Sensitivity And Specificity

Question 1

What is sensitivity?

Answer 1

The number of true positives correctly identified out of all the actual positives.

True positives/ true positive + false negative.

Question 2

What is specificity?

Answer 2

The number of negatives correctly identified out of all the actual negatives.

True negative/ true negatives + false positives

Question 3

What is the positive predictive value?

Answer 3

The proportion of positive results that are actually positive.

True positive/ true positive + false positive

Question 4

What are the negative predictive value?

Answer 4

Proportion of negative results that are actually negative.

True negative/ true negative + false negative.

Question 5

What is the null hypothesis?

Answer 5

The reasoning that there will be no difference when administering a new experimental drug.

Question 6

What is a type 1 error?

Answer 6

False positive/ Rejection of the null hypothesis when it is true

Question 7

What is a type 2 error?

Answer 7

False negative/ Accepting the null hypothesis when it’s false.

Question 8

What is a lead time bias?

Answer 8

Survival seems longer because diagnosis occurs earlier, such as through screening.

Question 9

What is a length time bias?

Answer 9

Overestimation of survival because Patients with slowly progressing diseases are more likely to be detected through screening than fast-progressing tumours, because fast-progressing tumours are detected through symptoms.

Question 10

What is a case control study?

Answer 10

Selecting people for an outcome and asking them to recall for exposure. It is calculated using odds ratio.

It is cheap and easy to conduct, but recall bias is an issue

Question 11

What is a cohort study?

Answer 11

Selecting a group of people based on an exposure and following them to see if they develop an outcome. It is calculated using relative risk.

It is expensive and risk of people dropping out of the study, and not ideal for rare disease. However it is good for risk factor analysis and determining disease time sequence.

Question 12

What is a cross-sectional study?

Answer 12

Snapshot in time to provide information about a population and prevalence, such as questionnaires.

Question 13

How to calculate odds ratio?

Answer 13

Odds of being exposed in the case/ odds of being exposed in control

Question 14

How to calculate relative risk?

Answer 14

Risk in the exposed/ risk in the control.

Question 15

What is ‘per protocol” analysis?

Answer 15

Analysing data from a Randomised controlled trial by removing any participant which did not comply with their treatment in either the experimental or control.

Question 16

What is “as treated” analysis?

Answer 16

Analysing the data from a Randomised controlled trial by placing non-compliant participants into a certain group, regardless of which group they were originally placed.

Question 17

What is “intention to treat” analysis?

Answer 17

Analysing data from a Randomised controlled trial by keeping non-compliant participants in the group they were originally randomised to.

Question 18

What is a systematic review?

Answer 18

Literature review search which involves:
Identifying all relevant studies related to the question, including unpublished and untrasnlated
Appraises the strength and evidence of papers
Synthesis of the findings to come to a conclusion.

Question 19

In a systematic review, what is the framework for searching for identifying relevant articles?

Answer 19

PICO

P: Patient
I: Intervention
C: Control
O: outcome

Question 20

What is important for identifying articles in systematic review?

Answer 20

—>Specific inclusion and exclusion criteria such as timeframe and type of trial.

There must be a rationale behind this to avoid missing studies that may influence the results. This can be language and the type of database used

Question 21

What is important for appraising articles in systematic review?

Answer 21

The size of the study participants
The type of study, e.g RCT are much better due to less bias than a cohort > case control.
Quality of study is important to avoid weak studies providing an overestimate of an effect.

—>A pre-determined criteria is important to make the process objective and transparent. It should be applicable for the patient you are treating.

Question 22

How does synthesis occur in systematic review?

Answer 22

Meta-analysis which collects the results from similar studies addressing a specific question into one pooled result in the form of a forest plot. The studies should not have too much heterogenity, such as many differences like intervention or population which limits the comparison that can be made

Question 23

What does the size of the square indicate in a forest plot?

Answer 23

Effect size of the study, located at the point of the 95% confidence interval value. The lines on ether side represent the range of the 95% confidence interval and the wider this is, the less significant the study is.

Question 24

What does the diamond represent in forest plot?

Answer 24

Overall pooled effect of all the studies. The points between the diamond are the 95% confidence interval.

Question 25

What are the benefits of systematic review?

Answer 25

Rigorous summary of all research evidence relating to a question, guarding against the limitations of a single study. Individual studies may have an inadequate sample size and lead to false negatives.

Question 26

Which study design is least subject to bias?

Answer 26

RCTs, the gold standard which avoids selection bias by using similar participants and randomly assigning to different groups, which ensures any difference is due to the outcome.

Question 27

What is the 95% confidence interval?

Answer 27

Range f values where the true value of the mean lies, with a z value of 1.96.

Question 28

What is Z value?

Answer 28

The number of standard deviations a value is from the mean.

Question 29

What is the p value?

Answer 29

Probability from 0-1 of obtaining the observed results, under the assumption that the p value is true.
The threshold is 0.05.
Values below 0.05 are statistically significant/ Values above this are not statistically significant.

Question 30

What is effect size?

Answer 30

Quantitative measure of the magnitude of the experimental effect, such as an intervention. The larger effect size, the stronger the relationship to the outcome being measured.

Question 31

What is deductive reasoning?

Answer 31

Coming to a valid specific conclusion based on a general idea.

Question 32

What is inductive reasoning?

Answer 32

Coming to a generalised conclusion about a treatment or group of people based on a specifically observed pattern.

Question 33

What is a sound argument?

Answer 33

An argument which fulfils 2 criteria:
1) Logically follows from the premises
2) The premises are true

Question 34

What makes an argument valid?

Answer 34

Logically follows from the premises.