ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
This work addresses the problem of generating personalized ECG digital twins for healthcare applications, offering an incremental improvement over existing methods by enhancing controllability and feature preservation.
The paper tackles personalized ECG generation by proposing ECGTwin, a two-stage framework that extracts individual features from reference ECGs and injects them with target cardiac conditions using a diffusion model, resulting in high-fidelity and diverse ECG signals with fine-grained controllability.
Personalized electrocardiogram (ECG) generation is to simulate a patient's ECG digital twins tailored to specific conditions. It has the potential to transform traditional healthcare into a more accurate individualized paradigm, while preserving the key benefits of conventional population-level ECG synthesis. However, this promising task presents two fundamental challenges: extracting individual features without ground truth and injecting various types of conditions without confusing generative model. In this paper, we present ECGTwin, a two-stage framework designed to address these challenges. In the first stage, an Individual Base Extractor trained via contrastive learning robustly captures personal features from a reference ECG. In the second stage, the extracted individual features, along with a target cardiac condition, are integrated into the diffusion-based generation process through our novel AdaX Condition Injector, which injects these signals via two dedicated and specialized pathways. Both qualitative and quantitative experiments have demonstrated that our model can not only generate ECG signals of high fidelity and diversity by offering a fine-grained generation controllability, but also preserving individual-specific features. Furthermore, ECGTwin shows the potential to enhance ECG auto-diagnosis in downstream application, confirming the possibility of precise personalized healthcare solutions.