Some statistical measures in evidence-based medicine, such as RRR, ARR and NNTwere introduced.
NNT defines the number of patients who need to be treated in order to achieve one additional favorable outcome, and NNH is defined as the number of patients who must be treated with a therapy in order to have one additional patient suffer an adverse effect compared with the control treatment. This is the most important thing that should beconsidered before administering a treatment. NNT can also be used to assess the relative benefit or harm in the comparison of intervention versus positive control. If the effect is smaller in the intervention group than that in the control group, NNT should be used; if the effect is bigger in the intervention group than that in the control group, NNH should be used. When comparison is made between an intervention versus placebo, NNT and NNH are absolute outcomes; when an intervention is compared to a positive control, NNT and NNH are relative outcomes. RR or OR or RD may help to judge which comparator has bigger or smaller effect, and whether NNT or NNH should be used.