A Principal Component Regression Approach for Estimating Ventricular Repolarization Duration Variability. (8th January 2007)

• Record Type: Journal Article
• Authors: Tarvainen Tarvainen, Mika P. Mika P.; Laitinen Laitinen, Tomi Tomi; Lyyra-Laitinen Lyyra-Laitinen, Tiina Tiina; Niskanen Niskanen, Juha-Pekka Juha-Pekka; Karjalainen Karjalainen, Pasi A. Pasi A.
• Other Names: Lasaosa Lasaosa Pablo Laguna Pablo Laguna Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2007(2007)
• Publication Date: 2007-01-08
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2007/58358
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : Ventricular repolarization duration (VRD) is affected by heart rate and autonomic control, and thus VRD varies in time in a similar way as heart rate. VRD variability is commonly assessed by determining the time differences between successive R- and T-waves, that is, RT intervals. Traditional methods for RT interval detection necessitate the detection of either T-wave apexes or offsets. In this paper, we propose a principal-component-regression- (PCR-) based method for estimating RT variability. The main benefit of the method is that it does not necessitate T-wave detection. The proposed method is compared with traditional RT interval measures, and as a result, it is observed to estimate RT variability accurately and to be less sensitive to noise than the traditional methods. As a specific application, the method is applied to exercise electrocardiogram (ECG) recordings.