Disease incidence and prediction. Flashcards

1
Q

Tests that define an exposure or a disease status are subjected to what sort of error?

A

Systematic and random error.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Is random or systematic error important in regards to bias?

A

Systematic.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What two things can result in information bias?

A
  1. Imperfect definitions of study variables.

2. Flawed data collection procedures.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What can information bias result in?

A

Misclassification of exposure or disease.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What two types of misclassification bias exist?

A
  1. Non differential.

2. Differential.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What sort of bias exhibits bias towards the null (in terms of the Odds Ratio)?

A

Non differential.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Misclassification bias is similar but different to information bias. True or false?

A

False, misclassification bias is a type of information bias.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Is the OR higher, lower, the same, or both in differential misclassification bias?

A

Both, it can be higher or lower.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Define non differential misclassification bias.

A

The same amount of bias towards exposed/ non exposed state is the same in both the cases and control group.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Define differential misclassification bias.

A

The same amount of bias towards exposed/ non exposed state is different in the cases and control group.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What defines the ‘True status’ of a disease when testing a new diagnostic test?

A

The current gold standard test.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Define sensitivity.

A

Proportion of individuals with a disease which test positive.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Define specificity.

A

Proportion of those without a disease who tested negative.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the equation for sensitivity?

A

TP/(TP+FN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the equation for specificty?

A

TN/(TN+FP)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the equation for false positivity rate?

A

FP/(FP+TN) –> FP/ all non diseased

17
Q

What is the equation for false negative rate?

A

FN/(FN+TP) -> FN/ all diseased

18
Q

Define ‘Positive Predictive Value’ (PPV).

A

Proportion of positive tests that correctly identify diseased individuals.

19
Q

Define ‘Negative Predictive Value’ (NPV)

A

Proportion of negative tests that correctly identify non-diseased individuals.

20
Q

What is the equation for PPV?

A

TP/(TP+FP).

21
Q

What is the equation for NPV?

A

TN/(TN+FN)

22
Q

Which of the following vary with as disease prevalence varies?

  1. Specificity.
  2. Sensitivity.
  3. PPV.
  4. NPV.
A

PPV/NPV.

23
Q

Despite the fact that PPV and NPV are influenced by prevalence a good test will always show a good PPV. True or false?

A

False. A good test can result in a poor PPV if the prevalence is low.

24
Q

Is PPV or NPV more commonly used?

A

PPV (specificity is used more than sensitivity also).

25
Q

Disease prevalence does not modify sensitivity or specificity. What does?

A

The chosen cut-off value of a continuous variable.

26
Q

What does lowering the cut-off point of a test do? Why does it do this?

A

Improves sensitivity but lowers specificity.

More false positives.

27
Q

What does increasing the cut-off point of a test do? Why does it do this?

A

Lowered sensitivity but improved specificity.

More false negatives.

28
Q

When is cut point decision in disease status especially important?

A

When the distribution of characteristic is ‘unimodal’. This is because the ‘grey area’ is so large.

29
Q

Is a test with a sensitivity of 50%/ specificity of 50% better or worse than a test of sensitivity of 1%/ specificity of 1% better?

A

Sensitivity of 1%/ specificity of 1%. This is because if you swap the definitions over it becomes 99%/ 99%.

30
Q

What does ROC stand for and why is it used?

A

Receiver Operator Characteristics.

Used to analyse the trade of between sensitivity and specificity.

31
Q

Would a ROC curve closer to the top left or bottom left corner represent a better test?

A

Top left corner.

32
Q

What is the AUC for a ROC curve and what does it show?

A

Area under the curve.

When this is 1 the test is perfect.

33
Q

What does a diagonal line of 45 degrees on a ROC curve represent?

A

A test with no diagnostic value (same amount of true positives and false negatives).

34
Q

What can you correct for if sensitivity and specificity are known?

A

Misclassification, providing you have the data for correctly classified subjects.