Table 2. Comparison of ABC/GCB classification performed using Wright’s naive Bayes classifier [36] and the established elastic net classifier both based on cohort normalization.

The second column shows the accuracy of the classifiers with 95% CI. The third column shows the Cohen’s weighted κ with 95% CI.

Dataset	Accuracy	Cohen’s κ
CHEPRETRO	0.94 (0.87, 0.98)	0.94 (0.88, 1.00)
MDFCI	0.78 (0.68, 0.86)	0.77 (0.66, 0.88)
IDRC	0.82 (0.79, 0.86)	0.80 (0.76, 0.85)
LLMPP R-CHOP	0.91 (0.86, 0.94)	0.90 (0.85, 0.96)