Week 4 Methods for Diagnostic Analysis Flashcards
A, B, C
What is the primary purpose of a diagnostic test?
To determine whether someone has or doesn’t have a particular disease or condition.
What are the two possible outcomes of a diagnostic test?
- Positive (bad news) * Negative (good news)
What is assumed about the gold-standard test in diagnostic testing?
It is completely accurate—no mistakes.
What does ‘True Positives (TP)’ represent in diagnostic testing?
Correctly detected cases of the disease.
What does ‘False Positives (FP)’ represent in diagnostic testing?
Incorrectly detected cases where the test indicates disease when there is none.
In diagnostic testing, what is the formula for Positive Predictive Value (PPV)?
PPV = TP / (TP + FP)
What is the significance of a high Positive Predictive Value (PPV)?
Fewer false positives; more people who test positive actually have the disease.
What does Negative Predictive Value (NPV) indicate?
The chance that a person is actually healthy if their test result is negative.
What is the formula for Negative Predictive Value (NPV)?
NPV = TN / (TN + FN)
What does Sensitivity measure in diagnostic testing?
The likelihood that the test will correctly identify someone who has the disease.
What is the formula for calculating Sensitivity?
Sensitivity = TP / (TP + FN)
What does Specificity measure in diagnostic testing?
The likelihood that the test will correctly identify someone who does not have the disease.
What is the formula for calculating Specificity?
Specificity = TN / (TN + FP)
What does the overall accuracy of a test represent?
An overall idea of test performance.
What is the formula for calculating Accuracy?
Accuracy = (TP + TN) / (TP + TN + FP + FN)
How is Prevalence defined in the context of diagnostic testing?
The number of people in a population who have a specific disease at a given time.
What is the formula for calculating Prevalence?
Prevalence = number of existing cases of disease / total population at risk x 100
True or False: Sensitivity and specificity are dependent on the prevalence of a disease.
False
What do likelihood ratios (LRs) help determine in diagnostic testing?
How reliable a test result is in assessing the presence of a disease.
What does Positive Likelihood Ratio (LR⁺) indicate?
How much more likely a person is to have the disease after a positive test result.
What is the formula for calculating Positive Likelihood Ratio (LR⁺)?
LR⁺ = TP / FP
What does Negative Likelihood Ratio (LR⁻) indicate?
How much less likely a person is to have the disease after a negative test result.
What is the formula for calculating Negative Likelihood Ratio (LR⁻)?
LR⁻ = FN / TN
How can likelihood ratios be used with multiple tests?
They can be used cumulatively if tests are correlated only with respect to the disease.
What is a diagnostic threshold?
The cut-off point at which a test result is declared positive.
How does changing the diagnostic threshold affect sensitivity and specificity?
It changes both sensitivity and specificity of the test.
Fill in the blank: A test with high _______ is great for catching disease but may flag some healthy people.
[sensitivity]
Fill in the blank: A test with high _______ is great at confirming who’s healthy but might miss real cases.
[specificity]
What is the formula for calculating sensitivity?
Sensitivity = TP / (TP + FN)
TP = True Positives, FN = False Negatives
What is the formula for calculating specificity?
Specificity = TN / (TN + FP)
TN = True Negatives, FP = False Positives
What happens to sensitivity and specificity when the diagnostic threshold is lowered?
Sensitivity increases, specificity decreases
What happens to sensitivity and specificity when the diagnostic threshold is raised?
Sensitivity decreases, specificity increases
What does an ROC curve represent?
The trade-off between sensitivity and specificity at different thresholds
What does it indicate if an ROC curve hugs the top-left corner?
The test is highly accurate
What does it indicate if an ROC curve is a diagonal line?
The test is no better than random guessing
What is the purpose of the area under the ROC curve (AUC)?
It indicates the overall accuracy of the test
What does an AUC of 1.0 signify?
A perfect test with zero mistakes
What does an AUC of 0.5 signify?
A non-informative test, equivalent to random guessing
What is the relationship between false negatives and false positives when selecting a diagnostic threshold?
Choosing a threshold depends on which is considered worse
Fill in the blank: The likelihood ratio for a positive test result is calculated as LR+ = _______ / (1 – Specificity).
Sensitivity
Fill in the blank: The likelihood ratio for a negative test result is calculated as LR- = (1 – _______) / Specificity.
Sensitivity
What does a positive likelihood ratio (LR+) greater than 10 indicate?
Strong evidence for disease
What does a negative likelihood ratio (LR-) less than 0.1 indicate?
Strong evidence against disease
What does it mean if the ROC curve is closer to the top-left corner?
The test is better
What is the purpose of constructing a contingency table in diagnostic testing?
To organize the test results
What are the four outcomes in diagnostic testing?
- True Positive (TP)
- False Positive (FP)
- True Negative (TN)
- False Negative (FN)
True or False: Lowering the diagnostic threshold will always improve specificity.
False
True or False: ROC curves can help determine the ideal cut-point for a continuous diagnostic test.
True
What is the mathematical definition of AUC?
The probability that a randomly selected diseased individual has a higher test value than a non-diseased individual
What is the impact of a higher threshold on the number of false positives?
It decreases the number of false positives
What does it mean to use Bayes’ Theorem in diagnostic testing?
To adjust pre-test probability using likelihood ratios
