Table 4.

Overall performance of prediction models

OutcomePredictive ModelAUC (95% CI)SensitivitySpecificity
All-cause mortalityMortality base modela0.71 (0.66 to 0.76)48.580.8
Multibiomarker panelb0.74 (0.68 to 0.80)83.356.8
Self-rated health modelc0.80 (0.76 to 0.85)60.681.7
Multibiomarker panel plus self-rated health0.78 (0.72 to 0.84)76.967.3
Kidney disease progressionKidney disease progression base modeld0.88 (0.83 to 0.92)57.793.9
Multibiomarker panel0.89 (0.85 to 0.94)61.390.3
Self-rated health model0.93 (0.88 to 0.97)60.094.7
Multibiomarker panel plus self-rated health0.90 (0.83 to 0.96)76.294.0
Combined end pointCombined base modele0.73 (0.69 to 0.78)74.158.6
Multibiomarker panel0.76 (0.70 to 0.82)87.250.0
Self-rated health model0.81 (0.76 to 0.84)71.379.3
Multibiomarker panel plus self-rated health0.77 (0.72 to 0.81)67.374.8
  • Sensitivity and specificity estimated at the cut-point that predicted the probability of the outcome at ≥0.5. Pearson’s correlation coefficients between the self-rated health assessment and each of the biomarkers from the multibiomarker panel are as follows (higher value refers to worse self-rated health): r=0.14 for cystatin C, r=0.08 for logCRP, r=−0.16 for 25-hydroxyvitamin D, r=0.10 for parathyroid hormone, r=0.11 for fibroblast growth factor-23 (log-transformed), r=−0.12 for hemoglobin, r=0.09 for uric acid, and r=0.03 for anion gap. AUC, area under the curve; CRP, C-reactive protein.

  • a The mortality base model was composed of age, race, sex, eGFR, albuminuria, and the Framingham Risk Score (n=443).

  • b The multibiomarker panel included cystatin C, CRP (log-transformed), 25-hydroxyvitamin D, parathyroid hormone, fibroblast growth factor-23 (log-transformed), hemoglobin, uric acid, and anion gap (n=210).

  • c The self-rated health model combined age, sex, race, eGFR, albuminuria, and the participant’s response to the self-rated health question (n=443). The multibiomarker panel plus self-rated health model comprised 210 participants.

  • d The kidney disease progression base model included age, sex, eGFR, albuminuria, serum calcium, serum phosphate serum bicarbonate, and serum albumin (25) (n=443).

  • e The kidney disease progression plus mortality base model (combined base model) includes all characteristics from the mortality base model and the kidney disease progression base model.