Table 3.
Classification performance of the two machine learning classifiers with the selected features.
| Classification Performance | Model | %Sn | %Sp | %Acc | AUC | Selected Feature(s) |
|---|---|---|---|---|---|---|
|
First and second-order
(QUS + QUS-Tex1) |
k-NN | 73 (61–83) |
64 (52–75) |
74 (63–85) |
0.70 (0.59–0.79) |
ΔSAS ΔASD-ENE ASD-CONW0 |
| SVM | 74 (64–83) |
86 (77–95) |
84 (72–95) |
0.78 (0.66–0.89) |
SASW0 ASD-CONW0 ΔAAC-HOM |
|
|
All features
(QUS + QUS-Tex1 + QUS-Tex1-Tex2) |
k-NN |
87
(78–95) |
75
(64–85) |
81
(70–93) |
0.83
(0.73–0.92) |
ACEW0
AAC-CON-CONW0 ΔASD-CON-CON |
| SVM | 75 (62–87) |
85 (72–96) |
85 (73–97) |
0.78 (0.68–0.88) |
SASW0 ASD-CONW0 ΔAAC-HOM |
∆ Indicates the difference of values of week 4 from week 0 for each feature included in the analysis. The best classifier performances using the k-NN model have been highlighted in bold. The values in parenthesis represent 95% confidence interval. Abbreviations: Sn: Sensitivity; Sp: Specificity, Acc: Accuracy, AUC: Area under curve; k-NN: k-nearest-neighbors; SVM: Support vector machine with radial based kernel function; AAC (dB/cm3): Average Acoustic Concentration; ASD (µm): Average Scatterer Diameter; SAS: Spacing Among Scatterer; ACE (dB/cm-MHz): Attenuation Coefficient Estimate; CON: Contrast; HOM: Homogeneity; ENE: Energy.