Automated Cardiovascular Arrhythmia Detection - Automated ECG
Sep 1, 2025
·
1 min read
This is the official code repository accompanying the paper titled Toward Robust Automated Cardiovascular Arrhythmia Detection using Self-supervised Learning and 1-Dimensional Vision Transformers.
Abstract
This project developed a robust automated cardiovascular arrhythmia detection system using self-supervised pretraining and 1D vision transformer architectures tailored for ECG signals. The system emphasizes reliability under distribution shift and low-labeled-data regimes.
Dataset & Artifacts
- Public datasets: (see repository for dataset details and preprocessing scripts)
- Code: https://github.com/Mitchell-Chatterjee/Robust-Automated-Cardiovascular-Arrhythmia-Detection
- Paper: Toward Robust Automated Cardiovascular Arrhythmia Detection using Self-supervised Learning and 1-Dimensional Vision Transformers
Methods
- Self-supervised pretraining on large unlabeled ECG corpora
- 1D Vision Transformer fine-tuning for classification and detection
- Augmentation strategies, calibration, and uncertainty estimation for safer clinical deployment
Results
- Achieved state-of-the-art robustness across held-out datasets.
- Demonstrated improved calibration and lower false positive rates in low-label settings.
Relevance
This work underpins my research focus on medical AI and time-series modelling, and complements my engineering work on large-scale retrieval systems by bringing rigorous evaluation and robustness-first design.
