Research map / Image generation / GANs
PGANs: Personalized Generative Adversarial Networks for ECG Synthesis to Improve Patient-Specific Deep ECG Classification
Tomer Golany, Kira Radinsky
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 GAN-synthesized ECG beats to training | LSTM classifier · MIT-BIH S and F beats | AUC | Improved |
| add GAN-synthesized ECG beats to training | LSTM classifier · MIT-BIH V beats | AUC | No clear effect |
| add a small set of predicted patient-specific real beats (Personalized LSTM) | LSTM classifier · MIT-BIH F, S, V | AUC: gap of 0.1 to 0.15 | Hurt |
| add P,Q,R,S,T morphology MSE loss to generator (ECG GAN vs GAN/DCGAN) (ablation) | GAN data augmentation · MIT-BIH F and V beats | AUC | Improved |
| add P,Q,R,S,T morphology MSE loss to generator (ablation) | GAN data augmentation · MIT-BIH S beats | AUC | Hurt |
| personalize vanilla GAN / DCGAN with patient beats in discriminator (ablation) | GAN data augmentation · MIT-BIH F, S, V | AUC | Mixed |
| use patient-specific wave features in morphology loss (PGAN) (ablation) | ECG GAN · MIT-BIH F, S, V | AUC | Improved |
| increase number of synthesized beats | LSTM + GAN augmentation · MIT-BIH | AUC | Mixed |
Closest papers by meaning
- Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning (AAAI 2024 · similarity 0.84)
- Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model (ICLR 2025 · similarity 0.83)
- Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners (ICML 2025 · similarity 0.82)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · similarity 0.82)
- Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals (NeurIPS 2024 · similarity 0.82)
- Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITA (AAAI 2025 · similarity 0.81)
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.
