Game 4 · Study designs, risk and bias
Which study design is this?
Cross-sectional, case-control, cohort and trial designs, and PICO.
Read with: Study designs, The research question118 DNB questions
Play
Read the study, name the design
Each round describes a made-up study. Some rounds ask you to name the design, some to place the exposure and the outcome on a time line, some to match designs to the measure they give, and some to split a thesis question into PICO. You have three lives.
Loading the first round…
The idea
Two facts name almost every design
First, did the investigator assign the exposure? If yes, the study is experimental. If chance decided who received it, it is a randomised trial. If the investigator only observed exposures that people already had, the study is observational.
Second, for an observational study, when were the exposure and the outcome recorded? A cross-sectional study records both at one visit. A case-control study starts from people with and without the outcome and looks back at their past exposure. A cohort study starts from people free of the outcome, classifies them by exposure, and follows them forward.
Prospective and retrospective describe timing, not direction. A retrospective cohort uses old records but still runs from exposure to outcome. A case-control study that enrols new cases over the next two years is still a case-control study, because it runs from outcome back to exposure.
Cohort: exposure first, then wait for the outcome. Case-control: outcome first, then look back for the exposure. Cross-sectional: both at the same visit.
Design and measure
Each design gives its own measure
The totals the investigator fixes decide which proportions in a 2 × 2 table mean anything. A survey fixes only the total sample, so it gives prevalence. A case-control study fixes the numbers of cases and controls, so it cannot give incidence and gives the odds ratio. A cohort study follows people from exposure, so it gives incidence in each group and the relative risk. When follow-up time differs and some people are censored, the hazard ratio from Cox regression is used.
| Feature | Case-control | Cohort |
|---|---|---|
| Starts with | People with and without the disease | People with and without the exposure, all free of the disease |
| Direction | Outcome → past exposure | Exposure → later outcome |
| Best for | Rare diseases, long latency, many possible exposures | Rare exposures, several outcomes, when incidence is needed |
| Measure of association | Odds ratio | Incidence, relative risk, attributable risk |
| Time order | Can be uncertain | Clear |
| Main biases | Selection of controls, recall bias | Loss to follow-up, change in exposure over time |
The full classification, with nested case-control, case-cohort, cluster and quasi-experimental designs, is in the study designs chapter.
Levels of evidence
Where each design sits in the hierarchy
The traditional evidence pyramid has, from the base upwards: case series and basic science, then cohort and case-control studies, then randomised controlled trials, with systematic reviews and meta-analyses at the top. Designs less open to bias rank higher.
Murad and colleagues (2016) revised the pyramid in two ways. The lines between designs became wavy, because GRADE can rate the certainty of evidence up or down whatever the design. Systematic reviews were taken off the top and used as the lens through which the other studies are appraised.
The Oxford CEBM 2011 levels for “Does this intervention help?” run from 1 to 5. Level 1 is a systematic review of randomized trials or n-of-1 trials. Level 2 is a randomized trial or an observational study with dramatic effect. Level 3 is a non-randomized controlled cohort or follow-up study. Level 4 is case series, case-control studies or historically controlled studies. Level 5 is mechanism-based reasoning. The full tables are in the systematic review chapter.
PICO
A design follows from a well-built question
Richardson and colleagues proposed a four-part structure for clinical questions in 1995, now known as PICO. Each part becomes part of the protocol.
- P
- population: gives the inclusion and exclusion criteria
- I
- intervention: with C, gives the study groups
- C
- comparison: what the other group receives
- O
- outcome: gives the primary outcome, the measuring tool and the basis for the sample size
When you cannot assign the exposure (smoking, cooking fuel, a blood marker), write PECO: population, exposure, comparator, outcome. The design will then be observational. PICOT adds the time at which the outcome is measured. See the research question chapter.
Writing the answer
How to write this in a 10-mark DNB answer
- Start with a classification tree: observational (descriptive and analytical) and experimental (randomised and non-randomised).
- Draw a time line for each analytical design, marking when exposure and outcome are recorded and the direction of the arrow.
- Define each design in one line and give one clinical example, such as smoking and wound infection.
- Give the measure each design yields: prevalence, odds ratio, incidence and relative risk, hazard ratio.
- Add a table of advantages and limitations, and the case-control versus cohort comparison if the question asks for it.
- End with the hierarchy of evidence, and with PICO if the question is about framing a research question.
The one thing to remember
Name a design by who chose the exposure and the direction of enquiry, not by whether the data are old or new.
Past papers
DNB questions this game helps you answer
Questions from NBE theory papers for DNB, DrNB and Diploma courses, most often asked first. The tag after each question is the specialty and the year it was set.
- ×3Describe briefly the different types of research studies in medicine. [5]
- ×2Cohort study.
- ×2Case control study vs Cohort study.
- ×2Formulate a plan for statistical analysis of quantitative data obtained from three separate groups of subjects (n=50) in a cross-sectional study design.
- ×2Write a research protocol for epidemiological study to assess the effect of health education in a community.
