ECGrecover: a Deep Learning Approach for Electrocardiogram Signal Completion

TL;DR

This paper introduces ECGrecover, a deep learning model that reconstructs complete 12-lead ECG signals from incomplete data, improving digitalization and wearable ECG analysis.

Contribution

We propose a novel U-Net based neural network with a composite loss function for accurate ECG signal reconstruction from partial or single-lead data.

Findings

ECGrecover outperforms existing methods in distortion metrics.

It better preserves ECG features like P, QRS, T wave coordinates.

The approach is effective for digitizing paper ECGs and wearable device data.

Abstract

In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from its incomplete parts. We focus on two main scenarios: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering entire leads from signal in another unique lead. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications, often limited to digital 12 lead 10s ECGs. The second is the widespread use of wearable devices that record ECGs but typically capture only one or a few leads. In both cases, a non-negligible amount of information is lost or not recorded. Our approach aims to recover this missing signal. We propose ECGrecover, a U-Net neural network model trained on a novel composite objective function to address the reconstruction problem. This function incorporates both spatial and temporal features of the ECG by combining the distance in amplitude and sycnhronization through time between the reconstructed and the real digital signals. We used real-life ECG datasets and through comprehensive assessments compared ECGrecover with three state-of-the-art methods based on generative adversarial networks (EKGAN, Pix2Pix) as well as the CopyPaste strategy. The results demonstrated that ECGrecover consistently outperformed state-of-the-art methods in standard distortion metrics as well as in preserving critical ECG characteristics, particularly the P, QRS, and T wave coordinates.