Key result
Model-driven environments improve ECG feature classification accuracy by providing a reusable parametric structure.
Population
Articles published between 2008 and 2017 proposing techniques for the classification of ECG features
Design
Systematic_review
Authors
Loading...
May improve ECG arrhythmia diagnosis accuracy; extends feature extraction methods by resolving dependency gaps in model-driven frameworks.
Systematic Review
This systematic review highlights the potential of model-driven environments to improve the accuracy of ECG feature classification for arrhythmia and heart disease diagnosis.
Iqbal et al. (2018) conducted a systematic review in Heart diseases and arrhythmia. Model-driven environment (MDE) was evaluated on Compatibility of MDE with research questions regarding ECG feature classification. A model-driven environment provides a reusable parametric structure for more accurate classification of ECG features, addressing existing gaps in feature dependencies.
Synapse has enriched one closely related paper. Consider it for comparative context: