Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xin, Ozek, Burcu, Mohan, Aruna, Ravari, Amirhossein, Zilbershot, Or, Afghah, Fatemeh
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.23060
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910034089213952
author Wang, Xin
Ozek, Burcu
Mohan, Aruna
Ravari, Amirhossein
Zilbershot, Or
Afghah, Fatemeh
author_facet Wang, Xin
Ozek, Burcu
Mohan, Aruna
Ravari, Amirhossein
Zilbershot, Or
Afghah, Fatemeh
contents Electrocardiogram (ECG) analysis is crucial for diagnosing heart disease, but most self-supervised learning methods treat ECG as a generic time series, overlooking physiologic semantics and rhythm-level structure. Existing contrastive methods utilize augmentations that distort morphology, whereas generative approaches employ fixed-window segmentation, which misaligns cardiac cycles. To address these limitations, we propose RhythmBERT, a generative ECG language model that considers ECG as a language paradigm by encoding P, QRS, and T segments into symbolic tokens via autoencoder-based latent representations. These discrete tokens capture rhythm semantics, while complementary continuous embeddings retain fine-grained morphology, enabling a unified view of waveform structure and rhythm. RhythmBERT is pretrained on approximately 800,000 unlabeled ECG recordings with a masked prediction objective, allowing it to learn contextual representations in a label-efficient manner. Evaluations show that despite using only a single lead, RhythmBERT achieves comparable or superior performance to strong 12-lead baselines. This generalization extends from prevalent conditions such as atrial fibrillation to clinically challenging cases such as subtle ST-T abnormalities and myocardial infarction. Our results suggest that considering ECG as structured language offers a scalable and physiologically aligned pathway for advancing cardiac analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23060
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection
Wang, Xin
Ozek, Burcu
Mohan, Aruna
Ravari, Amirhossein
Zilbershot, Or
Afghah, Fatemeh
Machine Learning
Electrocardiogram (ECG) analysis is crucial for diagnosing heart disease, but most self-supervised learning methods treat ECG as a generic time series, overlooking physiologic semantics and rhythm-level structure. Existing contrastive methods utilize augmentations that distort morphology, whereas generative approaches employ fixed-window segmentation, which misaligns cardiac cycles. To address these limitations, we propose RhythmBERT, a generative ECG language model that considers ECG as a language paradigm by encoding P, QRS, and T segments into symbolic tokens via autoencoder-based latent representations. These discrete tokens capture rhythm semantics, while complementary continuous embeddings retain fine-grained morphology, enabling a unified view of waveform structure and rhythm. RhythmBERT is pretrained on approximately 800,000 unlabeled ECG recordings with a masked prediction objective, allowing it to learn contextual representations in a label-efficient manner. Evaluations show that despite using only a single lead, RhythmBERT achieves comparable or superior performance to strong 12-lead baselines. This generalization extends from prevalent conditions such as atrial fibrillation to clinically challenging cases such as subtle ST-T abnormalities and myocardial infarction. Our results suggest that considering ECG as structured language offers a scalable and physiologically aligned pathway for advancing cardiac analysis.
title RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection
topic Machine Learning
url https://arxiv.org/abs/2602.23060