Epi
Number Needed to Screen
search
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
http://www.nntonline.com
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]
Type your search phrase here