Epi
Positive Predictive Value
search
Positive Predictive Value
, Test Precision
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
)
Number Needed to Screen
(
Number Needed to Treat
,
Absolute Risk Reduction
,
Relative Risk Reduction
)
Negative 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
Definitions
Positive Predictive Value (PPV)
Percent of patients with positive test having disease
P(Disease | test positive)
Assesses reliability of positive test
Precision
Identical to the PPV, but Precision term is used more in data science
Reflects what percentage of positive items are relevant (true positives)
See
Test Recall
(
Test Sensitivity
)
Indications
Puts
Test Specificity
in context of disease
Prevalence
Lower disease
Prevalence
results in lower PPV
Test Specificity
effect is magnified
False Positive
s increase substantially
Results in less reliable positive test
Example:
HIV Test
in a patient in a low risk, low
Prevalence
cohort has an increased risk of
False Positive
testing
Calculation
PPV = (True positive) / (True positive +
False Positive
)
Example 1
High
Prevalence
Disease
Major Depression
Prevalence
is 10 per 100
New
Screening Test
efficacy
Test Sensitivity
: 100%
Test Specificity
: 99% (1
False Positive
in 100)
Screen 1000 patients
True positives: 100 per 1000 (10%
Prevalence
)
False Positive
s: 10 per 1000 (99%
Test Specificity
)
PPV: 100 true positives / 110 total positives = 91%
Summary
Pre-Test Probability
: 10% (baseline
Prevalence
)
Post-Test Probability
: 91% (PPV)
Example 2
Low
Prevalence
Disease
Scleroderma
Prevalence
is 1 per 1000
New
Screening Test
efficacy
Test Sensitivity
: 100%
Test Specificity
: 99% (1
False Positive
in 100)
Screen 1000 patients
True positives: 1 per 1000 (0.1%
Prevalence
)
False Positive
s: 10 per 1000 (99%
Test Specificity
)
PPV: 1 true positive / 11 total positives = 9%
Summary
Pre-Test Probability
: 0.1% (baseline
Prevalence
)
Post-Test Probability
: 9% (PPV)
Contrast with PPV 91% for high
Prevalence
disease
Type your search phrase here