Skip to main content

Table 2 Results of breath analysis between patient groups

From: Differentiating interstitial lung diseases from other respiratory diseases using electronic nose technology

Group 1

n = 

Group 2

n = 

Dataset

AUC

95% CI

Specificity

Sensitivity

Accuracy

NPV

PPV

ILD

108

Asthma–COPD–Lung cancer

108

Training

0.97

0.95–0.99

0.93

0.93

0.93

0.93

0.93

 

53

 

53

Test

0.99

0.97–1.00

0.89

1.00

0.94

1.00

0.90

ILD

37

Asthma

44

Training

0.99

0.97–1.00

0.91

1.00

0.95

1.00

0.90

 

18

 

21

Test

1.00

1.00–1.00

1.00

1.00

1.00

1.00

1.00

ILD

37

COPD

34

Training

0.97

0.97–1.00

1.00

0.86

0.93

0.87

1.00

 

18

 

16

Test

0.96

0.90–1.00

0.94

0.89

0.91

0.88

0.91

ILD

37

Lung cancer

31

Training

1.00

1.00–1.00

1.00

1.00

1.00

1.00

1.00

 

18

 

15

Test

0.98

0.94–1.00

0.89

1.00

0.94

1.00

0.88

COPD

34

Lung cancer

31

Training

0.88

0.79–0.97

0.88

0.87

0.88

0.88

0.87

 

16

 

15

Test

0.97

0.90–1.00

1.00

0.93

0.97

0.94

1.00

COPD

34

Asthma

44

Training

0.92

0.85–0.98

0.95

0.76

0.87

0.84

0.93

 

16

 

21

Test

0.90

0.79–1.00

0.86

0.88

0.86

0.90

0.82

IPF

41

COPD

34

Training

0.88

0.80–0.96

0.71

0.98

0.85

0.96

0.80

 

20

 

16

Test

0.93

0.86–1.00

0.75

0.95

0.86

0.92

0.83

IPF

41

Lung cancer

31

Training

0.91

0.85–0.98

0.98

0.68

0.85

0.80

0.95

 

20

 

15

Test

0.93

0.82–1.00

1.00

0.87

0.94

0.91

1.00

  1. Results based on 2 principal components. AUC: area under the curve; CI: confidence interval; COPD: chronic obstructive pulmonary disease; ILD: interstitial lung disease; IPF: idiopathic pulmonary fibrosis; NPV: negative predictive value; PPV: positive predictive value