TABLE 1

Performance metrics for all six BSEP classification models

Models indicating an improvement in performance of ≥0.05 over the simple property based recursive partitioning scheme are highlighted in bold.

Model	Precision		Sensitivity	Specificity	Accuracy	F score	κ	Matthew's Correlation Coefficient
Model	Positive	Negative	Sensitivity	Specificity	Accuracy	F score	κ	Matthew's Correlation Coefficient
RP_ClogP_MW	0.83	0.84	0.84	0.83	0.83	0.83	0.67	0.67
RF_AZdesc	0.83	0.82	0.82	0.83	0.82	0.82	0.65	0.65
SVM_AZdesc	0.85	0.90	0.90	0.84	0.87	0.88	0.74	0.74
PLS_AZdesc	0.82	0.88	0.89	0.80	0.84	0.85	0.69	0.69
RF_AZFP_AZtop14	0.82	0.83	0.83	0.82	0.82	0.83	0.59	0.65
SVM_AZFP_AZtop14	0.84	0.85	0.85	0.84	0.84	0.85	0.69	0.69