A Deep Learning Method for Beat-Level Risk Analysis and Interpretation of Atrial Fibrillation Patients during Sinus Rhythm

TL;DR

This paper introduces a deep learning approach for beat-level risk analysis of atrial fibrillation patients during sinus rhythm, improving interpretability and accuracy for early detection and risk assessment.

Contribution

It presents a novel AI algorithm that distinguishes sinus rhythm in AF patients from normal individuals at beat-level, with interpretable risk trends and enhanced accuracy.

Findings

Average AUC of 0.7314 for single beats

AUC of 0.7591 with 150-beat fusion

Reduced data dimensionality for portable deployment

Abstract

Atrial Fibrillation (AF) is a common cardiac arrhythmia. Many AF patients experience complications such as stroke and other cardiovascular issues. Early detection of AF is crucial. Existing algorithms can only distinguish ``AF rhythm in AF patients'' from ``sinus rhythm in normal individuals'' . However, AF patients do not always exhibit AF rhythm, posing a challenge for diagnosis when the AF rhythm is absent. To address this, this paper proposes a novel artificial intelligence (AI) algorithm to distinguish ``sinus rhythm in AF patients'' and ``sinus rhythm in normal individuals'' in beat-level. We introduce beat-level risk interpreters, trend risk interpreters, addressing the interpretability issues of deep learning models and the difficulty in explaining AF risk trends. Additionally, the beat-level information fusion decision is presented to enhance model accuracy. The experimental results demonstrate that the average AUC for single beats used as testing data from CPSC 2021 dataset is 0.7314. By employing 150 beats for information fusion decision algorithm, the average AUC can reach 0.7591. Compared to previous segment-level algorithms, we utilized beats as input, reducing data dimensionality and making the model more lightweight, facilitating deployment on portable medical devices. Furthermore, we draw new and interesting findings through average beat analysis and subgroup analysis, considering varying risk levels.