Table 3. Fitted Bayesian log-normal survival model for overall survival (N=45).

Values in the column “Probability of a Beneficial Effect” close to either 1 or 0 correspond to a significant effect. Higher number of administered cycles of azacitidine, but not dose, was associated with improved survival.

Variable	Mean	SD	Posterior 95% Credible Interval		Probability of a Beneficial Effect
			2.5%	97.5%
Intercept	1.474	0.337	0.787	2.174	-
log(BM blast)	−0.108	0.062	−0.253	−0.003	0.022
Number of chemotherapy regimens >=2 (versus 0, 1)	−0.334	0.187	−0.707	−0.005	0.023
Number of comorbidities	−0.086	0.041	−0.176	−0.013	0.010
Azacitidine dose	0.006	0.009	−0.010	0.026	0.716
Number of cycles	0.118	0.074	−0.029	0.263	0.946
r	0.676	0.272	0.247	1.293	-