Study Designs in Epidemiology

Study Designs in Epidemiology Epidemiologic Study Design Study design is the arrangement of conditions for the collection and analysis of data to provide the most accurate answer to a question in the most economical way. Types of Epidemiologic Study Designs I. Based on objective/focus/research question: 1. Descriptive studies Describe: what, who, when, where 2. Analytic studies Analyze: How and why Types of Epidemiological Study Designs II. Based on the role of the investigator 1. Observational studies • The investigator observes nature • No intervention 2. Intervention/Experimental studies • Investigator intervenes: changes things • He has a control over the situation Types of Epidemiological Study Designs III. Based on timing : 1. One-time (one-spot) studies •Conducted at a point in time •An individual is observed at once 2. Longitudinal (Follow-up) studies •Conducted over a period of time •Individuals are followed over a period of time Types of Epidemiological Study Designs IV. Based on direction of follow-up/data collection: 1. Prospective Conducted forward in time: into the future 2. Retrospective Conducted backward in time: past events Timeframe of Studies Prospective Study looks forward, looks to the future, examines future events, follows a condition, concern or disease into the future time Study begins here Timeframe of Studies Retrospective Study “to look back”, looks back in time to study events that have already occurred time Study begins here Types of Epidemiological Study Designs V. Based on type of data they generate: 1. Qualitative studies: • Generate textual data • Also called exploratory studies 2. Quantitative studies: • Generate numerical data • Also called explanatory studies Types of Epidemiological Study Designs The most widely used: •Descriptive studies describe occurrence of outcome •Analytic studies describe association between exposure and outcome Scientific Research Basic Research Study Designs in Epidemiology Study design is the arrangement of conditions for the collection and analysis of data to provide the most accurate answer to a question in the most economical way. (RCT) Cross-sectional Ecological Descriptive Studies •Descriptive studies are usually the first phase of an epidemiological investigation. •These studies are concerned with observing the distribution of disease or health – related characteristics in human populations. •Such studies basically ask the questions of what, who, where, and when. •Useful for generating new hypothesis (provides clues to disease etiology) Research Hypothesis A hypothesis is a supposition, arrived at from observation or reflection.  It can be accepted or rejected using the techniques of analytical epidemiology. A hypothesis should specify the following: 1. The population. 2. The specific cause being considered. 3. Expected outcome – disease. 4. Time response relationship (expectation). 5. Be understandable, measurable and testable. Descriptive studies 1. Case Reports: •presentation of a single case or handful of cases •Generally report a new or unique finding •e.g. previous undescribed disease •e.g. unexpected link between diseases •e.g. unexpected new therapeutic effect •e.g. adverse events Descriptive studies 2. Case Series Experience of a group of patients with a similar diagnosis •Cases may be identified from a single or multiple sources •Generally report on new/unique condition •May be the only realistic design for rare disorders Case Series •Advantages •Useful for hypothesis generation •Informative for very rare diseases with few established risk factors •Disadvantages •Cannot study cause and effect relationships •Cannot assess disease frequency 3. Ecological Studies (correlation study) The ecologic study is a hypothesis generating study. Usually using group-level data, it examines if two factors are correlated with each other. •It involves the collection of events over a defined population base and by the use of denominator data to determine rates. It results in Ecological Fallacy: Failure in reasoning that arises when an inference is made about an individual based on aggregate data for a group. (e.g. Higher rates of coronary heart disease in countries with higher income, Higher rates of leukemia in larger cities , higher rates of car accidents in countries or regions with higher smoking rates) Analytical Epidemiology Are exposure and disease linked? Exposure Disease Basic Questions in Analytic Epidemiology To prevent and control diseases ……… What is the exposure? Who are the exposed? What are the potential health effects?  Generate a hypothesis about the relationship between exposure and effect, and then test this hypothesis.  