Key result
A back propagation neural network using 324 multi-domain features achieved an overall accuracy of 0.818, with a sensitivity of 0.807 and specificity of 0.829, for classifying normal and abnormal heart sounds on the hidden test set.
Why the study?
Can a back propagation neural network using multi-domain features accurately classify heart sound recordings as normal or abnormal?
Can a back propagation neural network using multi-domain features accurately classify heart sound recordings as normal or abnormal?
A back propagation neural network using 324 multi-domain features can classify heart sound recordings as normal or abnormal with over 80% accuracy, offering a potential tool for computer-aided cardiovascular diagnosis.
Answers are grounded in this paper and cite their sources.
May support automated heart sound screening; leaves open prospective validation before clinical use.
This paper aims to classify a single PCG recording as normal or abnormal for computer-aided diagnosis. The proposed framework for this challenge has four steps: preprocessing, feature extraction, training and validation. In the preprocessing step, a recording is segmented into four states, i.e., the first heart sound, systolic interval, the second heart sound, and diastolic interval by the Springer Segmentation algorithm. In the feature extraction step, the authors extract 324 features from multi-domains to perform classification. A back propagation neural network is used as predication model. The optimal threshold for distinguishing normal and abnormal is determined by the statistics of model output for both normal and abnormal. The performance of the proposed predictor tested by the six training sets is sensitivity 0.812 and specificity 0.860 (overall accuracy is 0.836). However, the performance reduces to sensitivity 0.807 and specificity 0.829 (overall accuracy is 0.818) for the hidden test set.
No takes yet. Share an insight, caveat, or question.
Tang et al. (2016) studied Heart sound classification (normal vs abnormal) (n=3,153). Back Propagation Neural Network with Multi-Domain Features was evaluated on Overall accuracy on the hidden test set. A back propagation neural network using 324 multi-domain features achieved an overall accuracy of 0.818, with a sensitivity of 0.807 and specificity of 0.829, for classifying normal and abnormal heart sounds on the hidden test set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: