Plot versus prevalence

Command:

Statistics ROC curves Plot versus prevalence

Description

In this graph (part of ROC curve analysis) you can plot positive and negative predictive values against disease prevalence, for one pair of sensitivity/specificity values.

You obtain sensitivity and specificity values from ROC curve analysis or from the literature.

• Positive predictive value
  Probability that the disease is present when the test is positive.
  $$ PPV = \frac {sensitivity \times prevalence } {sensitivity \times prevalence + (1-specificity)\times (1-prevalence) } $$
• Negative predictive value
  Probability that the disease is not present when the test is negative.
  $$ NPV = \frac {specificity \times (1-prevalence) }{ (1-sensitivity) \times prevalence + specificity \times (1-prevalence) } $$

Optionally the program can draw the 95% confidence intervals.

Required input

Giguère et al. (2016) studied the use of stall-side serum amyloid (SAA) for early detection of pneumonia on a farm endemic for R. equi. For an optimal cut-point of >53 μg/mL they found a sensitivity of 64% and a specificity of 77%.

• Sensitivity and Specificity: enter sensitivity and specificity as a percentage.
• Options: see below

Graph

In the graph the positive and negative predictive values are plotted against disease prevalence.

Plotting the 95% confidence intervals

MedCalc can also draw the 95% confidence intervals in the graph. This requires you to enter the number of cases in the diseased and normal groups. These are the number of cases included in the study in which sensitivity and specificity were established.

First click the option 95% Confidence Interval and next enter the number of cases in the diseased and normal groups.

The study by Giguère et al. (2016) included 25 foals with a culture-confirmed R. equi pneumonia (the positive or diseased cases in which sensitivity was established), and 22 foals that remained clinically healthy during the entire breeding season (the negative or normal cases, in which specificity was established).

Graph

The new graph includes the 95% confidence intervals for positive and negative predictive values.

MedCalc calculates the confidence intervals for the predictive values using the standard logit method given by Mercaldo et al. 2007.

Literature

• Giguère S, Berghaus LJ, Miller CD (2016) Clinical assessment of a point-of-care serum amyloid A assay in foals with Bronchopneumonia. Journal of Veterinary Internal Medicine 30:1338-1343.
• Mercaldo ND, Lau KF, Zhou XH (2007) Confidence intervals for predictive values with an emphasis to case-control studies. Statistics in Medicine 26:2170-2183.

See also

• ROC curve analysis
• Plot versus criterion values: Plots sensitivity and specificity versus criterion values
• Format graph
• Graph legend
• Add graphical objects
• Reference lines