Table 4.

Comparison of multivariate logistic regression model and chi-squared automatic interaction detection classification tree

ModelAUC (95% CI)Sensitivity (%)Specificity (%)PPV (%)NPV (%)
Multivariate logistic regressiona0.85 (0.77 to 0.92)76.979.135.076.5
CHAIDb0.91 (0.87 to 0.96)c30.898.980.490.7
  • Multivariate logistic regression and CHAID models were generated using the following variables: Cleveland Clinic score, percentage increase in serum creatinine at the time of sample collection, urinary angiotensinogen-to-creatinine ratio (uAnCR), and urinary renin-to-creatinine ratio (uRenCR). AUC, area under the receiver-operating characteristic curve; CI, confidence interval; PPV, positive predictive value; NPV, negative predictive value; CHAID, chi-squared automatic interaction detection.

  • a Cutoff specific performance characteristics shown are from the point on the receiver-operating characteristic curve closest to the point of 100% sensitivity and specificity.

  • b Cutoff specific performance characteristics shown are for the node representing uAnCR >337.89 ng/mg and uRenCR >893.41 pg/mg.

  • c P=0.02 compared with multivariate logistic regression model.