# RawECGNet: Deep Learning Generalization for Atrial Fibrillation Detection from the Raw ECG

arXiv: https://arxiv.org/abs/2401.05411 · HTML: https://mlsanity.com/paper/2401.05411/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 26 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Automatic diagnosis of the 12-lead ECG using a deep neural network](https://mlsanity.com/paper/1904.01949/) (2019)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging](https://mlsanity.com/paper/1809.10932/) (2018)
- [HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks](https://mlsanity.com/paper/2002.05262/) (2020)
- [Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks](https://mlsanity.com/paper/2303.11338/) (2023)
- [SleepPPG-Net: a deep learning algorithm for robust sleep staging from continuous photoplethysmography](https://mlsanity.com/paper/2202.05735/) (2022)
- [Generalization in medical AI: a perspective on developing scalable models](https://mlsanity.com/paper/2311.05418/) (2023)
- [Remote atrial fibrillation burden estimation using deep recurrent neural network](https://mlsanity.com/paper/2008.02228/) (2020)
- [Machine Learning for Ranking f-wave Extraction Methods in Single-Lead ECGs](https://mlsanity.com/paper/2307.08331/) (2023)

## Built on by (most cited first, 6 of 6)

- [Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection](https://mlsanity.com/paper/2506.03964/) (2025)
- [SHDB-AF: a Japanese Holter ECG database of atrial fibrillation](https://mlsanity.com/paper/2406.16974/) (2024)
- [uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm](https://mlsanity.com/paper/2506.11238/) (2025)
- [Consciousness-ECG Transformer for Conscious State Estimation System with Real-Time Monitoring](https://mlsanity.com/paper/2511.02853/) (2025)
- [FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection](https://mlsanity.com/paper/2608.03597/) (2026)
- [Atrial Fibrillation Detection with Arbitrary Leads via a Codebook-Based Reconstruction-Classification Framework](https://mlsanity.com/paper/2608.18451/) (2026)

## Abstract (arXiv)

Introduction: Deep learning models for detecting episodes of atrial fibrillation (AF) using rhythm information in long-term, ambulatory ECG recordings have shown high performance. However, the rhythm-based approach does not take advantage of the morphological information conveyed by the different ECG waveforms, particularly the f-waves. As a result, the performance of such models may be inherently limited. Methods: To address this limitation, we have developed a deep learning model, named RawECGNet, to detect episodes of AF and atrial flutter (AFl) using the raw, single-lead ECG. We compare the generalization performance of RawECGNet on two external data sets that account for distribution shifts in geography, ethnicity, and lead position. RawECGNet is further benchmarked against a state-of-the-art deep learning model, named ArNet2, which utilizes rhythm information as input. Results: Using RawECGNet, the results for the different leads in the external test sets in terms of the F1 score were 0.91--0.94 in RBDB and 0.93 in SHDB, compared to 0.89--0.91 in RBDB and 0.91 in SHDB for ArNet2. The results highlight RawECGNet as a high-performance, generalizable algorithm for detection of AF and AFl episodes, exploiting information on both rhythm and morphology.