Skip to main content

Table 3 The effective performances of the model in the validation group

From: A novel model to predict mental distress among medical graduate students in China

Discrimination ability

AUROC

Slopea

95% CI

CCR

Sensitivity

Specificity

False POS

False NEG

Training group

0.70

0.06

0.04ā€‰~ā€‰0.08

82.30%

11.80%

94.70%

71.90%

14.10%

Validation group

0.66

0.04

0.02ā€‰~ā€‰0.06

81.30%

4.70%

96.70%

77.80%

16.60%

Calibration ability

Slopeb

95% CI

X-intercept

95% CI

Y-intercept

95% CI

Pc

Ā 

Training group

0.90

0.65ā€‰~ā€‰1.15

āˆ’0.02

āˆ’0.09ā€‰~ā€‰0.03

0.02

āˆ’0.03ā€‰~ā€‰0.06

0.82

Ā 

Validation group

0.80

0.51ā€‰~ā€‰1.09

āˆ’0.01

āˆ’ā€‰0.11ā€‰~ā€‰0.04

0.01

āˆ’ā€‰0.05ā€‰~ā€‰0.06

0.97

Ā 
  1. Abbreviations: AUROC the area under the receiver operating characteristic curve, CI Confident interval, CCR Correct classification rate, POS Indicates positive, NEG indicates negative
  2. a indicates discrimination slope;
  3. b indicates calibration slope;
  4. c indicates Hosmer and Lemeshow Goodness-of-Fit Test