MAR-ECG is an ontology-guided masked autoregressive pretraining method that uses SNOMED-CT graph alignment and graph-smoothed contrastive learning plus signal-derived auxiliaries to achieve competitive ECG classification performance without clinical text.
2018.2442
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Reports to Ontologies: Ontology-Guided Representation Learning for 12-Lead ECG
MAR-ECG is an ontology-guided masked autoregressive pretraining method that uses SNOMED-CT graph alignment and graph-smoothed contrastive learning plus signal-derived auxiliaries to achieve competitive ECG classification performance without clinical text.