PaperarXiv:2610.41795
Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)
arXiv 2610.41795v1 (cs.LG, 2026-10-30); arXiv licence CC BY-NC-SA 4.0
TL;DR
Representation: each 10 s 12-lead record is band-passed (0.5–40 Hz), resampled to 300 Hz, split into beats, and each beat becomes a turning-point visibility graph. This cuts node count by more than 86 % and storage to about 14 % of an all-points graph. Model: hierarchical GNN. GINE layers over each beat graph. GATv2 plus attention pooling over the beats of each lead. The 12 lead embeddings are pooled into one exam embedding, and an MLP head gives 6 logits. 327,371 trainable parameters. Labels: six CODE abnormalities: 1dAVb, RBBB, LBBB, SB, AF and ST.
- Form factor: clinical-12-lead
Abstract
Physicians read electrocardiograms (ECGs) from waveform shape and timing, yet accurate deep-learning classifiers rarely show which waveform regions drive their predictions. We introduce LYNX-ECG, a graph neural network that represents each heartbeat as a sparse visibility graph of timestamped turning points. On CODE-Test, LYNX-ECG reaches a macro F1 score of 0.889, outperforming five baselines including the ECGFounder foundation model, while its graphs need about 14% of the storage of graphs built from every sample. Because each node maps to a specific ECG time, we can delete clinically defined waveform regions and alter beat timing to audit predictions. For conduction disorders, the clinically expected region was the strongest evidence in more than 90% of correct predictions. Bradycardia and tachycardia calls follow heart rate with conduction intervals held fixed, and atrial fibrillation calls vanish when beat-to-beat variation is removed. Sparse visibility graphs thus pair accurate ECG classification with clinically grounded, testable explanations.
Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)
Results on ChatPPG leaderboards · 3
All leaderboards| Leaderboard | Method | Result | Rank |
|---|---|---|---|
| PTB-XL Class F1 for one stated class , not macroAtrial fibrillation detection | LYNX-ECGvia model LYNX-ECG | 0.920Class F1 for one stated class , not macro, higher is better | #1 of 1 |
| Ribeiro 2020, Zenodo AUROCAtrial fibrillation detection | LYNX-ECGvia model LYNX-ECG | 0.9996AUROC, higher is better | #1 of 1 |
| Ribeiro 2020, Zenodo Class F1 for one stated class , not macroAtrial fibrillation detection | LYNX-ECGvia model LYNX-ECG | 0.918Class F1 for one stated class , not macro, higher is better | #1 of 1 |
No row is credited to the paper itself; 3 more belong to models it introduces or evaluates. Ranks apply within each leaderboard only, as reported by the source.
Tasks & signals
Tasks
Signals
Keywords
Datasets used
Models
How it works
Cite this paper
Xavier, A., Evangelista, G. H. G., Khan, A., Ribeiro, A. L. P., Zaki, M. J., Parthasarathy, S., & Jr, W. M. (2026). Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG). arXiv 2610.41795v1. https://arxiv.org/abs/2610.41795
Xavier, Artur, Guilherme Henrique Gomes Evangelista, Aitazaz Khan, Antonio Luiz Pinho Ribeiro, Mohammed J. Zaki, Srinivasan Parthasarathy, and Wagner Meira Jr. 2026. "Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)." arXiv 2610.41795v1. https://arxiv.org/abs/2610.41795.
Xavier, A., Evangelista, G. H. G., Khan, A., Ribeiro, A. L. P., Zaki, M. J., Parthasarathy, S. and Jr, W. M. (2026) 'Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)', arXiv 2610.41795v1. Available at: https://arxiv.org/abs/2610.41795
Xavier, Artur, et al. "Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)." arXiv 2610.41795v1, 2026. https://arxiv.org/abs/2610.41795.
A. Xavier et al., "Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)," arXiv 2610.41795v1, 2026, [Online]. Available: https://arxiv.org/abs/2610.41795.
@misc{xavier2026accurate,
title = {{Accurate and Auditable ECG Classification via Visibility Graph Neural Networks (LYNX-ECG)}},
author = {Xavier, Artur and Evangelista, Guilherme Henrique Gomes and Khan, Aitazaz and Ribeiro, Antonio Luiz Pinho and Zaki, Mohammed J. and Parthasarathy, Srinivasan and Jr, Wagner Meira},
year = {2026},
howpublished = {arXiv 2610.41795v1},
eprint = {2610.41795},
archivePrefix = {arXiv}
}Added to the ChatPPG research hub
