Analysis of ECG data to detect Atrial Fibrillation

TL;DR

This paper explores adapting CNN models to detect atrial fibrillation from single-point, noisy ECG data collected by a health watch, addressing challenges of real-world data variability.

Contribution

It introduces modifications to CNN models to effectively analyze single-lead, noisy ECG data from wearable devices for atrial fibrillation detection.

Findings

Modified CNN models successfully detect Afib in noisy, single-lead ECG data.

The approach demonstrates potential for real-time AF detection on wearable devices.

Results show comparable accuracy to traditional multi-lead ECG methods.

Abstract

Atrial fibrillation(termed as AF/Afib henceforth) is a discrete and often rapid heart rhythm that can lead to clots near the heart. We can detect Afib by ECG signal by the absence of p and inconsistent intervals between R waves as shown in fig(1). Existing methods revolve around CNN that are used to detect afib but most of them work with 12 point lead ECG data where in our case the health gauge watch deals with single-point ECG data. Twelve-point lead ECG data is more accurate than a single point. Furthermore, the health gauge watch data is much noisier. Implementing a model to detect Afib for the watch is a test of how the CNN is changed/modified to work with real life data