Key result
A support vector machine classifier using multidomain features achieved an average sensitivity of 0.88, specificity of 0.87, and overall score of 0.88 for classifying heart sound recordings.
Population
Heart sound recordings from the PhysioNet/CinC Challenge 2016 database
Design
Other
Authors
Loading...
Promising SVM performance for heart sound classification; hypothesis-generating and requires prospective validation before clinical use.
A machine learning approach using multidomain features and an SVM classifier demonstrated high accuracy in classifying normal and abnormal heart sounds.
Tang et al. (2018) studied Normal and abnormal heart sound recordings. Multidomain features and SVM classifier was evaluated on Classification of normal and abnormal heart sound recordings (overall score). A support vector machine classifier using multidomain features achieved an average sensitivity of 0.88, specificity of 0.87, and overall score of 0.88 for classifying heart sound recordings.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: