To study the discriminatory ability of the change (delta) in the Score for Neonatal Acute Physiology-II (SNAP-II) for 14-d mortality in preterm neonates with severe sepsis. Consecutively born neonates of < 34-wk gestation during the 1-y study period in a tertiary care neonatal unit were included. SNAP-II was recorded at the onset of severe sepsis (T0) and serially at 24 (T1), 48 (T2), and 72 (T3) h. Delta scores (Δ SNAP-II) were derived from the difference between the SNAP-II at baseline and each one of the subsequent time points. Seventy-one preterm neonates were enrolled. Baseline characteristics were similar in survivors (n = 53) and nonsurvivors (n = 18). Median SNAP-II at all the four time points were significantly higher in nonsurvivors (p < 0.001). Delta SNAP-II (T0-T2) was significantly different between nonsurvivors and survivors (mean difference: -14.7; 95% CI: -29, -0.9; p = 0.02), while the difference was not significant between T0-T1 and T0-T3. Initial SNAP-II had a significantly better discriminating ability than Δ SNAP-II at various time points (AUC, 95% CI: 0.59, 0.41-0.75 for T0-T1; 0.70, 0.50-0.87 for T0-T2; and 0.64; 0.38-0.89 for T0-T3). Delta SNAP-II does not have a better discriminatory ability for mortality by 14 d in preterm neonates with severe sepsis.