Skip to content
Omnikalc

Number needed to treat calculator: how many must be treated for one to benefit?

Enter the event rate in the control and treated groups to get the NNT, absolute and relative risk reduction, relative risk and odds ratio.

Updated on

Educational tool, not medical advice: this page does not diagnose and does not replace a doctor, nurse or pharmacist. It has not been reviewed by a healthcare professional. Editorial and medical policy

Your inputs
%

Value out of range

%

Value out of range

Results

Number needed to treat (NNT) or to harm (NNH if the treatment raises risk)

20

A moderate NNT
Absolute risk reduction (ARR)
5.00%
Relative risk reduction (RRR)
25.0%
Relative risk (RR)
0.75
Odds ratio (OR)
0.71
Events prevented per 1,000 people treated (negative = caused)
50.0

The number needed to treat (NNT) puts the benefit of a treatment into a number anyone can picture: how many people must be treated for one extra person to benefit. This calculator takes the event rate in the control and treated groups and gives the NNT, the absolute and relative risk reductions, the relative risk and the odds ratio.

How the calculation works

  • Absolute risk reduction (ARR) = control rate − treated rate
  • Relative risk reduction (RRR) = ARR ÷ control rate
  • Relative risk (RR) = treated rate ÷ control rate
  • Odds ratio = [treated ÷ (1 − treated)] ÷ [control ÷ (1 − control)]
  • NNT = 1 ÷ ARR, rounded up; a negative ARR means a number needed to harm

Example

In a trial, 20 % of the control group and 15 % of the treated group have the event. The ARR is 5 percentage points, the RRR is 25 %, and the relative risk is 0.75. The NNT is 1 ÷ 0.05 = 20: treating 20 people prevents one event, or 50 events prevented per 1,000 treated. The odds ratio is 0.71.

Why it matters

Headlines love relative figures such as “cuts the risk by a quarter”. The NNT shows what that means for a patient, and lets you compare a drug that prevents a heart attack with a vaccine, a screening test or a side effect on the same scale.

Good to know

The NNT applies to the time period and the population of the study. It has no confidence interval here, although published values should have one. Different baseline risks can give a different NNT for the same relative effect. This calculator is for education and does not give medical advice. When you read a study, also look at how long patients were followed, how the outcome was defined and whether the result is statistically significant, because a small trial can produce a large effect by chance.

The relative risk calculator adds confidence intervals, the odds calculator converts between odds and probability, and the sensitivity and specificity calculator assesses a diagnostic test.

Frequently asked questions

What is the number needed to treat?

The NNT is how many people must receive a treatment for one of them to benefit who would not have without it, over the study period. It is 1 divided by the absolute risk reduction.

Why not just use the relative risk reduction?

A 25 percent relative reduction sounds large but can come from a risk falling from 20 to 15 percent or from 0.4 to 0.3 percent, which are very different benefits. The NNT and the absolute change keep that context.

What is the number needed to harm?

If the treated group has a higher event rate, such as a side effect, the same formula gives the number needed to harm, the number treated for one extra harm.

Is the NNT fixed for a treatment?

No. It depends on the baseline risk, the time period and the outcome. The same drug has a lower NNT in high-risk patients than in low-risk ones, and a longer follow-up usually lowers the NNT.

Was this calculator helpful?

Thanks for your feedback!

Results are estimates provided for information purposes. They do not replace professional advice.