- ×1Describe descriptive and analytical study designs. Where does “clinical trial” fall in the above classification? Describe the various phases of a clinical trial and give some examples of its use in genetic disorders. [4+2+4]
- ×1Briefly outline the various types of research study types.
- ×1Difference between the study design of case series and case control study.
- ×1Discuss in detail the steps involved in conducting a scientific research study, including formulation of a research problem, study design, data collection, analysis, and ethical considerations.
- ×1Discuss prospective vs retrospective study design.
- ×1Epidemiological Investigation of RA (EIRA) study was conducted to investigate the influence of environmental factors on the risk of developing rheumatoid arthritis. 679 patients with rheumatoid arthritis were compared with 847 individuals randomly selected from the population for smoking status. The incidence of RA in current smokers, ex-smokers and ever-smokers, respectively, was compared with that of never-smokers. a) What study design was it? b) What sampling technique would be appropriate for such a study? c) What are the potential biases? d) What is the measure of effect calculated in such a study? e) Enumerate the pros and cons of this study design.
- ×1Outline the various study designs in surgical research.
- ×1Case control and cohort study.
- ×1Cohort studies.
- ×1Define case control study and cohort study.
- ×1Differentiate between case control and cohort study.
- ×1Draw the schematic diagrams of the design of case-control and cohort studies. Explain the concept of matching with examples. How will you measure the strength of the association between the risk factor and the outcome in a case-control study?
- ×1Define evidence based medicine and hierarchy of evidence. Discuss in brief the various types of research studies.
- ×1Describe a quality improvement research methodology to decrease the door to needle time in a patient with acute myocardial infarction.
- ×1Describe study designs in medical research.
- ×1Sample size calculation in research methodology.
- ×1Systematic reviews are an important component of scientific writing and deliver a meticulous summary of all the available primary research in response to the research question : a) What are the steps of a systematic review? [3] b) Comment on: Are systematic review and meta-analysis different? [3] c) Draw a Forest Plot, with a brief description of its components.
- ×1Types of study designs for research.
- ×1What are the types of clinical study designs? Describe the characteristics of commonly used study designs. Compare these common design’s strengths and weaknesses.
- ×1What are the types of research studies?
- ×1What are the types of sampling methods in research methodology? Describe them in brief.
- ×1What is qualitative research? How does it differ from quantitative research in terms of essential features, strengths & limitations? How a researcher generates a research question?
- ×1a) Classify various research study design. [3] b) Describe the terms “exposure” and “outcome variable” in a study. [3] c) What is a cross sectional study and how it is different from case control study?
- ×1a) Study design in biomedical research. b) Describe the methods of types of study and calculating sample size prior to a clinical study.
- ×1Cohort study - Definition, advantages and disadvantages.
- ×1Compare and contrast between Case control and Cohort study.
- ×1Describe in detail alongwith one example each the following research studies: a) Cross sectional study. b) Randomized control trial. c) Cohort studies.
- ×1Describe the levels of evidences in research methodology.
- ×1Discuss various types of study designs for research.
- ×1PICO criteria in research.
- ×1What are the essential considerations while framing a research question?
- ×1What are the various components of a thesis protocol? Describe the Phase 1 & Phase 2 of a clinical trial.
- ×1What are the various types of Research studies? Explain each with example.
- ×1What is the type of study design you would need to use if it has to be completed within a year of your posting and mention reasons?
- ×1Cohort studies and their importance.
- ×1Compare case-control and cohort studies.
- ×1What is a Cohort study?
- ×1Write the steps for designing a cohort study to assess effect of air pollution on health. What possible biases can occur and how can they be reduced.
- ×1Classify research study designs.
- ×1Clinical research methodology: Describe design of a phase-III randomized trial to test non-inferiority of oral metronomic chemotherapy compare to conventional intravenous chemotherapy in recurrent epithelial ovarian cancer.
- ×1Clinical research methodology: What are various Phases of clinical trials?
- ×1Describe briefly various study designs used for clinical studies.
- ×1Describe various levels of evidences based on types of studies in research methodology.
- ×1Describe various study designs and its limitations.
- ×1Discuss the study designs to identify a causative factor for cancer.
- ×1Enumerate various types of epidemiological studies. There are cases of rare disease with manifestation of neurological symptoms in children in a district of 10 lakh population. Describe the study which you will plan to find out the cause of disease.
- ×1Explain Propensity Score Matching in research methodology.
- ×1Hierarchical study design in clinical trials.
- ×1There has been a cholera outbreak in the locality where you practice. You have been asked by the local administration to investigate this. How will you proceed to ascertain the existing situation of outbreak? Briefly describe the study design, objective, methodology and associated factors.
- ×1Variuos study designs with special emphasis on their strengths and weaknesses.
- ×1What are various types of research studies? Compare RCT with Case-control study.
- ×1Difference between case control and cohort study.
- ×1Explain the following in context of research study: a) Nested cohort study. [5] b) Methods to counteract the multiple comparisons problem.
- ×1Types of cohort studies.
- ×1Explain cross sectional study with an example.
