Diffusion-based Conditional ECG Generation with Structured State Space Models

This is the official repository for the paper Diffusion-based Conditional ECG Generation with Structured State Space Models. We propose diverse algorithms (primarly SSSD-ECG) for the generation of 12-lead ECG signals conditioned on disease labels.

Dataset and pre-trained model

Experiments

Visit the clinical evaluation directory to get the medical expert results, and the source directory to get our experiments source code.

Please cite our publication if you found our research to be helpful.

@misc{https://doi.org/10.48550/arxiv.2208.09399,
  doi = {10.48550/ARXIV.2208.09399},
  url = {https://arxiv.org/abs/2208.09399},
  author = {Alcaraz, Juan Miguel Lopez and Strodthoff, Nils},
  keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}