Fig. 1.

ROC curve for predictive performance in CF diagnosis, defined as compatible clinical presence plus positive pilocarpine test, model evaluated; the total yield reached 91.1%, with an AUC: 0.963. The best cut point was reached with a probability p ≥ 0.25, the prediction model reached a total yield of 91.1%, with a sensitivity of 93.3% (95% CI: 77.9% to 99.2%); specificity of 90.7% (95% CI: 84.8% to 94.8%); a positive predictive value (PPV) of 66.7% (95% CI: 54.6% to 76.9%) and a negative predictive value of 98.6% (95% CI: 94.7% a 99.6%), total area under the curve (AUC) was calculated at 0.963.