ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Prediction of Spiral-Tip Trajectories via Pseudo-ECGs and LSTM Networks

Babu, VK and Alageshan, JK and Pandit, R (2023) Prediction of Spiral-Tip Trajectories via Pseudo-ECGs and LSTM Networks. In: 50th Computing in Cardiology, CinC 2023, 1 October - 4 October 2023, Atlanta.

[img] PDF
Com_car_2023.pdf - Published Version
Restricted to Registered users only

Download (5MB) | Request a copy
Official URL: https://doi.org/10.22489/CinC.2023.186


Spiral waves of electrical activation in cardiac tissue can lead to life-threatening ventricular arrhythmias. The tracking of the tip of a spiral wave is a problem of central importance that can play an essential role in eliminating these arrhythmias via methods such as catheter ablation. We first obtain pseudo-ECGs from our simulations of spiral waves in the two-dimensional, two-variable Aliev-Panfilov model for cardiac tissue. We then use these pseudo ECGs in conjunction with Long-Short-Term-Memory (LSTM) networks to track the tip trajectories of spiral waves. We demonstrate that our LSTM-based tip-tracking compares favorably with the Iyer-Gray method, which requires the full spatiotemporal evolution of spiral waves to obtain tip trajectories. Our tip-trajectory data include rigid, meandering, and drifting spiral waves. We use the Iyer-Gray method to get the spiral wave trajectories during training and testing. We demonstrate that training with noise can lead to better results in testing data with noise. By using an ensemble of 5 LSTM networks, we show that the number of outliers, in the presence of noise, can be decreased. © 2023 CinC.

Item Type: Conference Paper
Publication: Computing in Cardiology
Publisher: IEEE Computer Society
Additional Information: The copyright for this article belongs to IEEE Computer Society.
Keywords: Electrocardiograms; Long short-term memory; Tissue, Aliev-Panfilov model; Cardiac tissues; Catheter ablation; Electrical activation; Grey methods; Memory network; Spatiotemporal evolution; Spiral waves; Two-dimensional; Ventricular arrhythmias, Trajectories
Department/Centre: Others
Date Deposited: 04 Mar 2024 10:21
Last Modified: 04 Mar 2024 10:21
URI: https://eprints.iisc.ac.in/id/eprint/84061

Actions (login required)

View Item View Item