Table 3 Performance of models in predicting pathological complete response
DL model | Rad model | Clinic model | BR model | Image model | BCRP model | |
|---|---|---|---|---|---|---|
TC | ||||||
AUC | 0.88 (0.83, 0.93) | 0.84 (0.78, 0.90) | 0.66 (0.58, 0.74) | 0.63 (0.54, 0.71) | 0.90 (0.86, 0.95) | 0.94 (0.91, 0.98) |
Accuracy | 0.83 (0.77, 0.89) | 0.78 (0.71, 0.85) | 0.64 (0.56, 0.72) | 0.61 (0.52, 0.69) | 0.83 (0.77, 0.89) | 0.86 (0.81, 0.92) |
Sensitivity | 0.81 (0.75, 0.88) | 0.76 (0.69, 0.83) | 0.82 (0.76, 0.89) | 0.69 (0.61, 0.77) | 0.76 (0.69, 0.83) | 0.80 (0.74, 0.87) |
Specificity | 0.84 (0.78, 0.90) | 0.80 (0.74, 0.87) | 0.44 (0.35, 0.52) | 0.51 (0.42, 0.60) | 0.90 (0.86, 0.95) | 0.93 (0.89, 0.97) |
PPV | 0.85 (0.79, 0.91) | 0.81 (0.75, 0.88) | 0.62 (0.54, 0.70) | 0.61 (0.52, 0.70) | 0.90 (0.85, 0.94) | 0.92 (0.88, 0.97) |
NPV | 0.80 (0.74, 0.87) | 0.75 (0.68, 0.82) | 0.69 (0.61, 0.77) | 0.60 (0.52, 0.68) | 0.77 (0.70, 0.84) | 0.81 (0.74, 0.88) |
ETC | ||||||
AUC | 0.77 (0.66, 0.87) | 0.72 (0.62, 0.83) | 0.55 (0.43, 0.66) | 0.58 (0.46, 0.69) | 0.80 (0.71, 0.90) | 0.84 (0.75, 0.92) |
Accuracy | 0.71 (0.60, 0.82) | 0.73 (0.62, 0.83) | 0.51 (0.39, 0.63) | 0.55 (0.43, 0.66) | 0.75 (0.64, 0.85) | 0.77 (0.67, 0.87) |
Sensitivity | 0.71 (0.61, 0.82) | 0.74 (0.64, 0.85) | 0.49 (0.37, 0.60) | 0.60 (0.49, 0.72) | 0.63 (0.51, 0.74) | 0.74 (0.64, 0.85) |
Specificity | 0.71 (0.60, 0.82) | 0.72 (0.61, 0.83) | 0.52 (0.40, 0.64) | 0.52 (0.40, 0.64) | 0.80 (0.70, 0.90) | 0.79 (0.69, 0.89) |
PPV | 0.53 (0.42, 0.65) | 0.55 (0.44, 0.67) | 0.32 (0.22, 0.42) | 0.37 (0.26, 0.48) | 0.59 (0.48, 0.71) | 0.62 (0.50, 0.73) |
NPV | 0.84 (0.75, 0.93) | 0.86 (0.77, 0.94) | 0.68 (0.57, 0.80) | 0.74 (0.63, 0.84) | 0.82 (0.73, 0.91) | 0.87 (0.79, 0.95) |
