Lecture 26-28: Screenings In Medicine

Question 1

What are the two general questions a patient has for a physician regarding medical screening?

Answer 1

1. How ACCURATE is the screening test you are about to recommend for me?
2. Based on the test results, how CONFIDENT will you be in your prediction of whether I do or don’t have the disease?

Question 2

What are the 4 outcomes of a screening?

Answer 2

True Positive
False Positive
True Negative
False Negative

Question 3

In the 2x2 table, what is represented with A + B

A + C?

Answer 3

A+ B = Total Number of Positive Screening results (True and False)

A + C = Total Number of those with disease presence (true Positive and false negative result)

Question 4

Describe Sensitivity?

Answer 4

• How well A Test can Detect Presence Of Disease when in fact disease is Present
• POSITIVITY-OF-TEST IN THE DISEASED
• Proportion of time that a TEST is Positive in a patient that Does have the disease
• A HIGHLY SENSITIVE TEST HAS A LOW FALSE NEGATIVE RATE

Question 5

Describe the Formula for sensitivity

Answer 5

Sensitivity = TP ÷ (TP + FN) x 100%. (Or A / (A + C))

Or TP / (All Diseased) * 100%

Question 6

Describe Specificity

Answer 6

• How well A Test can Detect Absence of Disease when in fact the disease is Absent
• NEGATIVITY-OF-TEST IN THE HEALTHY
• Proportion of time that a TEST is NEGATIVE in a patient that Does Not have the disease
• A Highly Specific Test Has A LOW FALSE POSITIVE RATE

Question 7

What is the formula for specificity

Answer 7

Specificity = TN ÷ (TN + FP) x 100% 
OR 
(D / (D + B)) * 100%
OR
Specificity = TN ÷ (All Not Diseased) x 100%

Question 8

Describe Positive Predictive Values (PPV)

Answer 8

• How accurately a POSITIVE test PREDICTS the PRESENCE of disease
• Percentage of TP’s in patients with a positive test (correct prediction)
• Also referred to as Predictive Value-Positive (PVP)

Question 9

Give the formula for calculating PPV

Answer 9

PPV = TP ÷ (TP + FP) x 100% 
OR
PPV = TP ÷ (All Positive Tests) x 100%
OR
PPV = A / (A + B) x 100%

Question 10

Describe Negative Predictive Value (NPV)

Answer 10

• How accurately a NEGATIVE test PREDICTS the ABSENCE of DISEASE
• Percentage of TN’s in patients with a negative test (correct prediction)
• Also referred to as Predictive Value-Negative (PVN)

Question 11

Give the Formula for NPV

Answer 11

NPV = TN ÷ (TN + FN) x 100% 
OR
NPV = TN ÷ (All Negative Tests) x 100%
OR
NPV = D / (C + D) x 100%

Question 12

Describe Diagnostic Accuracy (DA) or Diagnostic Prediction (DP)

Answer 12

Proportion of time that a patient is CORRECTLY IDENTIFIED as either having a disease or not having a disease with a positive or negative test, respectively

DA/DP = (TP + TN) ÷ (TP+FP+FN+TN) x 100%
OR
DA/DP = (TP + TN) ÷ (All Patients) x 100%

Question 13

Describe Likelihood Ratios (LR)

Answer 13

Definition:

• Ratio of the probability of a given test result (positive or negative) for a person WITH THE DISEASE divided by the probability of the same test result (positive or negative) for a person WITHOUT THE DISEASE
• Can be calculated for both POSITIVE AND NEGATIVE

Question 14

Describe the Likelihood of Ratio Positive (LR+)

Answer 14

• Probability of a POSITIVE test in the PRESENCE of disease divided by the Probability of a POSITIVE test in the ABSENCE of disease
• Sensitivity divided by (1-Specificity),
  OR
  [(A/(A+C)) / (B/(B+D))]

Question 15

Describe the Likelihood Ratio Negative (LRP-)

Answer 15

• Probability of a NEGATIVE test in the PRESENCE of disease divided by the Probability of a NEGATIVE test in the ABSENCE of disease
  = (1-Sensitivity) / Specificity,
  or
  [(C/(A+C)) / (D/(B+D))]

Question 16

How does one tell if LR is beneficial?

Answer 16

• LR+ should be >10 to demonstrate the test is most beneficial
• LR- should be <0.1 to demonstrate the test is most beneficial

Question 17

Describe Validity

Answer 17

• Ability to accurately discern between those that do and those that do not have the disease – “TELLING THE TRUTH”
• INTERNAL VALIDITY: Extent to which results accurately reflect what was being assessed (true situation of study population)
• EXTERNAL VALIDITY: Extent to which results are applicable to other populations (not included in the original study; also known as “GENERALIZABILITY”)

Question 18

Describe Reliability

Answer 18

Side NOTE: It seems the table’s a lot more important this time. So may wanna practice drawing it or something.

Ability of a test to give the SAME RESULT on repeated uses
- Analogous to: REproducibility/Consistency

• A VALID test is ALWAYS RELIABLE, yet a RELIABLE test is NOT ALWAYS VALID

Question 19

Describe Multiple Cutoff Values

Answer 19

• Many diagnoses typically have two dichotomous outcomes (POSITIVE/NEGATIVE)
• What if there are potentially multiple cut-off values that correspond with better sensitivity vs. specificity?
• For screening tests with numerical values, we use ROCs (RECEIVER OPERATOR CURVES)
• A more efficient way to show a relationship between sensitivity & specificity for tests with numerical (continuous) outcomes
• Practice the problem on slide 24 - 31