# Domain-Adaptive Arrhythmia Classification Using a Hybrid Transformer on Wearable Heart Signals

arXiv: https://arxiv.org/abs/2605.08199 · HTML: https://mlsanity.com/paper/2605.08199/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 69 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Automatic diagnosis of the 12-lead ECG using a deep neural network](https://mlsanity.com/paper/1904.01949/) (2019)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.16765/) (2021)
- [Convolution-Free Medical Image Segmentation using Transformers](https://mlsanity.com/paper/2102.13645/) (2021)
- [Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty](https://mlsanity.com/paper/2202.01339/) (2022)
- [Self-supervised Autoregressive Domain Adaptation for Time Series Data](https://mlsanity.com/paper/2111.14834/) (2021)
- [A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data](https://mlsanity.com/paper/2110.09260/) (2021)
- [Why Do Probabilistic Clinical Models Fail To Transport Between Sites?](https://mlsanity.com/paper/2311.04787/) (2023)
- [Similarity Learning based Few Shot Learning for ECG Time Series Classification](https://mlsanity.com/paper/2202.00612/) (2022)
- [MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots](https://mlsanity.com/paper/2408.01988/) (2024)
- [Ultra Low-Power System for Remote ECG Monitoring](https://mlsanity.com/paper/1903.08835/) (2019)

## Abstract (arXiv)

Cardiovascular disease remains the leading cause of death globally, underscoring the need for effective, accessible monitoring solutions, particularly through wearable devices that enable continuous, real-time tracking of heart rhythms in home settings. However, deploying deep learning models trained on clinical electrocardiogram (ECG) datasets to wearable devices remains challenging, as differences in recording equipment, signal quality, and patient populations introduce domain shifts that degrade model performance. We propose a hybrid transformer model that processes continuous ECG signals alongside seven heart rate variability (HRV) features, where the raw signal path captures beat-level morphological patterns and the HRV path encodes rhythm regularity statistics, allowing the model to jointly leverage complementary information from both representations. To enhance the model's ability to generalize across domains, we employ representation learning techniques, including Maximum Mean Discrepancy (MMD), a non-parametric kernel-based metric that quantifies the distance between feature distributions of different domains, to align feature distributions between source and target domains, addressing the challenge of domain shifts between public datasets and wearable device data. By leveraging five public ECG datasets for training, the model learns robust, generalized representations that mitigate domain-specific biases. When tested on wearable device data with an unseen domain, the model achieved an F1-macro 95% and balanced accuracy of 96.15%. These results demonstrate minimal performance degradation, with only a 2% drop in F1-macro compared to seen-domain evaluation, highlighting the model's generalization capabilities and its potential for reliable, real-time heart monitoring applications in home and ambulatory settings.