This paper explains the number needed to treat and its implications in clinical research, highlighting common interpretive pitfalls.
The Number Needed to Treat (NNT) is an intuitive tool for evaluating intervention effectiveness, and plays a valuable role in informed medical decision-making. This paper explains the calculation of NNT for risks estimated using both binary and time-to-event data, and introduces related concepts such as the Number Needed to Harm (NNH) and the Likelihood to be Helped or Harmed (LHH). To ensure accurate interpretation, we address common pitfalls associated with NNT, and provide guidance for its correct application in clinical research, highlighting the importance of considering baseline risk, time, and confidence intervals when interpreting the NNT.
No takes yet. Share an insight, caveat, or question.
Chesnaye et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: