# BenchECG and xECG: a benchmark and baseline for ECG foundation models

arXiv: https://arxiv.org/abs/2509.10151 · HTML: https://mlsanity.com/paper/2509.10151/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 70 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [Automatic diagnosis of the 12-lead ECG using a deep neural network](https://mlsanity.com/paper/1904.01949/) (2019)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning](https://mlsanity.com/paper/2505.23719/) (2025)
- [MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation](https://mlsanity.com/paper/2110.01406/) (2021)
- [Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram](https://mlsanity.com/paper/2402.09450/) (2024)
- [Vision-LSTM: xLSTM as Generic Vision Backbone](https://mlsanity.com/paper/2406.04303/) (2024)
- [Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram](https://mlsanity.com/paper/2203.06889/) (2022)
- [Deep learning cardiac motion analysis for human survival prediction](https://mlsanity.com/paper/1810.03382/) (2018)
- [Unlocking the Power of LSTM for Long Term Time Series Forecasting](https://mlsanity.com/paper/2408.10006/) (2024)
- [Simplifying DINO via Coding Rate Regularization](https://mlsanity.com/paper/2502.10385/) (2025)
- [Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2410.08559/) (2024)
- [Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences](https://mlsanity.com/paper/2411.04165/) (2024)
- [Advancing the State-of-the-Art for ECG Analysis through Structured State Space Models](https://mlsanity.com/paper/2211.07579/) (2022)

## Built on by (most cited first, 9 of 9)

- [Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos](https://mlsanity.com/paper/2603.08505/) (2026)
- [SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG](https://mlsanity.com/paper/2603.09940/) (2026)
- [Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study](https://mlsanity.com/paper/2605.12241/) (2026)
- [DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition](https://mlsanity.com/paper/2605.16441/) (2026)
- [How Do Electrocardiogram Models Scale?](https://mlsanity.com/paper/2605.17276/) (2026)
- [Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification](https://mlsanity.com/paper/2606.02605/) (2026)
- [Next-Token Prediction Learns Generalisable Representations of Sleep Physiology](https://mlsanity.com/paper/2606.09605/) (2026)
- [Looking Beyond Accuracy: A Holistic Benchmark of ECG Foundation Models](https://mlsanity.com/paper/2601.21830/) (2026)
- [Do ECG Foundation Models Transfer to Rare Cardiac Diseases? Evidence from Brugada Syndrome Detection](https://mlsanity.com/paper/2607.03009/) (2026)

## Abstract (arXiv)

Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised learning, which achieves the best BenchECG score compared to publicly available state-of-the-art models. In particular, xECG is the only publicly available model to perform strongly on all datasets and tasks. By standardising evaluation, BenchECG enables rigorous comparison and aims to accelerate progress in ECG representation learning. xECG achieves superior performance over earlier approaches, defining a new baseline for future ECG foundation models.