Study designs may be observational or interventional/experimental. Let’s dig deeper in this video overview and the chapter below:
Meta-analysis is also a type of study design.
Case series: It describes interesting characteristics observed in a group of patients. It may be used to report a cluster of rare cases or cases with unique presentations. For example, a hospital may report a case series of Coronavirus infections in 12 pediatric patients presenting with Kawasaki syndrome. Typically, case series do not have a control group. It may also be used to compare modalities of treatment used in different groups of patients and compare the outcomes. Case series are a precursor to further more detailed studies.
Case-control study: It compares two groups - “cases” which are individuals who have a particular disease or outcome of interest; and “controls” which consists of individuals without the disease or outcome of interest. The two groups are compared for the presence or absence of particular risk factors. It is retrospective in nature, as the selection is based on the presence or absence of disease and you go back in time to identify the risk factors.
For example, if I want to study if cigarette smoking causes heart disease, then two groups are selected - one with heart disease and another group without heart disease. Then I go back and get a history of cigarette smoking in the two groups and compare the data. Similarly, when you compare both groups , you may find more risk factors associated with heart disease.
The two groups should be comparable, e.g. you cannot compare risk factors for Ischemic heart disease between adults and children. But, you can compare risk factors for IHD between two states or countries.
Case control studies are analyzed by Odds Ratio. It establishes association between risk factor and outcome/disease but does not establish causality i.e. cannot state that a particular risk factor caused the outcome. Incidence or prevalence cannot be established from a case control study. It is useful to study rare outcomes and outcomes with long latent periods. If the exposure is rare, then a case control study is not useful.
Cross sectional or prevalence studies: In this type of study, data is collected from the study group at one time , rather than over a period of time. It measures the outcome and the exposure(s) in the population, and may study their association, an example is population survey. Another example is calculating the percentage of abnormal glucose tolerance tests among adults attending a clinic on Jan 1,2020; or what is the prevalence of HIV among 300 patients that attended an STI clinic?
Prevalence of a disease and odds ratio can be calculated from cross sectional studies. Cross sectional studies are relatively faster and inexpensive to conduct. It cannot establish causal relationships.
Cohort studies: They are prospective studies where groups are selected based on the presence or absence of a risk factor or exposure, and are then followed over a period of time to observe the effect of the outcome or exposure. Cohort studies are of the following types:
i) Typical or classical or prospective cohort studies: In this type of cohort study, all the data are collected prospectively. Subjects in both groups are assessed regularly for outcomes , natural history of the disease and/or disease process. It is time consuming and costly.
ii) Historical or retrospective cohort studies: This type of study begins with the outcome/disease and then, the researchers go back in time, typically using hospital or health records to identify risk factors. You may get confused between this type of study design and case control. Always see what they are trying to find - are they looking for risk factors (cohort study) or are they looking for what disease is caused (case control study) ? Although it is less time consuming and less expensive than a classical cohort study, it is less accurate.
Cohort studies are used to establish causation as the temporality between exposure and outcome is well defined. If the exposure is rare, then a cohort design is an efficient method to study the relation between exposure and outcomes. Cohort studies are not always useful for rare outcomes. Incidence rate can be calculated from a cohort study.
Experimental studies or clinical trials: Experimental studies that involve humans are called clinical trials. Controlled trials are studies where the investigational drug or procedure is compared to a placebo, another drug/treatment or to standard therapy. In uncontrolled trials, there is no such control group.
In a double bind trial, neither the subject nor the researcher knows whether the subject is in the treatment group or control group. The treatment group receives the experimental drug or intervention, while the control group receives placebo. If only one party, either the patient or the researcher is blinded, the study is called single blind. A study with no blinding is described as open. The highest possible degree of blinding should be chosen to minimize bias.
A randomized controlled trial or RCT is a study design that randomly assigns participants into an experimental group or a control group. They are used to study the safety and efficacy of new treatments. RCT is the best study design, establishes causality with less bias.
Non-randomized trials do not use randomization and are considered weak studies which are prone to bias.
A sequential clinical trial is a trial in which the observations are assessed as they are produced and the total number of participants is not predetermined, but depends on the accumulated results. More subjects are added to the study if the statistical analysis demands so.
In a crossover trial, all patients eventually receive the experimental drug/intervention (by exchanging their groups). For example, group A gets placebo for the first three months while group B gets the drug 1. At the end of 3 months, group A gets drug 1 for another three months while group B gets the placebo.