Key result
Machine learning model achieves ~99% accuracy in binary heart sound classification using two-second signal segments.
Why the study?
Early detection of cardiac disease is vital, and advanced diagnostic methods for phonocardiogram analysis are needed to improve detection and classification of cardiac abnormalities.
Do recurrence plot-derived features and machine learning algorithms accurately classify heart sound recordings to detect cardiac abnormalities?
Population
Phonocardiogram (PCG) heart sound recordings
Comparison
Recurrence plot feature extraction with machine learning algorithms
Design
Diagnostic classification model development and validation study
Authors
Loading...
Supports automated PCG screening potential; leaves open prospective clinical validation.
Do recurrence plot-derived features and machine learning algorithms accurately classify heart sound recordings to detect cardiac abnormalities?
A machine learning framework using recurrence plots for feature extraction from phonocardiograms achieves high accuracy in classifying heart sounds, offering a potential automated screening tool.
Almosained et al. (2026) studied Cardiac disease. Recurrence plot-derived features and machine learning classification was evaluated on Classification accuracy of cardiac abnormalities. A machine learning framework using recurrence plot-derived features achieved up to 98.4% multiclass and 99.5% binary accuracy in classifying cardiac abnormalities from 2-second heart sound segments.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: