Skip to main content

Table 1 Performance of selected models in predicting attention deficit hyperactivity disorder diagnosis in the derivation and validation cohorts

From: Utility of medical record diagnostic codes to ascertain attention-deficit/hyperactivity disorder and learning disabilities in populations of children

 

Sensitivity

Specificity

Accuracy

PPV

NPV

Kappa

Concordance

ENET-MIN all codesa

 Derivation cohort

0.94

0.99

0.98

0.84

0.99

0.88

0.99

 Validation cohort

0.69

0.99

0.96

0.93

0.96

0.77

0.93

ENET-MIN selected codesa

 Derivation cohort

0.82

0.97

0.96

0.69

0.99

0.73

0.93

 Validation cohort

0.76

0.98

0.96

0.85

0.97

0.78

0.91

Single code

 Derivation cohort

0.90

0.96

0.95

0.82

0.98

0.83

0.93

 Validation cohort

0.81

0.98

0.96

0.83

0.97

0.80

0.89

  1. PPV positive predictive value, NPV negative predictive value, ENET-MIN Elastic Net model with tuning parameters minimizing cross-validation mean misclassification error
  2. aprior probability for models set at 0.25