arXiv cs.AI· Artur Xavier, Guilherme Henrique Gomes Evangelista, Aitazaz Khan, Antonio Luiz Pinho Ribeiro, Mohammed J. Zaki, Srinivasan Parthasarathy, Wagner Meira Jr·· 4 小时前AI 评分43
LYNX-ECG：基于可见性图神经网络的可审计心电分类方法
Accurate and Auditable ECG Classification via Visibility Graph Neural Networks
AI 导读
研究者提出 LYNX-ECG，一种将每个心跳表示为带时间戳转折点的稀疏可见性图的图神经网络。在 CODE-Test 上其 macro F1 达 0.889，超过包括 ECGFounder 在内的五个基线，图存储仅需逐样本图的约 14%。通过删除临床定义的波形区域并改变心跳时序可审计预测：传导异常正确预测中超过 90% 以临床预期区域为最强证据，房颤预测在去除逐搏变异后消失。
正文 · 原文
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.
| Comments: | 43 pages, 10 figures, 21 tables, including Supplementary Information |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41795 [cs.LG] |
| (or arXiv:2610.41795v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41795 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Artur Xavier [view email]
[v1]
Fri, 30 Oct 2026 14:24:47 UTC (1,600 KB)
来源：arXiv cs.AI · arxiv.org