifier, was studied. Results counsel that the SQIs ought to be rhythm specific and that the classifier should be trained for every rhythm call independently. This would require a substantially increased set of labeled information in order to coach an accurate algorithm.