study designs in medical research - university of...
TRANSCRIPT
![Page 1: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/1.jpg)
Study designs in medical researchStudy designs in medical research
1
![Page 2: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/2.jpg)
2
Study design is the procedure under which a study is
carried out
Study design is the procedure under which a study is
carried out
![Page 3: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/3.jpg)
Two main categoriesTwo main categories
• Observation:
• Identify subjects, then
• Observe and record characteristics
• Experiment
• Identify subjects,
• Place in common context,
• Intervene, then
• Observe effects of intervention
• Observation:
• Identify subjects, then
• Observe and record characteristics
• Experiment
• Identify subjects,
• Place in common context,
• Intervene, then
• Observe effects of intervention 3
![Page 4: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/4.jpg)
Observation vs ExperimentObservation vs Experiment
• Observations are readily obtained, but subject to bias, that is systematic errors
• Observations are readily obtained, but subject to bias, that is systematic errors
4
• Some observational designs are less subject to bias than others
• Some observational designs are less subject to bias than others
• Experiments are hard to do well• Experiments are hard to do well
• Experiments can answer narrow questions definitively
• Experiments can answer narrow questions definitively
• Generalizability of results from experiments may be at issue, eg new drug testing that excludes women subjects
• Generalizability of results from experiments may be at issue, eg new drug testing that excludes women subjects
![Page 5: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/5.jpg)
Observational studiesObservational studies
5
• Case Series
• Case-control studies
• Cohort Studies
• Case Series
• Case-control studies
• Cohort Studies
• (Meta-Analyses)• (Meta-Analyses)
![Page 6: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/6.jpg)
![Page 7: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/7.jpg)
![Page 8: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/8.jpg)
![Page 9: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/9.jpg)
![Page 10: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/10.jpg)
![Page 11: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/11.jpg)
![Page 12: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/12.jpg)
Case seriesCase series
• Example: “Normal plasma cholesterol in an 88-year-old man who eats 25 eggs a day” [Kern J, NEJM 1991; 324:896–899]
• Example: “Normal plasma cholesterol in an 88-year-old man who eats 25 eggs a day” [Kern J, NEJM 1991; 324:896–899]
12
• Advantages• Excellent at identifying unusual situation
• Good for generating hypotheses amenable to rigorous test
• Disadvantages• Generally short-term
• Investigators self-select (bias!)
• Generally no controls
• Advantages• Excellent at identifying unusual situation
• Good for generating hypotheses amenable to rigorous test
• Disadvantages• Generally short-term
• Investigators self-select (bias!)
• Generally no controls
![Page 13: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/13.jpg)
ControlsControls
• A control is a standard of comparison for
• Effects
• A control is a standard of comparison for
• Effects
13
• Variability• Variability
![Page 14: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/14.jpg)
Case-control studiesCase-control studies
• Controlled studies
• Retrospective
• Controlled studies
• Retrospective
14
![Page 15: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/15.jpg)
![Page 16: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/16.jpg)
How are Case-Control Studies Done?How are Case-Control Studies Done?
• Identify cases (with condition of interest, here, coccidioidomycosis)
• Match to disease-free controls who are similar with respect to known risk factors for condition
• Compare degree of exposure to possible risk factor (here, being in dust cloud).
• Identify cases (with condition of interest, here, coccidioidomycosis)
• Match to disease-free controls who are similar with respect to known risk factors for condition
• Compare degree of exposure to possible risk factor (here, being in dust cloud).
16
![Page 17: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/17.jpg)
The logic of Case-Control StudiesThe logic of Case-Control Studies
• Cases differ from controls only in having the disease
• If exposure does not predispose to having the disease, then exposure should be equally distributed between the cases and controls.
• The extent of greater previous exposure among the cases reflects the increased risk that exposure confers
• Cases differ from controls only in having the disease
• If exposure does not predispose to having the disease, then exposure should be equally distributed between the cases and controls.
