Key result
HRV-based ECG feature selection impacts the performance of machine learning algorithms for atrial fibrillation detection, yielding optimal feature sets for specific classifiers.
Feature selection of HRV-based features from ECG impacts the performance of machine learning algorithms in detecting atrial fibrillation.
Answers are grounded in this paper and cite their sources.
HRV feature optimization could refine ML algorithms for AF detection; leaves open prospective clinical validation before adoption.
We investigated the selection of features used in various machine learning algorithms to detect atrial fibrillation. The features were derived from the analysis of Heart Rate Variability from ECG. We show how the feature selection impacts the statistical metrics of the atrial fibrillation detection and identify the best feature sets for particular classifiers.
No takes yet. Share an insight, caveat, or question.
Buś et al. (2021) studied this question. HRV-based ECG feature selection impacts the performance of machine learning algorithms for atrial fibrillation detection, yielding optimal feature sets for specific classifiers.
Synapse has enriched 10 related papers. Consider them for comparative context: