Table 3.

The AUC in the task of classification of lesions as benign or malignant, for classification using preharmonization features and for classification using postharmonization features. Within each dataset, the AUC was determined using classification with random forest classifier via 10-fold cross validation, with the posterior probability of malignancy used as the classifier output for ROC curve analysis.

Dataset	${\mathrm{AUC}}_{\text{preharmonization}}$ [95% CI]	${\mathrm{AUC}}_{\text{postharmonization}}$ [95% CI]	$\mathrm{\Delta }\mathrm{AUC}$ [95% CI]	$p$ value
US set	0.839 [0.810 to 0.864]	0.951 [0.937 to 0.964]	0.122 [0.095 to 0.131]	$p<0.001$
China set	0.886 [0.869 to 0.902]	0.999 [0.995 to 1.000]	0.113 [0.097 to 0.131]	$p<0.001$
Combined set (US and China)	0.872 [0.857 to 0.886]	0.974 [0.968 to 0.980]	0.102 [0.090 to 0.115]	$p<0.001$