How arianabdollahi83/qrs-annotation works
This repository combines ECG beat classification and evaluation with a separate beat-clustering toolkit, alongside patient ECG exports and example clustering results. The classifier workflow detects R-peaks, extracts beat and rhythm features, trains a hierarchical model, then predicts and evaluates arrhythmia labels and thresholds. Clustering accepts ECG signals and R-peaks independently and saves cluster artifacts. The README is empty; relationships below are limited to the sampled source excerpts and SOURCE INDEX references.
Main entry points: train.py Model Training · evaluate_thresholds.py Threshold Evaluation · hierarchical_qrs_classifier.py QRS Classifier · functions.py R-Peak Detector
Components 11
ECG Preparation
- R-Peak Detector
functions.py - Beat Features
features.py
Classification
- Model Training
train.py - QRS Classifier
hierarchical_qrs_classifier.py - Threshold Evaluation
evaluate_thresholds.py
Beat Clustering
- Clustering Methods
ecg_cluster_toolkit.py
Data Artifacts
- Patient ECG Exports
Pats - Trained Model
ecg_hierarchical_v4.keras - Threshold Config
ecg_hierarchical_v4_threshold.json - Cluster Artifacts
results
Other components
- ECG Analyst
Connections 14
- Patient ECG Exports → R-Peak Detector: reads signal
functions.py - ECG Analyst → Model Training: runs training
- Model Training → R-Peak Detector: detects peaks
train.py - Model Training → Beat Features: extracts features
train.py - Model Training → Trained Model: saves model
train.py - ECG Analyst → QRS Classifier: requests predictions
- QRS Classifier → Beat Features: extracts features
hierarchical_qrs_classifier.py - QRS Classifier → Trained Model: loads model
hierarchical_qrs_classifier.py - ECG Analyst → Threshold Evaluation: runs evaluation
evaluate_thresholds.py - Threshold Evaluation → QRS Classifier: evaluates predictions
evaluate_thresholds.py - Threshold Evaluation → R-Peak Detector: detects peaks
evaluate_thresholds.py - Threshold Evaluation → Threshold Config: writes threshold
evaluate_thresholds.py - ECG Analyst → Clustering Methods: runs clustering
- Clustering Methods → Cluster Artifacts: saves clusters
ecg_cluster_toolkit.py