Skip to main content

Table 2 Discrimination and calibration performance statistics for risk score models in estimating the 10-year risk of CVD death

From: Independent external validation of cardiovascular disease mortality in women utilising Framingham and SCORE risk models: a mortality follow-up study

 

FPR

SCORE-Low

SCORE-High

Quintiles

Actual

Predicted

Actual

Predicted

Actual

Predicted

  1

1*

0.1

0

0.0

0

0.0

  2

0

0.3

0

0.1

0

0.2

  3

2

0.8

2

0.6

2

1.0

  4

4

3.6

5

3.5

5

5.6

  5

21

29.7

21

28.3

21

42.4

Total

27

34.5

28

32.5

28

49.1

Hosmer-Lemeshow X2

4.74

6.09

12.06

Hosmer-Lemeshow p-value

0.1918

0.1074

0.0072

Calibrated model?

Yes

Yes

No

ROC AUC (95% CI)

0.858 (0.786 – 0.929)

0.877 (0.827 – 0.927)

0.877 (0.827 – 0.927)

  1. *An outlier was excluded from quintile 1 (1 death) in the calculation of the Hosmer-Lemeshow test, owing to its undue influence on the test. Including this outlier would result in the Hosmer-Lemeshow X2 = 14.35, p-value = 0.0025, and the risk score model being assessed as not calibrated. This outlier did not represent a woman with elevated risk factors associated with increased CVD risk, on further examination.
  2. Abbreviations: FPR, Framingham 10-year predicted risk for CVD death; SCORE-Low, SCORE-Low 10-year predicted risk for CVD death; SCORE-High, SCORE-High 10-year predicted risk for CVD death; ROC, receiver operating characteristic curve; AUC, area under the curve; CI, confidence interval.