Absolute Risk Difference

Situation: You have two populations (or groups) for whom you have calculated their risk of a particular outcome.  A typical scenario is one group has been exposed to something that might cause a disease and the other one hasn’t.  Or one group has received treatment A and another treatment B, and you want to see if one of the treatments has a better chance of cure.

The absolute risk difference (“ARD”) is the observed risk in one group minus the observed risk in the other group.

ARD = Risk_A – Risk_B

The theoretical minimum and maximum of ARD is -1 to +1 (-100% to +100%).

Example.  This paper reports 30-day readmission risk for various subgroups of a patient population of 29,292.  The overall 30-day readmission risk was 11.7% (0.117).  For patients with sepsis (n=978), the 30-day readmission risk was 19.7% (0.197).

The absolute risk difference in this example is Risk_Sepsis – Risk_Other = 0.197 – 0.117 = 0.08 (8%).

Note: normally we would examine patients diagnosed with sepsis vs. all other patients not diagnosed with sepsis.  However, we can’t get that information from the paper so we are ignoring that issue for the sake of the example.  Sepsis patients represented only 3.3% of all admissions, so the error should be minimal.