Key result
A novel machine learning method combining a deep CNN-based feature extractor and a support vector machine achieved a challenge score of 0.812 for heart sound classification on the hidden testing set.
A deep CNN-based feature extractor combined with an SVM classifier achieved robust automated classification of normal and abnormal heart sounds.
We present a novel machine learning-based method for heart sound classification which we submitted to the Phy-sioNet/CinC Challenge 2016. Our method relies on a robust feature representation-generated by a wavelet-based deep convolutional neural network (CNN)-of each cardiac cycle in the test recording, and support vector machine classification. In addition to the CNN-based features, our method incorporates physiological and spectral features to summarize the characteristics of the entire test recording. The proposed method obtained a score, sensitivity, and specificity of 0.812, 0.848, and 0.776, respectively, on the hidden challenge testing set.
No takes yet. Share an insight, caveat, or question.
Tschannen et al. (2016) studied Heart sound classification (n=764). Deep CNN-based feature extractor and SVM was evaluated on Challenge score (MAcc) on hidden testing set. A novel machine learning method combining a deep CNN-based feature extractor and a support vector machine achieved a challenge score of 0.812 for heart sound classification on the hidden testing set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: