Model | Accuracy | Sensitivity | Specificity | AUC | |
---|---|---|---|---|---|
Groupe | Machine learning classification | ||||
CT | |||||
NN | 0.61 | 0.50 | 0.72 | 0.70 | |
NB | 0.61 | 0.38 | 0.68 | 0.68 | |
RF | 0.61 | 0.64 | 0.60 | 0.60 | |
LR | 0.68 | 0.67 | 0.65 | 0.65 | |
AdaBoost | 0.70 | 0.78 | 0.64 | 0.64 | |
SVM | 0.63 | 0.62 | 0.78 | 0.70 | |
PET | |||||
NN | 0.70 | 0.31 | 0.72 | 0.61 | |
NB | 0.61 | 0.38 | 0.69 | 0.65 | |
RF | 0.52 | 0.54 | 0.50 | 0.57 | |
LR | 0.61 | 0.76 | 0.56 | 0.70 | |
AdaBoost | 0.65 | 0.79 | 0.63 | 0.60 | |
SVM | 0.71 | 0.72 | 0.80 | 0.76 | |
PET/CT | |||||
NN | 0.63 | 0.68 | 0.56 | 0.67 | |
NB | 0.63 | 0.77 | 0.43 | 0.79 | |
RF | 0.73 | 0.89 | 0.38 | 0.73 | |
LR | 0.66 | 0.43 | 0.77 | 0.80 | |
AdaBoost | 0.70 | 0.54 | 0.78 | 0.67 | |
SVM | 0.73 | 0.77 | 0.83 | 0.82 |