Nelson Flashcards
Precision
ability of a test to reproduce the same result when repeated
Accuracy
ability of a test to actually measure what it claims to measure correctly
Sensitivity
True positives over total positives - probability that an individual with the disease will test positive - A test with high sensitivity will not miss many patients who have the disease (low false negative rate)
A highly sensitive test minimizes the number of false negatives, often at the expense of specificity.
If a highly sensitive test is negative, it is unlikely that the individual has the disease in question - used as screening test!
SNOUT = Sensitive test when negative rules out the disease
Specificity
True negatives over total negatives - probability that an individual without the disease will test negative. A test with high specificity will infrequently identify patients as having a disease when they do not (low false positive rate) [this is why we want to use it in confirming diagnosis]
A highly specific test minimizes the number of false positives, often at the expense of sensitivity. Thus, if a highly specific test is positive, it is quite likely that the individual has the disease.
SPIN = Specific test when positive rules in the disease
Positive Predictive Value (PPV)
Like sensitivity, but it measures the population, not the test
Based off of populations - It is the probability that a positive test correctly identifies an individual who actually has the disease. Calculated by taking the true positives and dividing them by all who test positive for the disease [Ex: if you test a large population that is unlikely to have a disease, the PPV will be very low]
Negative Predictive Value (NPV)
Refers to the probability that a negative test correctly identifies an individual without the disease. It is calculated from the true negatives divided by all who test negative for the disease.
[Affected by disease prevalence - snapshot of the population at that time]
