APPRAISE: Harm Studies Part 2
Consider the results of harm studies:
- How strong is the association between exposure and outcome?
- What is the risk ratio or odds ratio?
- Is there a dose-response relationship between exposure and outcome?
- How precise was the estimate of the risk?
- What is the confidence interval for the relative risk or odds ratio?
Strength of Inference
For RCT or Prospective Cohort Studies: Relative Risk
Relative Risk (RR) = a / (a + b) / c / (c + d)
is the risk of the outcome in the exposed group divided by the risk of the outcome in the unexposed group:
RR = (exposed outcome yes / all exposed) / (not exposed outcome yes / all not exposed)
Example: “RR of 3.0 means that the outcome occurs 3 times more often in those exposed versus unexposed.”
Knowledge Check: A harm study finds a relative risk (RR) of 3.0 for heart disease in people who smoke compared with those who do not smoke. What does this mean?
A) Smokers are three times more likely to develop heart disease than non-smokers.
B) The harm study found little risk of heart disease among smokers compared to non-smokers.
C) Smoking and heart disease are not related.
Case Control or Retrospective Studies: Odds Ratio
Odds Ratio (OR) = (a / c) / (b / d)
is the odds of previous exposure in a case divided by the odds of exposure in a control patient:
OR = (exposed - outcome yes / not exposed - outcome yes) / (exposed - outcome no / not exposed - outcome no)
Example: “OR of 3.0 means that cases were 3 times more likely to have been exposed than were control patients.”
Confidence Intervals are a measure of the precision of the results of a study. For example, “36 [95% CI 27-51]“, a 95%CI range means that if you were to repeat the same clinical trial a hundred times you can be sure that 95% of the time the results would fall within the calculated range of 27-51. Wider intervals indicate lower precision; narrow intervals show greater precision.
Knowledge Check: A study reports a result of RR = 2.0 [95% CI 1.5–2.5]. What does the confidence interval (CI) tell you about this finding??
A) The result is very uncertain because the range is wide and includes 1.0.
B) The estimate is fairly precise, since the range is narrow and still shows an increased risk.
C) The confidence interval shows that the risk is definitely the same for both groups.
Confounding Variable is one whose influence distorts the true relationship between a potential risk factor and the clinical outcome of interest.
Learn more:
- The Odds Ratio, Douglas G Altman & J Martin Bland, BMJ 2000; 320:1468 (27 May).
- Understanding Odds Ratio, Gordon Guyatt, video (21 minutes).
Knowledge Check: In a case-control harm study, cases were interviewed in person about their past exposures, while controls completed an online survey. Which potential problem does this design introduce?
A) Recall or measurement bias due to differing methods for assessing exposure.
B) Selection bias caused by excluding participants with incomplete surveys.
C) Confounding from failure to match controls by age or gender.