Critical appraisal

Question 1

How do you calculate sensitivity?

Answer 1

Sensitivity

= TP/(TP+FN)

Question 2

How do you calculate specificity?

Answer 2

Specificity

= TN/(FP+TN)

Question 3

How do you calculate NPV?

Answer 3

= TN/(TN+FN)

Question 4

How do you calculate PPV?

Answer 4

= TP/(TP+FP)

Question 5

How do you calculate positive likelihood ratio?

Answer 5

= sensitivity/(1- specificity)

= [TP/(TP+FN)]/[1-(TN/(FP+TN))]

Question 6

How do you calculate negative likelihood ratio?

Answer 6

= (1-sensitivity)/specificity

= [1-(TP/(TP+FN))]/[TN/(FP+TN)]

Question 7

How do you calculate OR?

Answer 7

= (TPxTN)/(FPxFN)

Question 8

How do you calculate RRR?

Answer 8

= 1-RR

Question 9

How do you calculate NNT?

Answer 9

= 1/ARR

Question 10

How do you calculate ARR?

Answer 10

= incidence in intervention group - incidence in control group

Question 11

How do you calculate RR?

Answer 11

= incidence in intervention group/incidence in control group

Question 12

What is the definition of sensitivity?

Answer 12

Given that a disease is present, what is the probability that the test is positive
SnOUT (likelihood positive test is positive)

Question 13

What is the definition of specificity?

Answer 13

Given that the disease is absent, what is the probability that the test is negative
SpIN (likelihood negative test is negative)

Question 14

What is the definition of positive predictive value (PPV)?

Answer 14

Given that the test is positive, the probability that the disease is present

Question 15

What is the definition of negative predictive value?

Answer 15

Given that the test is negative, the probability that the disease is absent

Question 16

What is a type I error?

Answer 16

The probability that the difference observed in a study sample is simply due to chance aka p value

Question 17

What is type II error?

Answer 17

Based on an estimate of the “true difference” between groups, what is the chance that the difference in the study sample will not be statistically significant

Question 18

What is power?

Answer 18

Power = 1 - Type II error

Question 19

What is the definition of number needed to treat (NNT)?

Answer 19

The number of patients who need to be treated in order to prevent one additional bad outcome

Question 20

What is the definition of internal validity?

Answer 20

The degree to which the study truly answers the question it poses

Question 21

What is the definition of external validity?

Answer 21

Can the study results be generalized to other populations

Question 22

What is clinical equipoise?

Answer 22

State of uncertainty as to the balance of benefits and harm that may result from two or more therapeutic regimens.

Indication for a RCT

Question 23

What is a meta-analysis?

Answer 23

A quantitative, formal, epidemiological study design used to systematically assess previous research studies to derive conclusions about that body of research

Question 24

What is a systematic review?

Answer 24

A systematic review summarizes the results of available carefully designed healthcare studies (RCT) and provides a high level of evidence on the effectiveness of health care interventions

Question 25

What is the difference between a systematic review and meta analysis?

Answer 25

A systematic review answers a defined research question by collecting and summarizing all empirical evidence that fits pre-specified eligibility criteria A meta analysis is the use of statistical methods to summarize the results of these studies

Question 26

What is the interpretation of a forest plot?

Answer 26

Horizontal line = individual study with result as a box and the 95% CI as a line If a study crosses the vertical line it means it crosses the null value Diamond = average of all individual studies with the horizontal points of the diamond 95% CI I2 statistic = heterogeneity of studies, if >50% means studies are inconsistent

Question 27

What is a cohort study?

Answer 27

A longitudinal study where you observe a group with a certain exposure over time and look for development of an outcome. Retrospective or prospective

Question 28

What are the pros of a cohort study?

Answer 28

* treatment not withheld * generally cheaper than RCTs * can estimate relative risk (incidence)

Question 29

What are the cons of a cohort study?

Answer 29

* controls may be difficult to obtain * does not deal with unanticipated confounders * blinding is more challenging * can be expensive * challenging for rare diseases/outcomes

Question 30

What is a case control study?

Answer 30

Groups identified on the basis of OUTCOME (disease and control). Compare rates of exposure retrospectively. Can match cases and controls based on potential con founders. Can give an estimate of odds ratio

Question 31

What are the pros of a case control study?

Answer 31

* relatively quick and cheap | * maybe the only feasible method to study rare disease of long lag from exposure to outcome

Question 32

What are the cons of a case control study?

Answer 32

* recall/record bias * choice of controls can be problematic * does not deal with unanticipated confounders * no incidence rates/relative risk