Figure 3

Evaluation and validation of the nomograms in the training and testing sets (A). (B) The area under the curve. (C,D) Internal consistency calibration plot. The abscissa is the Predicted Probablity, and the ordinate is the observed Actual Probablity. The diagonal line is the reference line, which is the case where the predicted value = the actual value. (E,F) Decision curve analysis (DCA). The y axis represents the net benefit and the x axis represents the high-risk thresholds that were chosen here range from 0 to 1. The black line represents the assumption of none have CAA, the gray line represents the assumption that all CSVD are diagnosed as CAA.