Summary of classification scores of Persistence Images (PIs) for patients with low-intermediate risk.

An SVM classifier was constructed for patients with low or intermediate risk at the time of diagnosis, using PIs obtained from PH analysis of biomarkers CD10, CD20, CD38, and CD45. These results depend on the dimension of the barcode, the spread of the Gaussian and the grid size used for the PIs. We fixed parameters C = 10 and γ = 0.001 for the SVM method, based on the previous results. The accuracy (Acc.) of the model predictions after 6-fold cross-validation is greatest for Dimensions 0 and 1. An expanded analysis with additional classification scores (AUC, mean accuracy, standard deviation of the accuracy, recall, precision, F1-score and confusion matrices) can be found in Tables H-I in S1 Text.