Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms

Joao D. S. Marques, Arlindo L. Oliveira
3/11/2025
cs.CVcs.AIcs.LG

Official code: joaodsmarques/Are-ECGs-enough-Deep-Learning-Classifiers (8 stars, MIT, last commit 2025-07-29).

Abstract

Pulmonary embolism is a leading cause of out of hospital cardiac arrest that requires fast diagnosis. While computed tomography pulmonary angiography is the standard diagnostic tool, it is not always accessible. Electrocardiography is an essential tool for diagnosing multiple cardiac anomalies, as it is affordable, fast and available in many settings. However, the availability of public ECG datasets, specially for PE, is limited and, in practice, these datasets tend to be small, making it essential to optimize learning strategies. In this study, we investigate the performance of multiple neural networks in order to assess the impact of various approaches. Moreover, we check whether these practices enhance model generalization when transfer learning is used to translate information learned in larger ECG datasets, such as PTB-XL, CPSC18 and MedalCare-XL, to a smaller, more challenging dataset for PE. By leveraging transfer learning, we analyze the extent to which we can improve learning efficiency and predictive performance on limited data. Code available at https://github.com/joaodsmarques/Are-ECGs-enough-Deep-Learning-Classifiers .

View on arXivView PDF

Code Implementations(1)

joaodsmarques/Are-ECGs-enough-Deep-Learning-ClassifiersOfficial100%
MIT

This repository presents the original implementation of the paper "Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms" by João D.S. Marques and Arlindo L. Oliveira. Accepted to the MIRASOL 2025 Workshop (MICCAI 2025).

81Python, Jupyter NotebookMar 11, 20251 years agoMIT

Similar Papers

Deep Neural Networks Generalization and Fine-Tuning for 12-lead ECG Classification

89% match2023

Transfer Learning in ECG Diagnosis: Is It Effective?

88% match1 repo42024

Transferring Clinical Knowledge into ECGs Representation

86% match2025

Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs

85% match2025

Evaluation of Deep Learning Models for LBBB Classification in ECG Signals

85% match2025

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

85% match2025

Cite this paper

@article{marques2025ecgs,
  title  = {Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms},
  author = {Joao D. S. Marques and Arlindo L. Oliveira},
  year   = {2025},
  eprint = {2503.08960},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.08960v2}
}

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/2503.08960.svg)](https://codeofpaper.com/paper/2503.08960)

Discussion