Table 3.

Comparative performance among different sampling strategies in predicting TMB group using LightGBM.

Method	Sensitivity	Specificity	Precision	Accuracy
ADASYN	0.72 ± 0.204	0.7571 ± 0.168	0.7010 ± 0.244	0.7449 ± 0.103
BorderlineSMOTE	0.8 ± 204	0.7143 ± 0.151	0.6573 ± 0.092	0.7462 ± 0.083
RandomOversampler	0.72 ± 0.219	0.8143 ± 0.148	0.7262 ± 0.129	0.7782 ± 0.127
RandomUndersampler	0.8 ± 0.4	0.7393 ± 0.15	0.6810 ± 0.169	0.7641 ± 0.069
SMOTE	0.8 ± 0.32	0.7714 ± 0.19	0.7219 ± 0.258	0.7808 ± 0.11
SVMSMOTE	0.76 ± 0.126	0.8107 ± 0.068	0.7952 ± 0.112	0.7936 ± 0.081

ADASYN: adaptive synthetic, SMOTE: synthetic minority oversampling technique.