mlsanityData to 14 Oct 2026

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

arXiv 2608.03690 ↗First posted 4 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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. We introduce LAEF (Lead-Agnostic ECG Foundation), a 7M-parameter ECG foundation model that can natively process any lead subset without zero-padding or architectural modification. LAEF represents ECGs as variable-size spatiotemporal graphs with physiologically motivated intra- and inter-lead connectivity, processed by a Graph Attention Network that scales naturally with active lead count.Pre-trained on 9.2M 12-lead ECGs via masked node modelling with stochastic lead sampling, LAEF learns representations robust to lead configuration. Across 18 downstream datasets, LAEF is on par with specialized 12-lead baselines over 12× larger at full lead availability. Under direct point-of-care-oriented diagnostics (1--2 leads), it outperforms all zero-padded alternatives on 17 out of 18 datasets with with a single randomly sampled lead and on 14 out of 18 with 2 leads, with an average AUROC gain of +3.2 points. Representation analysis links this advantage to architectural lead-agnosticism, and a lead-importance study across 164 cardiovascular conditions shows population-level performance is stable across single standard input leads while still recovering established clinically lead-condition associations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 49 references that are in the map. First posted on arXiv 4 Aug 2026.

Builds on

22 of 49 references.

References · 22

  1. 2017Graph Attention Networkscited by 8,923
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  5. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  6. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  7. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  8. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  9. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  10. 2019Automatic diagnosis of the 12-lead ECG using a deep neural networkcited by 164
  11. 2023Denoising Diffusion Autoencoders are Unified Self-supervised Learnerscited by 130
  12. 2024ECG-FM: An Open Electrocardiogram Foundation Modelcited by 90
10 more
  1. 2022Reliability of CKA as a Similarity Measure in Deep Learningcited by 87
  2. 2024Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogramcited by 84
  3. 2024Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancementcited by 67
  4. 2025Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Modelcited by 36
  5. 2024Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecturecited by 19
  6. 2025CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Modelscited by 7
  7. 2025Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECGcited by 4
  8. 2023Graph Neural Networks for Topological Feature Extraction in ECG Classificationcited by 3
  9. 2025Self-DANA: A Resource-Efficient Channel-Adaptive Self-Supervised Approach for ECG Foundation Modelscited by 3
  10. 2020Representing and Denoising Wearable ECG Recordingscited by 2

Built on by

Not cited yet.