BUPNN: Manifold Learning Regularizer-Based Blood Usage Prediction Neural Network for Blood Centers

Figure 5

The ROC curve comparison for COM-Mea schemes, the missing values are filled with the median value. The closer the curve is to the upper left corner, the better the model’s performance. The symmetry of the curve along the line from (0, 1) to (1, 0) indicates the balanced performance of the model.