The concept of Number Needed to Treat has become popular because it combines an estimate of the Relative Benefit of a particular treatment with the background risk of patients. It is the inverse of the Absolute Risk Reduction and represents how many people would need to receive a particular treatment or intervention in order that one of them should benefit from the treatment.
A practical example can be taken from the recent concerns about third generation oral contraceptive pills and the risk of Deep Vein Thrombosis. It is thought that third generation pills carry a risk of DVT of about 25 per 100,000 women per year of use; in comparison second generation pills carry a risk of about 15 per 100,000 women years and in women who do not take the pill the risk is about 5 per 100,000 per year.
Switching users of third generation pills to a second generation equivalent will result in an impressive sounding Relative Risk Reduction of 40%, but as the risk of DVT is so low the Absolute Risk Reduction is only 0.0001 giving an NNT of 10,000 women needing to be changed to prevent a single DVT in one year.