Table 4.

Added predictive value of biomarkers over the clinical models

Outcome and Clinical ModelaAUROC (95% CI)Integrated Discrimination Improvement (95% CI)Category Free Net Reclassification Index (95% CI)P Valuec
Recovery
 LASSO0.76 (0.71 to 0.81)Reference model0.45
 Add IL-80.77 (0.72 to 0.82)0.013 (0.002 to 0.03)b0.31 (0.11 to 0.51)b0.30
 Add IL-100.77 (0.72 to 0.82)0.014 (0.001 to 0.03)b0.18 (−0.01 to 0.40)0.07
 Add TNFR I0.76 (0.72 to 0.82)0.003 (-0.003 to 0.009)0.14 (−0.06 to 0.33)0.33
 LASSO+IL-80.77 (0.72 to 0.82)Reference model0.30
 Add IL-100.77 (0.73 to 0.82)0.01 (−0.003 to 0.01)0.17 (−0.03 to 0.36)0.36
 Parsimonious model0.73 (0.68 to 0.78)Reference model0.69
 Parsimonious model+IL-80.76 (0.71 to 0.81)0.02 (0.01 to 0.04)b0.27 (0.08 to 0.47)b0.50
Mortality
 LASSO0.78 (0.74 to 0.83)Reference model0.08
 Add IL-60.79 (0.75 to 0.83)0.01 (−0.002 to 0.01)0.10 (−0.09 to 0.29)0.01
 Add IL-80.80 (0.76 to 0.84)0.02 (0.01 to 0.04)b0.33 (0.14 to 0.52)b0.09
 Add IL-100.80 (0.76 to 0.84)0.02 (0.01 to 0.04)b0.27 (0.07 to 0.45)b0.07
 LASSO+IL-80.80 (0.76 to 0.84)Reference model0.09
 Add IL-100.01 (−0.001 to 0.02)0.14 (−0.05 to 0.33)0.02
 Parsimonious model0.74 (0.70 to 0.79)Reference model0.43
 Parsimonious model+IL-80.78 (0.73 to 0.82)0.05 (0.03 to 0.07)b0.41(0.22 to 0.59)b0.17
  • LASSO, least absolute shrinkage and selection operator; TNFR, TNF receptor; AUROC, area under the receiver-operating characteristic curve; 95% CI, 95% confidence interval.

  • a All models were built using the validation cohort consisting of 423 participants.

  • b P<0.05 implies a statistical improvement for that particular metric by adding biomarkers.

  • c P<0.05 implies lack of fit when adding biomarkers over and above the reference model.