Skip to main content

Table 1 Test characteristics of the RF algorithm for the Testing Algorithm in the Final Cohort

From: An algorithm to identify cases of pulmonary arterial hypertension from the electronic medical record

Dataset

AUC

Sensitivity

Specificity

PPV

NPV

Test (n = 338)

0.96

0.88

0.93

0.89

0.92

Training (n = 1356)

0.94 (0.94–0.95)

0.85 (0.83–0.87)

0.92 (0.91–0.92)

0.87 (0.85–0.88)

0.91 (0.91–0.92)

  1. For the cohort that was split into training and test sets (labeled “Final Test Set” and “Final Training Set” in Fig. 1). Values for training represent means and 95% confidence intervals based on 30 samples from tenfold cross validation repeated 3 times
Back to article page

Respiratory Research

ISSN: 1465-993X

Contact us