Key result
A feature extraction algorithm based on wavelet packet decomposition and neural network classification achieved 85% accuracy in distinguishing physiological and pathological heart murmurs.
Why the study?
Does a feature extraction algorithm based on wavelet packet decomposition accurately classify heart sound signals into physiological and pathological murmurs?
Does a feature extraction algorithm based on wavelet packet decomposition accurately classify heart sound signals into physiological and pathological murmurs?
A wavelet packet decomposition-based feature extraction algorithm combined with a neural network can classify heart sound signals with 85% accuracy, potentially assisting in medical diagnoses.
May aid automated murmur screening in low-resource settings; hypothesis-generating and requires prospective validation before clinical adoption.
In this paper, a feature extraction algorithm based on the wavelet packet decomposition (WPD) method was developed for the heart sound signals. Feature vectors obtained were used to classify the heart sound signals into physiological and pathological murmurs. The classification using a neural network method indicated a 85 percent accuracy. This could be an effective assistance for medical doctors to make their final diagnoses.
No takes yet. Share an insight, caveat, or question.
Liang et al. (2002) studied Heart murmurs. Wavelet packet decomposition (WPD) feature extraction and neural network classification was evaluated on Classification accuracy. A feature extraction algorithm based on wavelet packet decomposition and neural network classification achieved 85% accuracy in distinguishing physiological and pathological heart murmurs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: