← Back to all news
arXiv Machine Learning

Accurate and Auditable ECG Classification via Visibility Graph Neural Networks

The paper introduces LYNX-ECG, a graph neural network that represents each heartbeat as a sparse visibility graph of timestamped turning points, enabling accurate ECG classification while providing auditable, clinically grounded explanations. On the CODE-Test dataset, LYNX-ECG achieves a macro F1 score of 0.889, outperforming five baselines including the ECGFounder foundation model, and its graphs require only about 14% of the storage needed for full-sample graphs. Because each graph node corresponds to a specific ECG time, clinicians can delete waveform regions or alter beat timing to audit predictions, with the clinically expected region proving strongest evidence in over 90% of correct conduction disorder predictions. "whyItMatters":"The model’s ability to pair high classification accuracy with transparent, testable explanations directly addresses the need for clinically interpretable AI in ECG analysis."

Related stories

arXiv Machine Learning
Sep 29

BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment

BeatGraph is a self‑supervised model that represents infant ECG recordings as graphs of individual heartbeats rather than fixed‑length patches, allowing it to capture the higher heart rates and distinct waveform patterns of infants. The model uses a shared beat encoder, a Transformer for temporal ordering, and graph attention layers to produce a window embedding, which is pretrained on a large unlabeled infant ECG corpus and fine‑tuned for tasks such as sleep‑wake detection, infant‑state classification, activity‑source identification, and affect recognition. BeatGraph achieves state‑of‑the‑art performance on multiple infant‑specific benchmarks and transfers well to pediatric and adult ECG datasets, while also releasing the first public infant ECG corpus collected in diverse home and classroom settings.

By Mohammad Nur Hossain Khan, M. S. Krafczyk, Beverly G. Bolster, Nancy McElwain, Mark A. Hasegawa-Johnson, Bashima Islam
llmsragfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Aug 28

Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations

The paper introduces Graph-CMMC, a graph-based pseudo‑multimodal contrastive learning framework for 12‑lead ECG representations. It transforms ECG waveforms into Gramian Angular Difference Field (GADF) images to create complementary views, then aligns these views while modeling inter‑lead dependencies with a graph module. Experiments on coronary artery occlusion classification show that Graph-CMMC performs competitively with supervised methods, highlighting the value of GADF representations and explicit graph modeling for robust ECG analysis.

By Mengyu Wang, Kozo Okada, Takafumi Goto, Natsuko Jinba, Hiroki Yamaya, Kiyoshi Hibi, Tomoki Hamagami
multimodal
More like this →
arXiv Computer Vision
Oct 12

ECGWmark: Deep Watermarking for Electrocardiogram Signals

ECGWmark is a fully convolutional, quantization‑free deep watermarking framework designed for electrocardiogram (ECG) signals. It embeds patient metadata into ECGs while preserving high‑frequency diagnostic details by operating in a continuous latent space and using a localized frame‑level mechanism to resist severe temporal desynchronization. A differentiable Physiological Loss guided by a clinical classifier helps maintain diagnostic semantics, achieving over 90% channel‑bit extraction accuracy under circular phase shifts and demonstrating mixed effects on class‑level diagnostic metrics in the MIT‑BIH benchmark.

By Kuan-Yu Chen, Kuan-Chen Wang, Yu Tsao, Jian-Jiun Ding
diffusionefficiencybenchmarks
More like this →
arXiv Machine Learning
Aug 5

LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics

arXiv:2608. 03690v1 Announce Type: new Abstract: Point-of-care cardiac devices such as smartwatches and handheld ECG recorders typically capture 1--2 leads, yet existing ECG foundation models are architecturally constrained to fixed 12-lead inputs, degrading or failing under these reduced configurations.

By Edoardo Coppola, Stefano Fiorini, Pietro Li\`o, Mattia Savardi, Alberto Signoroni
More like this →
arXiv AI
Sep 21

BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis

BEAT-Net is a supervised biomimetic framework for ECG diagnosis that incorporates QRS-centered tokenization and a hierarchical architecture mirroring a cardiologist’s workflow. It processes heartbeat sequences through morphological, spatial, temporal, and transformer-based stages, achieving an AUC of 0.924 on large benchmarks while using only 0.7 million parameters. The model outperforms the 39.5‑million‑parameter HeartLang foundation model on morphological form classification and demonstrates superior cross‑dataset generalization with only 35% of the training data.

By Runze Ma, Haonan Lyu, Shunbo Jia, Qiang Yang, Muzi Xu, Jiaqi Zhang, Zihe Luo, Caizhi Liao
llmsnlpbenchmarks
More like this →
arXiv Machine Learning
Oct 7

MS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive Learning

arXiv:2610.07662v1 Announce Type: new Abstract: Electrocardiography (ECG) records the electrical activity of the heart, aiding diagnosis by detecting abnormalities in cardiac function. ECG foundation...

By Robert A. Lewis, I-Min Chiu, Kyle Verrier, Karthik Jayaraman Raghuram, Francoise Marvel, Salar Abbaspourazad, Anshuman Mishra, Guillermo Sapiro, Andrew C. Miller, Joseph Futoma
benchmarkssafety
More like this →