Skip to main content

Table 2 Statistical validation analysis for the proposed multi-disciplinary algorithm

From: A stepwise multi-disciplinary algorithm for diagnosis of fibrosing lung diseases contributing MDCT, MRI, and PET/CT: a study on 250 patients using significance and validation analyses

Group

TP

FP

TN

FN

Prevalence

Sensitivity

Specificity

PPV

NPV

Accuracy

Balanced accuracy

Value

95% CI

Value

95% CI

Interstitial fibrosing diseases:

 

IPF

23

0

77

0

23%

100%

85.18% to 100.00%

100%

95.32% to 100.00%

100%

100%

100%

1

Fibrosing NSIP

18

3

78

1

19%

94.7%

73.97% to 99.87%

96.3%

89.56% to 99.23%

85.7%

98.7%

96.00%

0.955

Chronic HP

15

1

81

3

18%

83.3%

58.58% to 96.42%

98.8%

93.39% to 99.97%

93.8%

96.4%

96.00%

0.91

PPFE

0

2

98

0

0%

NA

NA

98.0%

92.96% to 99.76%

NA

100%

NA

NA

Non-interstitial fibrosing diseases

 

Post-TB fibrosis

15

0

83

2

17%

88.2%

63.56% to 98.54%

100%

95.65% to 100.00%

100%

97.7%

98.00%

0.94

Post-irradiation fibrosis

14

0

86

0

14%

100%

75.29% to 100.00%

100%

95.85% to 100.00%

100%

100%

100%

1

Fibrosing sarcoidosis

6

0

94

0

6%

100%

54.07% to 100.00%

100%

96.15% to 100.00%

100%

100%

100%

1

PMF

3

0

97

0

3%

100%

29.24% to 100.00%

100%

96.27% to 100.00%

100%

100%

100%

1

Complications of lung fibrosis

 

Malignancy

2

0

98

0

2%

100%

15.81% to 100.00%

100%

96.31% to 100.00%

100%

100%

100%

1

  1. TP True positive, FP False positive, TN True negative, FN False negative, CI Confidence interval, PPV Positive predictive value, and NPV Negative predictive value