Net benefit calculator

Explanation

Scenario 1: No test available
You are considering a Treat/No Treat decision. In the absence of a test, the best decision depends on the probability of disease and:

     C = The Cost (used generally to include all harms)associated with treating someone without the disease
     B = The Benefit of treating someone with the disease (compared with not treating)

The treatment threshold probability P_tt is where the expected benefit associated with treatment first exceeds 0 (the benefit we assign to not treating)

Scenario 2: Dichotomous test available
Add the possibility of doing a dichotomous test. Now you can

• withhold treatment without testing (No Treat)
• do the test and treat if positive (Test)
• treat without testing (Treat).

Two probability thresholds, the No Treat/Test and the Test/Treat threshold, divide the entire range of pre-test probabilities (0.0 to 1.0) into 3 regions, in each one of which one of these strategies is optimal. In addition to C and B above, these threshold probabilities depend on the cost and accuracy of the test and on the "regret" associated with treatment decision errors. Specifically, the additional parameters are:
     T = the cost or harm from associated with doing the test
     Sensitivity = Probability of a positive test in people with disease P(T+|D+)
     Specificity = Probability of negative test in people without the disease P(T-|D-).

Chapter 2 of Evidence-Based Diagnosis uses a slightly different approach to demonstrating these concepts, called Regret Graphs. If you are reading Chapter 2, you may want to switch to the Regret Graph Calculator tab on this website. The difference is that the in expected benefit graphs on this tab all benefits and costs are in relation to not treating, whereas with regret graphs we graph regret compared with the zero regret associated with making the right decision (treating disease and not treating nondisease).