Research map / Probabilistic and scientific modeling / Differential equations and PDEs
ECG ODE-GAN: Learning Ordinary Differential Equations of ECG Dynamics via Generative Adversarial Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add ECG-ODE-GAN-generated heartbeats to ResNet training | ECG heartbeat classification · MIT-BIH, SVEB (S) | precision: 0.70 -> 0.83 | Helped |
| Add ECG-ODE-GAN-generated heartbeats to ResNet training | ECG heartbeat classification · MIT-BIH, Fusion (F) | precision: 0.25 -> 0.45 | Helped |
| Add ECG-ODE-GAN-generated heartbeats to ResNet training | ECG heartbeat classification · MIT-BIH, VEB (V) | precision: 0.86 -> 0.90 | Helped |
| Add physical ECG wave parameters to the ODE-generator input (ablation) | ODE-GAN ECG synthesis · MIT-BIH, ECG heartbeat classification | precision | Helped |
| Add noise alongside physical parameters to the ODE-generator input (ablation) | ECG-ODE-GAN · MIT-BIH, ECG heartbeat classification | precision | Hurt |
| Split the generator into wave-specific sub-networks instead of one network (ablation) | ECG-ODE-GAN · MIT-BIH, SVEB (S) | precision: 0.33 -> 0.83 | Helped |
| Split the generator into wave-specific sub-networks instead of one network (ablation) | ECG-ODE-GAN · MIT-BIH, Fusion (F) | precision: 0.06 -> 0.45 | Helped |
| Split the generator into wave-specific sub-networks instead of one network (ablation) | ECG-ODE-GAN · MIT-BIH, VEB (V) | recall: 0.79 -> 0.90 | Helped |
| Use ODE-GAN-generated heartbeat augmentation (ablation) | ECG heartbeat classification · MIT-BIH | precision | Helped |
| Generate heartbeats with ECG-ODE-GAN rather than the ECG Simulator (ablation) | ECG heartbeat classification · MIT-BIH, Fusion (F) | precision: 0.05 -> 0.45 | Helped |
Closest papers by meaning
- SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification (ICML 2020 · similarity 0.94)
- PDE-Driven Spatiotemporal Generative Modeling for Multilead ECG Synthesis (AAAI 2026 · similarity 0.92)
- Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals (NeurIPS 2024 · similarity 0.85)
- Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning (AAAI 2024 · similarity 0.84)
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images (NeurIPS 2025 · similarity 0.83)
- Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITA (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.