Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/4079
Title: ID163_Atrial features-based prediction of sinus tachycardia using LSTM-RNN model
Authors: Venkatesh, N. Prasanna
Kumar, R. Pradeep
Neelapu, Bala Chakravarthy
Kunal Pal
Sivaraman, J.
Keywords: Sinus Tachycardia (ST)
LSTM-RNN model
Issue Date: Jan-2023
Citation: IEEE Consumer Communications & Networking Conference, Las Vegas, Nevada, USA, 8–11 January 2023
Abstract: Sinus Tachycardia (ST) reveals pathological dysfunctions and differentiates distinct arrhythmias. The progression of Atrial Fibrillation (AF) from paroxysmal to persistent is frequently associated with tachycardias. Moreover, the most effective AF detection methods suggest incorporating both atrial and R-R interval features. Therefore, the study aims to use the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model to investigate the influence of atrial characteristics on predicting tachycardia. Electrocardiograms (ECGs) from 10 healthy volunteers 26 ± 3.4 years (4 females) were recorded for Sinus Rhythm (SR) and ST conditions along with 10 AF data. For ST, the 5-day follow-up recording was performed with each volunteer. ECG recordings were performed for a duration of 10 s. Atrial features, along with R-R interval and Heart Rate (HR), were utilized as inputs for the developed LSTM-RNN multivariate time series forecasting model. The features were statistically analyzed before training the LSTM-RNN model. The correlation is positive and significant between HR and atrial amplitude (p
Description: Copyright belongs to proceeding publisher
URI: http://hdl.handle.net/2080/4079
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2023_CINC_NPVenkatesh_ID163_Atrial_Poster.pdfPoster716.2 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.