POSITIVE PREDICTIVE VALUE OF SCREENING
AND DIAGNOSTIC TESTS
Review Questions?
1. What is sensitivity?
a. The ability of the test to identify correctly those how HAVE the disease
2. What is specificity?
a. The ability of the test to identify correctly those WHO DO NOT have the disease
2. What is one drawback of too many False Negatives?
a. Not getting early intervention and treatment and the disease continues to develop
2. What is one drawback of too many False Positives?
a. Burden to the system, financial/emotional for the person, and de-labeling
Objectives
Define and discuss positive and negative predictive values
Discuss how the prevalence of an illness in a population can affect the PPV and NPV of a
screening test
Sensitivity and Specificity
Sensitivity and Specificity ask:
o "How good is the test at identifying people with the disease and people without the
disease?"
When we're screening populations, we want to know:
o "What proportion of people who have the disease will be correctly identified?"
Positive Predictive Value (PPV) of a Test
Understanding sensitivity and specificity is clearly an important public health consideration
However, in a clinical setting, a different question may be important for a physician:
o "If the test results are positive in this patient, what is the probability that this patient has
the disease?"
What does this mean for the patient/clinician?
Patient may need to make important decisions and the clinician may
have to offer up important information
This is called the Positive Predictive Value (PPV) of a test
Positive Predictive Value (PPV) of a Test (cont.)
Positive Predictive Value
o What proportion of patients who test positive for a test, actually have the disease in
question?
To calculate PPV, we divide the number of true positives by the total number tested positive
(true and false positives) and then times 100.
o PPV = TP/TP+FP = ____ X 100
,
o Using True Positives divided by All positives (TP and FP)
EXAMPLE:
Population
Results of Disease No Disease Totals
Screening
Positive 80 100 180
Negative 20 800 820
Totals 100 900 1,000
o PPV = TP/TP+FP = 80/180 = 0.4444 x 100 = 44.4 %
o Interpretation: Of the people who tested positive for this disease, only 44.4% actually had the
disease.
PPV is useful because it tells us
Negative Predictive Value of a Test
A parallel question can be asked about negative test results:
o "if the test result is negative, what is the probability that this patient doesn’t have the
disease?"
o What does this mean for the patient/clinician?
This is called the Negative Predictive Value (NPV) of the test
Negative Predictive Value (NPV) of a Test
Negative Predictive Value:
o What proportion of patients who test negative for a test, really don’t have the disease in
question?
Its calculated by dividing the number of true negatives by all those who tested negative (true
negative and false negative)
o NPV = TN/ TN+FN = ___ X 100
EXAMPLE:
o
Population
Results of Disease No Disease Totals
Screening
AND DIAGNOSTIC TESTS
Review Questions?
1. What is sensitivity?
a. The ability of the test to identify correctly those how HAVE the disease
2. What is specificity?
a. The ability of the test to identify correctly those WHO DO NOT have the disease
2. What is one drawback of too many False Negatives?
a. Not getting early intervention and treatment and the disease continues to develop
2. What is one drawback of too many False Positives?
a. Burden to the system, financial/emotional for the person, and de-labeling
Objectives
Define and discuss positive and negative predictive values
Discuss how the prevalence of an illness in a population can affect the PPV and NPV of a
screening test
Sensitivity and Specificity
Sensitivity and Specificity ask:
o "How good is the test at identifying people with the disease and people without the
disease?"
When we're screening populations, we want to know:
o "What proportion of people who have the disease will be correctly identified?"
Positive Predictive Value (PPV) of a Test
Understanding sensitivity and specificity is clearly an important public health consideration
However, in a clinical setting, a different question may be important for a physician:
o "If the test results are positive in this patient, what is the probability that this patient has
the disease?"
What does this mean for the patient/clinician?
Patient may need to make important decisions and the clinician may
have to offer up important information
This is called the Positive Predictive Value (PPV) of a test
Positive Predictive Value (PPV) of a Test (cont.)
Positive Predictive Value
o What proportion of patients who test positive for a test, actually have the disease in
question?
To calculate PPV, we divide the number of true positives by the total number tested positive
(true and false positives) and then times 100.
o PPV = TP/TP+FP = ____ X 100
,
o Using True Positives divided by All positives (TP and FP)
EXAMPLE:
Population
Results of Disease No Disease Totals
Screening
Positive 80 100 180
Negative 20 800 820
Totals 100 900 1,000
o PPV = TP/TP+FP = 80/180 = 0.4444 x 100 = 44.4 %
o Interpretation: Of the people who tested positive for this disease, only 44.4% actually had the
disease.
PPV is useful because it tells us
Negative Predictive Value of a Test
A parallel question can be asked about negative test results:
o "if the test result is negative, what is the probability that this patient doesn’t have the
disease?"
o What does this mean for the patient/clinician?
This is called the Negative Predictive Value (NPV) of the test
Negative Predictive Value (NPV) of a Test
Negative Predictive Value:
o What proportion of patients who test negative for a test, really don’t have the disease in
question?
Its calculated by dividing the number of true negatives by all those who tested negative (true
negative and false negative)
o NPV = TN/ TN+FN = ___ X 100
EXAMPLE:
o
Population
Results of Disease No Disease Totals
Screening
