Key result
Multidomain PCG-based SVM classifier detects abnormal heart sounds with ~88% overall accuracy.
Why the study?
Does a support vector machine classifier using multidomain phonocardiogram features accurately classify normal and abnormal heart sound recordings in the PhysioNet/CinC Challenge 2016 database?
Does a support vector machine classifier using multidomain phonocardiogram features accurately classify normal and abnormal heart sound recordings in the PhysioNet/CinC Challenge 2016 database?
Answers are grounded in this paper and cite their sources.
Combining 400 multidomain phonocardiogram features—particularly state frequency spectrum, energy, and entropy—with a radial basis function SVM classifier enables stable and accurate automated discrimination of abnormal vs. normal heart sounds (overall score 0.88).
This paper proposes a method using multidomain features and support vector machine (SVM) for classifying normal and abnormal heart sound recordings. The database was provided by the PhysioNet/CinC Challenge 2016. A total of 515 features are extracted from nine feature domains, i.e., time interval, frequency spectrum of states, state amplitude, energy, frequency spectrum of records, cepstrum, cyclostationarity, high-order statistics, and entropy. Correlation analysis is conducted to quantify the feature discrimination abilities, and the results show that "frequency spectrum of state", "energy", and "entropy" are top domains to contribute effective features. A SVM with radial basis kernel function was trained for signal quality estimation and classification. The SVM classifier is independently trained and tested by many groups of top features. It shows the average of sensitivity, specificity, and overall score are high up to 0.88, 0.87, and 0.88, respectively, when top 400 features are used. This score is competitive to the best previous scores. The classifier has very good performance with even small number of top features for training and it has stable output regardless of randomly selected features for training. These simulations demonstrate that the proposed features and SVM classifier are jointly powerful for classifying heart sound recordings.
No takes yet. Share an insight, caveat, or question.
Tang et al. (2018) studied Cardiovascular disease / Normal vs. abnormal heart sound (PCG) recordings (n=764). Support vector machine (SVM) classifier with radial basis kernel function using 515 multidomain features vs. Reference cardiologist signal quality and confirmed clinical diagnosis labels was evaluated on Overall classification score (average of modified sensitivity and specificity) for discriminating normal and abnormal heart sound recordings. An SVM classifier using the top 400 multidomain PCG features achieved an average sensitivity of 0.88, specificity of 0.87, and overall score of 0.88 for classifying abnormal heart sounds.
Synapse has enriched 10 related papers. Consider them for comparative context: