Deep learning model for ECG reconstruction reveals the information content of ECG leads

Tomasz Gradowski, Teodor Buchner
2/1/2025
eess.SPcs.LG

No confident code implementation found for this paper.

Abstract

This study introduces a deep learning model based on the U-net architecture to reconstruct missing leads in electrocardiograms (ECGs). The model was trained to reconstruct 12-lead ECG data from reduced lead configurations using publicly available datasets. The results highlight the ability of the model to quantify the information content of each ECG lead and its inter-lead correlations. This has significant implications for optimizing lead selection in diagnostic scenarios, particularly in settings where complete 12-lead ECGs are impractical. In addition, the study provides insights into the physiological underpinnings of ECG signals and their propagation. The findings pave the way for advances in telemedicine, portable ECG devices, and personalized cardiac diagnostics by reducing redundancy and improving signal interpretation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ECGrecover: a Deep Learning Approach for Electrocardiogram Signal Completion

90% match1 repo62024

ECGXtract: Deep Learning-based ECG Feature Extraction for Automated CVD Diagnosis

87% match2025

Explaining deep learning for ECG using time-localized clusters

87% match2025

ECG-IMN: Interpretable Mesomorphic Neural Networks for 12-Lead Electrocardiogram Interpretation

86% match2026

Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models

86% match2024

Tracing the Heart's Pathways: ECG Representation Learning from a Cardiac Conduction Perspective

86% match2025

Cite this paper

@article{gradowski2025deep,
  title  = {Deep learning model for ECG reconstruction reveals the information content of ECG leads},
  author = {Tomasz Gradowski and Teodor Buchner},
  year   = {2025},
  eprint = {2502.00559},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.00559v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.00559.svg)](https://codeofpaper.com/paper/2502.00559)

Discussion