Study designs….. direct how this whole investigation is conducted. Analytical Studies (testing hypothesis) Observational Studies •Cross-sectional •Case-control •Cohort Experimental Studies •Randomized controlled clinical trials •Community trials Observational Studies non-experimental study designs •Observational because there is no individual intervention •Treatment and exposures occur in a “non-controlled” environment •Individuals can be observed prospectively, retrospectively, or currently Cross-sectional studies An “observational” design that surveys exposures and disease status at a single point in time (a cross-section of the population) time Study only exists at this point in time Cross-sectional studies Based on a single examination of a cross section of population at one point in time, by studying a sample that represents the population. Results of which can be generalized to the whole population (provided the sampling has been done correctly). Longitudinal studies are Based on multiple observations in the same population over a multiple points of time. e.g. What is the prevalence of diabetes in Jordan? A survey of asthma among animal handlers A survey of dietary habits among university students. Cross-sectional studies Used to learn more about the disease to explore factors that have role in the etiology of the disease: •Physical characteristics of people, material and environment •Socio-economic characteristics e.g., age, education , marital status, number of children and income •Behavior of people like knowledge, attitude and beliefs (KAP) •Events that occur in population Cross-sectional Design factor present No Disease factor absent Study population factor present Disease factor absent time Study only exists at this point in time Cross-sectional Studies •Are the simplest form of observational studies. •Often used to study conditions that are relatively frequent with long duration of expression (nonfatal, chronic conditions) •It measures prevalence, not incidence of disease •Example: community surveys •Not suitable for studying rare or highly fatal diseases or a disease with short duration of expression. Cross-sectional… Advantages of cross-sectional studies •Less time consuming •Less expensive •Provides more information •Describes the population well •Generates hypothesis Cross-sectional study provides a snap-shot or a photograph of a population at a certain point in time. 33 Cross-sectional studies Disadvantages •Weakest observational design, (it measures prevalence, not incidence of disease). Prevalent cases are survivors •The temporal sequence of exposure and effect may be difficult or impossible to determine. •Usually don’t know when disease occurred •Rare events a problem. Quickly emerging diseases a problem. •Least useful in establishing causation. Is Cross-sectional design Descriptive or Analytical? •It may be difficult to decide whether the disease or the exposure came first, so causation should always be confirmed by stronger studies. •The collection of information about risk factors is retrospective, running the risk of recall bias. •In practice cross-sectional studies include elements of both types of design. Case-Control Study Design The investigator compares one group among whom a health problem is present with another group, called a control or comparison group, where the health problem is absent to find out what factors have contributed to the problem. e.g. A study to explore the relationship between obesity and breast cancer. e.g. A study fo assess the effect of mothers’ educational level on malnutrition among children Case-Control Design factor present factor absent Cases (disease) factor present Controls (no disease) Study population factor absent present past time Study begins here Case-Control Studies An “observational” design comparing exposures in disease cases vs. healthy controls from the same population. •exposure data collected retrospectively. •most feasible design where disease outcomes are rare. •This is the first approach to test causal hypothesis. •Definition of a case is crucial to a case control study. SELECTION OF CONTROLS •The controls must be free from the disease under study. •They must be similar to the cases as possible, except for the absence of the disease under study (matching). •Each case needs one control or more. Selection of an appropriate control group is an important pre requisite, because we will be making comparison with these controls.. Case-Control Study Strengths: 1) Less expensive and less time consuming 2) Efficient for studying rare diseases 3) Allows the study of several different aetiological factors for one disease. 4) No attrition problems (no follow-up). 5) Ethical problems are minimal (no risk to participants) Case-Control Study Limitations 1. 2. 3. 4. 5. 