• The extent of greater previous exposure among the cases reflects the increased risk that exposure confers
17
![Page 18: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/18.jpg)
Measures of effectMeasures of effect
• Relative risk (ratio of probabilities of contracting disease given exposure), or
• Odds ratio (ratio of the odds of contracting disease given exposure)
• RR or OR of 1 indicate no effect of exposure (equal odds)
• “Physically being in a dust cloud (OR 3.0; CI, 1.6-5.4; P<.001) significantly increased the risk for being diagnosed with coccidioidomycosis”
• Relative risk (ratio of probabilities of contracting disease given exposure), or
• Odds ratio (ratio of the odds of contracting disease given exposure)
• RR or OR of 1 indicate no effect of exposure (equal odds)
• “Physically being in a dust cloud (OR 3.0; CI, 1.6-5.4; P<.001) significantly increased the risk for being diagnosed with coccidioidomycosis”
18
![Page 19: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/19.jpg)
![Page 20: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/20.jpg)
![Page 21: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/21.jpg)
![Page 22: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/22.jpg)
Cohort studiesCohort studies
• Prospective
• Controlled
• Can determine causes and incidence of diseases as well as identify risk factors
• Generally expensive and difficult to carry out
• Procedure for cohort study
• Logic of the cohort study
• Prospective
• Controlled
• Can determine causes and incidence of diseases as well as identify risk factors
• Generally expensive and difficult to carry out
• Procedure for cohort study
• Logic of the cohort study
22
![Page 23: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/23.jpg)
Procedure for cohort studyProcedure for cohort study
• Identify groups of exposed subjects and control subjects
• Match for other risk factors
• Follow over time
• Record the fraction in each group who develop the condition of interest
• Compare these fractions using RR or OR
• Identify groups of exposed subjects and control subjects
• Match for other risk factors
• Follow over time
• Record the fraction in each group who develop the condition of interest
• Compare these fractions using RR or OR
23
![Page 24: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/24.jpg)
Logic of the cohort studyLogic of the cohort study
Differences in the rate at which exposed and control subjects contract a disease is due to the differences in exposure, since other known risk factors are equally present in the two groups
Differences in the rate at which exposed and control subjects contract a disease is due to the differences in exposure, since other known risk factors are equally present in the two groups
24
![Page 25: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/25.jpg)
![Page 26: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/26.jpg)
![Page 27: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/27.jpg)
Experimental studies
Experimental studies
27
![Page 28: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/28.jpg)
Clinical trialsClinical trials
A clinical trial is a comparative, prospective experiment conducted in human subjects. (4 requirements)
A clinical trial is a comparative, prospective experiment conducted in human subjects. (4 requirements)
28
Controlled vs Uncontrolled studiesControlled vs Uncontrolled studies
Historical controlsHistorical controls
![Page 29: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/29.jpg)
Controlled vs Uncontrolled studiesControlled vs Uncontrolled studies
• Controlled → comparison made relative to a simultaneous reference condition
• Uncontrolled → comparison implicit
• Previous experience
• Historical evidence
• Anecdote
• Controlled trials…
• Controlled → comparison made relative to a simultaneous reference condition
• Uncontrolled → comparison implicit
• Previous experience
• Historical evidence
• Anecdote
• Controlled trials…
29
![Page 30: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/30.jpg)
Controlled trials…Controlled trials…
• …make it possible to ascribe differences in outcome to differences in treatment
• Differences from expectation in uncontrolled studies could also be due to many other factors
• Different kinds of patients
• Change in standard of care
• Improving technique, etc
• …make it possible to ascribe differences in outcome to differences in treatment
• Differences from expectation in uncontrolled studies could also be due to many other factors
• Different kinds of patients
• Change in standard of care
• Improving technique, etc
30
![Page 31: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/31.jpg)
Historical controlsHistorical controls
• Are better than no controls
• Example: ddI vs AZT for AIDS
• Are better than no controls
• Example: ddI vs AZT for AIDS
31
• But not by much
• Example: gastric freezing for peptic ulcer
• But not by much
• Example: gastric freezing for peptic ulcer
![Page 32: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/32.jpg)
![Page 33: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/33.jpg)
Randomization & Concurrent ControlsRandomization & Concurrent Controls
• Randomized vs nonrandomized assignment to Rx• “The randomized clinical trial is the epitome of all
research designs because it provides the strongest evidence for concluding causation.”
• Conclusions from nonrandomized studies subject to many sources of bias
• Randomized vs nonrandomized assignment to Rx• “The randomized clinical trial is the epitome of all
research designs because it provides the strongest evidence for concluding causation.”
• Conclusions from nonrandomized studies subject to many sources of bias
33
![Page 34: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/34.jpg)
![Page 35: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/35.jpg)
Patients can serve as own controlsPatients can serve as own controls
• This is usually beneficial
• The comparison removes patient differences.
• This is usually beneficial
• The comparison removes patient differences.
35
![Page 36: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/36.jpg)
Example: Vasocon-AExample: Vasocon-A
• Subjects received placebo eye drops in one eye, Vasocon-A drops in the other eye
• Randomization determined which eye gets placebo for each pt
• Cat-dander extract applied to both eyes
• Response between eyes compared.
• Subjects received placebo eye drops in one eye, Vasocon-A drops in the other eye
• Randomization determined which eye gets placebo for each pt
• Cat-dander extract applied to both eyes
• Response between eyes compared.
36
![Page 37: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/37.jpg)
Paired designsPaired designs
• Work best when outcome can be observed shortly after treatment, and
• Disease and treatment are both short-lived
• Work best when outcome can be observed shortly after treatment, and
• Disease and treatment are both short-lived
37
![Page 38: Study designs in medical research - University of Chicagogalton.uchicago.edu/~thisted/courses/315/lectures/0297.pdf · Study designs in medical research Study designs in 1. 2 Study](https://reader031.vdocument.in/reader031/viewer/2022030500/5aac99f27f8b9a59658d39be/html5/thumbnails/38.jpg)
BlindingBlinding
• Good practice: factors that can affect the evaluation of outcome should not be permitted to influence the evaluation process
• Double-blind design• Neither patient nor outcome evaluator knows Rx to which
patient was assigned
• Single-blind• Patient or evaluator is blinded as to Rx, but not both
• Triple-blind• Patient, Physician, and Data analyst are blinded as to Rx
identity
• Good practice: factors that can affect the evaluation of outcome should not be permitted to influence the evaluation process
• Double-blind design• Neither patient nor outcome evaluator knows Rx to which
patient was assigned
• Single-blind• Patient or evaluator is blinded as to Rx, but not both
• Triple-blind• Patient, Physician, and Data analyst are blinded as to Rx
identity
38