Tumour Relapse Prediction Using Multiparametric MR Data Recorded during Follow-Up of GBM Patients

Table 2

Detailed BER results for each time point for the best 6 classifiers when using the leave-one-patient-out method on complete features for all MR modalities. The decision moment marked by bold font. Some time points do not have results because there were no complete measurements.

BER	Random forests	dLDA	SVM-lin	LogitBoost	RobustBoost	SVM-mlp
	—	—	—	—	—	—
	—	—	—	—	—	—
L	0	0.1	0.217	0	0	0.1
	—	—	—	—	—	—
	—	—	—	—	—	—
wBER	0.148	0.172	0.276	0.148	0.148	0.136