analiza aiqbench
This research introduces Graph-CMMC, a self-supervised framework that leverages graph-based relational modules and pseudo-multimodal contrastive learning to capture inter-lead dependencies in 12-lead ECG signals. By transforming waveforms into Gramian Angular Difference Field images, the method effectively models global patterns essential for diagnosing coronary artery disease without relying on labeled data. The study demonstrates that incorporating explicit graph structures significantly improves robustness over traditional CNN or RNN approaches that treat leads independently.
Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
arXiv:2608.26964v1 Announce Type: new Abstract: 12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. However, most existing ECG analysis methods focus on single-lead signals or treat each lead independently, and typically process ECG signals as one-dimensional time-series data using CNNs or RNNs. While effective in modeling local waveform changes, such approaches have difficulty capturing inter-lead dependency and global waveform patterns essential for clinical diagnosis. To address this limitation, we propose a graph-based pseudo-multimodal contrastive learning framework called Graph-CMMC. ECG waveforms are transformed into Gramian Angular Difference Field (GADF) images to construct complementary representations of the same cardiac activity, enabling a pseudo-multimodal learning setting. Using all 12 leads, Graph-CMMC aligns waveform and GADF representations in a self-supervised manner, while a graph-based relational module is employed to model inter-lead dependency and enforce structural consistency across leads during contrastive learning. Experimental results on a multi-label coronary artery occlusion classification task demonstrate that the proposed framework achieves competitive performance compared to supervised learning methods. These results further suggest the effectiveness of using GADF as a complementary representation and incorporating explicit graph-based modeling of inter-lead dependency for learning robust 12-lead ECG representations.
Abstract:12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. However, most existing ECG analysis methods focus on single-lead signals or treat each lead independently, and typically process ECG signals as one-dimensional time-series data using CNNs or RNNs. While effective in modeling local waveform changes, such approaches have difficulty capturing inter-lead dependency and global waveform patterns essential for clinical diagnosis. To address this limitation, we propose a graph-based pseudo-multimodal contrastive learning framework called Graph-CMMC. ECG waveforms are transformed into Gramian Angular Difference Field (GADF) images to construct complementary representations of the same cardiac activity, enabling a pseudo-multimodal learning setting. Using all 12 leads, Graph-CMMC aligns waveform and GADF representations in a self-supervised manner, while a graph-based relational module is employed to model inter-lead dependency and enforce structural consistency across leads during contrastive learning. Experimental results on a multi-label coronary artery occlusion classification task demonstrate that the proposed framework achieves competitive performance compared to supervised learning methods. These results further suggest the effectiveness of using GADF as a complementary representation and incorporating explicit graph-based modeling of inter-lead dependency for learning robust 12-lead ECG representations.
7 pages, 7 figures. Presented at the 48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2026)
Machine Learning (cs.LG)
arXiv:2608.26964 [cs.LG]
(or arXiv:2608.26964v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.26964 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 315 cuvinte
Subiecte conexe
Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis
arXiv · 1 sept. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
arXiv · 6 aug. 2026
Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective
arXiv · 31 iul. 2026