Table 3.

Statistical significance of difference in AUC values compared to the baseline model, experiment 1

	Malignant vs benign vs recalled-benign	Benign vs recalled-benign	Malignant vs benign	Malignant vs recalled-benign	Malignant vs benign + recalled-benign	Recalled-benign vs. benign + malignant
Experiment 1	–	–	–	–	–	–
Experiment 2	0.32	< 0.01	0.96	0.09	0.02	0.53
Experiment 3	0.29	0.34	0.65	< 0.01	0.49	0.03
Experiment 4	< 0.01	< 0.01	< 0.01	< 0.01	< 0.01	< 0.01
Experiment 5	< 0.01	0.01	0.01	0.01	0.43	< 0.01
Experiment 6	< 0.01	0.35	< 0.01	< 0.01	0.48	< 0.01

Statistically significant results (p < 0.05) are displayed in bold