# http://www.fpnotebook.com/

## Number Needed to Screen

*Aka: Number Needed to Screen, Number Needed to Treat, Absolute Risk Reduction, Relative Risk Reduction*

- See Also
- Screening Test
- Contingency Grid or Cross Tab (includes Statistics Example)
- Bayes Theorem (Bayesian Statistics)
- Fagan Nomogram
- Experimental Error (Experimental Bias)
- Lead-Time Bias
- Length Bias
- Selection Bias (Screening Bias)
- Likelihood Ratio (Positive Likelihood Ratio, Negative Likelihood Ratio)
- Negative Predictive Value
- Positive Predictive Value
- Pre-Test Odds or Post-Test Odds
- Receiver Operating Characteristic
- Test Sensitivity (False Negative Rate)
- Test Specificity (False Positive Rate)
- U.S. Preventive Services Task Force Recommendations

- Definition: Event Rate (Event Probability)
- Event Rate: (Number Events) / (Number Total Patients)
- Calculate for both intervention and control groups

- Definition: Relative Risk (RR)
- RR = (Intervention Event Rate)/(Control Event Rate)

- Definition: Relative Risk Reduction (RRR)
- Relative Risk Reduction or RRR = 1 - (Relative Risk)
- RRR = (Absolute Risk)/(Control Group Event Probability)
- Relative Risk and Relative Risk Reduction can be misleading when applied to an individual patient
- Relative Risk Reduction reflects the effect of an intervention on a population
- Effect is not guaranteed for the individual patient
- Number Needed to Treat (NNT) is a better measure of the chance that a positive effect will apply to the individual patient
- http://www.thennt.com/thennt-explained/

- Definition: Absolute Risk Reduction (ARR)
- ARR = (Intervention Event Rate) - (Control Event Rate)
- A negative result is seen with effective intervention, while a positive result is seen with a harmful intervention (worse than control)

- Definition: Number Needed to Screen (NNS) or Treat (NNT)
- Number of patients screened to prevent one death
- Assumes certain period of time (e.g. one year)
- NNS or NNT = 1/(Absolute Risk Reduction)
- NNT = 100/abs(rateTreatment - rateControl)
- Where Intervention is intended to prevent event X (e.g. Myocardial Infarction)
- Where rateTreatment = Rate of event X in treatment group (e.g. 5%)
- Where rateControl = Rate of event X in a control group (e.g. 10%)
- Example: NNT = 100/(5-10)=-20
- Twenty persons would need to undergo intervention, to prevent one event X
- In this case, the result is negative, consistent with Number Needed to Treat
- If the result were positive, the finding would be consistent with number needed to harm

- Resources
- Visual Tool

- References
- Cook (1995) BMJ 310:492-4 [PubMed]
- Daya (1999) Evid Based Obstet Gynecol 1:103-4
- Mcquay (1997) Ann Intern Med 126(9):712-20 [PubMed]