# Data Augmentation for Electrocardiograms

arXiv: https://arxiv.org/abs/2204.04360 · HTML: https://mlsanity.com/paper/2204.04360/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 53 references that are in the map.
- First posted on arXiv 9 Apr 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [An Unsupervised Learning Model for Deformable Medical Image Registration](https://mlsanity.com/paper/1802.02604/) (2018)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [SpecAugment on Large Scale Datasets](https://mlsanity.com/paper/1912.05533/) (2019)
- [3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations](https://mlsanity.com/paper/2106.04452/) (2021)
- [Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation](https://mlsanity.com/paper/2008.02663/) (2020)
- [Meta-Learning to Improve Pre-Training](https://mlsanity.com/paper/2111.01754/) (2021)
- [Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher](https://mlsanity.com/paper/2004.08780/) (2020)
- [Meta Approach to Data Augmentation Optimization](https://mlsanity.com/paper/2006.07965/) (2020)
- [Deep neural networks can predict mortality from 12-lead electrocardiogram voltage data](https://mlsanity.com/paper/1904.07032/) (2019)
- [Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction](https://mlsanity.com/paper/2103.02768/) (2021)

## Built on by (most cited first, 12 of 12)

- [Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series](https://mlsanity.com/paper/2307.10923/) (2023)
- [GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction](https://mlsanity.com/paper/2208.01220/) (2022)
- [Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study](https://mlsanity.com/paper/2306.10494/) (2023)
- [PreFallKD: Pre-Impact Fall Detection via CNN-ViT Knowledge Distillation](https://mlsanity.com/paper/2303.03634/) (2023)
- [EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks](https://mlsanity.com/paper/2509.25791/) (2025)
- [MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report](https://mlsanity.com/paper/2410.16239/) (2024)
- [LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning](https://mlsanity.com/paper/2210.07340/) (2022)
- [Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report](https://mlsanity.com/paper/2304.06286/) (2023)
- [CAAP: Class-Dependent Automatic Data Augmentation Based On Adaptive Policies For Time Series](https://mlsanity.com/paper/2404.00898/) (2024)
- [Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning](https://mlsanity.com/paper/2309.07526/) (2023)
- [Contrastive Cross-Modal Learning for Infusing Chest X-ray Knowledge into ECGs](https://mlsanity.com/paper/2506.19329/) (2025)
- [Boosting ECG Classification Performance by Pre-training with Synthesized Data](https://mlsanity.com/paper/2606.10802/) (2026)

## Abstract (arXiv)

Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not available for many predictive tasks of interest. In this work, we perform an empirical study examining whether training time data augmentation methods can be used to improve performance on such data-scarce ECG prediction problems. We investigate how data augmentation strategies impact model performance when detecting cardiac abnormalities from the ECG. Motivated by our finding that the effectiveness of existing augmentation strategies is highly task-dependent, we introduce a new method, TaskAug, which defines a flexible augmentation policy that is optimized on a per-task basis. We outline an efficient learning algorithm to do so that leverages recent work in nested optimization and implicit differentiation. In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks. We distill key insights from our experimental evaluation, generating a set of best practices for applying data augmentation to ECG prediction problems.