- ×1A slum population under an Urban Health Center reports cases of diarrhoea in children. As a Medical Officer you are to find out the incidence of diarrhea in this population. Which is the most appropriate study design? Describe the steps to conduct such a study.
- ×1Case-control Study design and its utility
- ×1Discuss the benefits of Research methodology.
- ×1Discuss various study designs.
- ×1There are increased cases of pancreatic cancer reported from a district A. What will be the most appropriate study design? Describe the different measures of association obtained from this design to assess the risk factors?
- ×1What is Research Methodology? Enumerate its types.
- ×1You decide to study the effectiveness of a vaccine against COVID-19 infection in the adult population covered by your community health centre. Discuss the study design you would use to investigate this.
- ×1Case control versus Cohort study.
- ×1Compare case control study and cohort study.
- ×1Enumerate differences between case control and cohort studies.
- ×1A study compared post-operative infection rates in a standard surgical procedure with those for a new procedure. The study protocol claimed that roughly equal numbers of patients from 10 preoperative assessment clinics were to be randomly allocated to undergo either the new treatment or the standard procedure. Make a flow diagram of the type of study described here.
- ×1About research methodology: b) Levels of evidence.
- ×1Discuss the different types of study designs used in medical research with their advantages and limitations.
- ×1How do you frame a research question?
- ×1a) Write the difference between correlation and regression analysis. b) List the types of observational study design. c) How is sample size calculated in case-control study?
- ×1i. Case-control study. ii. Cohort study. iii. Interventional study. b) List the advantages and disadvantages of each of these study designs
- ×1procedure with those for a new procedure. The study protocol claimed that roughly equal numbers of patients from 10 preoperative assessment clinics were to be randomly allocated to undergo either the new treatment or the standard procedure. Make a flow diagram of the type of study described here? b) In each clinic, the first 20 patients received the new treatment, while the
- ×1procedure with those for a new procedure. The study protocol claimed that roughly equal numbers of patients from 10 preoperative assessment clinics were to be randomly allocated to undergo either the new treatment or the standard procedure. Make a flow diagram of the type of study described here? next 20 patients were allocated the standard procedure. Critically review on this allocation procedure. c) The results of the study showed that 24 out of 100 patients who underwent
- ×1Case control and Cohort studies.
- ×1Differences between case control studies and cohort studies using examples.
- ×1examples. b) Retrospective cohort studies.
- ×1Case Control study design.
- ×1Define population-attributable risk. How is it different from relative risk? What type of study design is required to measure it?
- ×1Enumerate various research methodologies relevant to medical research. Prepare a research protocol for any research on Forensic.
- ×1What are study designs and discuss about meta-analysis?
- ×1What are the common epidemiological study designs?
- ×1Cohort Study.
- ×1Describe benefits and disadvantages of cohort studies and how to handle the challenges in conduct of cohort study.
- ×1a) Meta-analysis in medical research. b) Cross sectional study. c) Controlled trials- discuss its types and merits.
- ×1Enumerate the types of research studies.
- ×1Study designs.
- ×1What do you mean by research methodology?
- ×1Clinical utilities of Cross sectional studies.
- ×1Relationship between incidence and prevalence
- ×1Sample size calculation in a cross sectional study.
- ×1Enumerate the types of clinical studies
- ×1Cross sectional study
- ×1A team of health care planers wishes to estimate the prevalence of AIDS in the state of Bihar. What is the most appropriate study design? Give reasons behind choosing this design?
- ×1Define sample size and its importance in research methodology.
- ×1Different types of epidemiological studies in Psychiatry.
- ×1Enumerate two broad headings for study designs and give one example under each category.
- ×1Types of study designs.
- ×1a) Common clinical research study designs. b) Phases in clinical trials.
- ×1Differentiate between incidence and prevalence with illustrative examples of each.
- ×1Explain the difference between a longitudinal and cross sectional study using suitable examples.
- ×1In a cross sectional study of the relationship between smoking and anxiety, 1000 people were simultaneously classified according to smoking status (500 smokers and 500 non-smokers) and current level of anxiety (high or low). 200 smokers had high anxiety level and 400 non smokers had low anxiety levels. a) Calculate appropriate rates and test of significance. b) Explain whether such association can be considered causal or not.
- ×1Incidence and prevalence.
- ×1Meta analysis in Research Methodology.
- ×1Randomized Phase –III studies with examples as applied to surgical oncology in Research Methodology.
- ×1Statistical analysis in research methodology
- ×1Differences between a longitudinal and cross sectional study, giving examples.
- ×1Explain the terms case-control and cohort studies. Indicate the advantages of each of these study designs.
- ×1Sampling techniques in Research Methodology.
- ×1Write in brief about the various types of studies in Research Methodology? What is sample size and its importance?
- ×1Describe challenges in conduct of cohort studies.
- ×1Define incidence and prevalence. What are different types of prevalence? Discuss briefly their significance.
- ×1What is incidence and prevalence of a disease?
- ×1Describe a cohort study. What are its advantages and disadvantages?
Read next