Skip to main content

Table 3 Heart sound classification techniques

From: The electronic stethoscope

References Classification method   Normal HS AR AS MR MS
[81] Markov Blanket Random Forests (multiple binary classification) Analyzed sound/disorder Y Y Y Y Y
No. of cases 38 38 41 43 38
Sensitivity Accuracy of 90.22% for distinguishing between normal and abnormal; accuracies of 92.45 and 90.34% for distinguishing between AR-MS and AS-MR
Specificity
[82] ANN (multi-class classification) Analyzed sound/disorder Y Y Y Y
No. of cases 31 26 28 26
Sensitivity 89.7 ± 5.9%
Specificity
[83] SVM (multiple binary classification) Analyzed sound/disorder Y Y Y Y
No. of cases 15 51 in total
Sensitivity 95.37% 94.02% 95.20%
Specificity 95.49% 96.68% 96.33%
[84] ANN, GMM, SVM (multiple binary classification) Analyzed sound/disorder Y Y Y Y
No. of cases 15 51 in total
Sensitivity 93.20% 92.63% 96.88%
Specificity 95.87% 95.80% 92.78%
[85] HMM, SVM (multi-class classification) Analyzed sound/disorder Y Y Y Y Y
No. of cases 80 6 9 9 12
Sensitivity 67% 67% 67% 83%
Specificity 99%
[86] ANN (multi-class classification) Analyzed sound/disorder Y Y Y Y Y
No. of cases 4 4 4 4 4
Sensitivity 100% 98% 100% 100%
Specificity 100%
[87] SVM (binary hierarchical classification) Analyzed sound/disorder Y Y Y
No. of cases 225 60 60
Sensitivity 85% 95%
Specificity 98.67%
[88] SVM (multiple binary classification) Analyzed sound/disorder Y Y Y Y Y
No. of cases 38 38 41 43 38
Sensitivity Accuracy of 91.43% for distinguishing between normal and abnormal; accuracies of 92.11 and 91.67% for distinguishing between AR-MS and AS-MR
Specificity
[89] SVM (binary hierarchical classification) Analyzed sound/disorder Y Y Y Y Y
No. of cases 6 6 4 6 9
Sensitivity 93.75% 92.31% 96.97% 90.63%
Specificity 99.49%
  1. Y yes.