6. Inappropriate when disease outcome for a specific exposure is not known at start of study. Selection of an appropriate control group may be difficult. Inefficient for evaluation of rare exposure Difficult to establish temporal sequence Determining exposure will often rely on memory, leading to bias (recall bias). We cannot measure incidence,& can only estimate the relative risk (RR). Cohort Study In a COHORT STUDY, a group of individuals that is exposed to a risk factor (study group) is compared with a group of individuals not exposed to the risk factor (control group). e.g. Does living in poor housing icrease the risk of developing cancer? Does following a healthy life style lower the risk of hypertension. Cohort Study Subjects are selected by exposure and followed to see development of disease Cohort study is known by a variety of names: prospective study, longitudinal study, incidence study & forward looking study. Cohort Study Is an “observational” design comparing individuals with a known risk factor or exposure with others without the risk factor or exposure. ➢ Looking for a difference in the risk (incidence) of a disease over time. ➢ Best (strongest) observational design. ➢ Data usually collected prospectively (some retrospective). Cohort Design Study population free of disease Factor present Factor absent disease no disease disease no disease present future time Study begins here Cohort Study Indications:  When there is a good evidence of an association between exposure & disease.  When exposure is rare, but incidence is high among the exposed.  When attrition of the study population can be minimized (due to long follow-up period).  When ample funds are available (it is expensive). Prospective Cohort study Exposed Outcome Non-exposed Outcome Measure exposure Baseline time Study begins here Advantages of cohort studies 1. Valuable when exposure is rare 2. Examines multiple outcomes of a single exposures 3. Temporal relationship is known 4. Allow direct measurement of risk 5. Minimize bias in ascertainment of exposure ✓ Exposure status determined before disease detection (avoid information bias). ✓ Subjects selected before disease detection (avoid selection bias). Limitations of Cohort Study 1. Expensive 2. Time-consuming 3. Inefficient for rare diseases or diseases with long latency 4. Loss to follow-up is a problem Experimental Studies (Intervention studies)  In an experiment, we are interested in the effect or consequences of a new therapeutic treatment or procedure on an outcome.  The subjects are allocated into a treatment group and a control group (old treatment or placebo). Intervention: The researcher administers the exposure (treatment) to the subjects Types of experimental studies: 1. Randomized Controlled Trial: on patients in clinical settings (e.g. RCT). 2. Quasi-experimental: Natural experiments, Field trial, Community trial, cross-over studies. outcome RANDOMIZATION Intervention no outcome Study population outcome Control no outcome baseline future time Study begins here (baseline point) Experimental Design (Intervention studies) If properly done, experimental studies can produce high quality data. Thy are the gold standard study design (strongest, most robust). The quality of “Gold standard” in experimental studies can be achieved through: Randomization, Blinding, and use of Placebo. e.g. The effectiveness of a new treatment for rheumatoid arthritis. E.g. Comparing the length of stay in hospital between laparoscopy and surgery for appendicitis. Randomization: random allocation of study subjects in to treatment & control groups. Avoids bias & confounding, and increases confidence in the results. Blinding: Denying information on treatment / control status (single, double or triple blinding). This helps to avoid observation bias. Placebo: an inert material indistinguishable from active treatment. Used to avoid Placebo effect: tendency to report favourable response regardless of physiological efficacy. (Placebo is used as blinding procedure ) RCT (Randomized Controlled Trial) Clinical trials are the most well known experimental design. RCT is a clinical trial that is well-designed (controlled and randomized). Controlled means: The researcher manipulates situations/objects. An experimental design with subjects randomly assigned by the investigator into a “treatment” group and a “comparison” group. The ultimate form of design in testing causal hypotheses (provides most convincing evidence). Randomized Controlled Trials (RCTs) Trials of hormone replacement therapy in menopausal women found no protection for heart disease, contradicting findings of prior observational studies. Randomized Controlled Trials Disadvantages of RCTs: •Very expensive •Not appropriate to answer certain types of questions: It may be unethical, for example, to assign persons to certain treatment or comparison groups if exposure has well-known benefit. Quasi-Experimental Studies The researcher does not decide or plan the intervention (e.g. changes in using health care after removing ophthalmic services from health insurance), no Randomization or no control group. Natural experiments Factor occured naturally : e.g. Increase in mental disorders following an earthquack. Crossover Studies participant work as a control for himself (e.g. New pain reliefmedication)