Table 2. p-values and classification performances (accuracy) of individual QUS parameters for differentiating responders from non-responders at weeks 1, 4 and 8.

		Week 1	Week 4	Week 8
ΔMBF	Accuracy	61 ± 8	65 ± 5	85 ± 5
	p-value	0.042	<0.005	<0.005
ΔSI	Accuracy	55 ± 8	65 ± 11	74 ± 6
	p-value	0.034	0.010	<0.005
ΔACE	Accuracy	54 ± 8	64 ± 4	60 ± 10
	p-value	<0.005	0.042	0.259
ΔAAC	Accuracy	58 ± 8	64 ± 9	69 ± 8
	p-value	0.404	0.069	0.135
ΔSS	Accuracy	53 ± 8	62 ± 7	63 ± 15
	p-value	0.424	0.368	0.727
ΔASD	Accuracy	54 ± 9	61 ± 9	60 ± 13
	p-value	0.382	0.377	0.570
ΔSAS	Accuracy	62 ± 7	58 ± 8	69 ± 7
	p-value	0.606	0.678	0.590

Parameters are sorted from highest to lowest accuracy at week 4. The bold entry indicates the best performance. Reported values are mean and standard deviation of the accuracies in percentages. Results were obtained by running the classification 10 times using 10 random samples from responders group