arXiv cs.AI· Artur Xavier, Guilherme Henrique Gomes Evangelista, Aitazaz Khan, Antonio Luiz Pinho Ribeiro, Mohammed J. Zaki, Srinivasan Parthasarathy, Wagner Meira Jr·· 11 小时前AI 评分34
LYNX-ECG：用可见图神经网络实现准确且可审计的心电图分类
Accurate and Auditable ECG Classification via Visibility Graph Neural Networks
AI 导读
LYNX-ECG 将每次心跳表示为带时间戳转折点的稀疏可见图，在 CODE-Test 上取得 0.889 的 macro F1，超过包括 ECGFounder 基础模型在内的五个基线，图存储量约为逐样本建图的 14%。由于每个节点对应具体 ECG 时刻，可删除临床定义的波形区域并改变心搏时序来审计预测：传导障碍中临床预期区域在超过 90% 的正确预测里是最强证据，房颤判断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