China
Africa
Explore chapters and articles related to this topic
Epidemiological Methods for Studying the Role of Beta Receptor Agonist Therapy in Asthma Mortality
Published in Richard Beasley, Neil E. Pearce, The Role of Beta Receptor Agonist Therapy in Asthma Mortality, 2020
This approach revolutionized the understanding of case-control studies because it showed that they did not involve an inherently different approach, but could actually be incorporated within cohort studies as a more efficient manner of achieving the same findings. This nested case-control approach only differed from the full cohort approach in one respect: that cases were compared with a sample of the cohort rather than the complete cohort. All of the other supposed shortcomings of case-control studies did not apply: there was no need for a “rare-disease” assumption; there was no greater tendency to bias (providing the control sample was genuinely random); and causal inference proceeded from cause to effect, just as in a full cohort study.22 Furthermore, the case-control approach had several important advantages; in particular, when the outcome under study was rare, it was considerably more efficient. This increase in efficiency usually meant that a much larger study (in terms of the number of cases) could be conducted.
Design Issues in Case-Control Studies
Published in Ørnulf Borgan, Norman E. Breslow, Nilanjan Chatterjee, Mitchell H. Gail, Alastair Scott, Christopher J. Wild, Handbook of Statistical Methods for Case-Control Studies, 2018
More than 60 years ago, Cornfield (1951) showed that case-control data could be used to approximate the cohort relative risk by using instead the odds ratio, under the assumption that the disease was rare and that cases and controls were sampled without reference to their exposure status. This happens because the ratio of case and control sampling fractions cancels out in the calculation of the population odds ratio, which in turn approximates the population relative risk. This so-called “rare disease assumption” has been repeated in most of the classic epidemiologic textbooks, although there are circumstances where it is not really needed to estimate parameters of real interest. For example, in a matched case-control study where controls are sampled from the population at risk at the age at which each case occurs, the odds ratio is an exact estimator of the hazard ratio (Miettinen, 1976); Greenland.Thomas.1982; Sheehe.1962; (Prentice and Breslow, 1978). Although matched case-control studies do not allow the main effects of the matching factors to be estimated, one can still study variation in exposure-disease odds ratio across levels of the matching variables (Section 2.3.3).
Epidemiology *
Published in Jamie Bartram, Rachel Baum, Peter A. Coclanis, David M. Gute, David Kay, Stéphanie McFadyen, Katherine Pond, William Robertson, Michael J. Rouse, Routledge Handbook of Water and Health, 2015
Measures of association such as “risk ratios,” “rate differences,” or “odds ratios” are used to compare disease occurrence in exposed and unexposed groups. These comparisons can be made by division (ratio effect measures) or subtraction (difference effect measures). In cohort studies, the risk or rate in the exposed group is compared with the risk or rate in the unexposed group. Risk ratios are interpreted as follows: Those who were exposed were [risk ratio] times as likely to develop the outcome compared with those who were unexposed over the follow-up timeframe of the study. A rate difference would be interpreted as: Among those who were exposed, the rate of the disease was [rate difference] higher/lower than among those who were unexposed. In a case-control study, we calculate the exposure odds ratio (OR). The OR approximates the rate ratio or risk ratio under the rare disease assumption, in which the prevalence is less than 10 percent. ORs are interpreted as: Those who were exposed had [OR times] the odds of the disease compared with those who were unexposed. For example, pregnant women of young maternal age (20 years of age or younger) were 2.61 times as likely to be develop a malaria infection compared with pregnant women of old ages (21 years of age or older) (Agomo and Oyibo 2013).
Quantification of the relationship between pyoderma gangrenosum and Crohn’s disease: a population-based case-control study
Published in Scandinavian Journal of Gastroenterology, 2020
Khalaf Kridin, Giovanni Damiani, Ralf J. Ludwig, Dana Tzur-Bitan, Arnon D. Cohen
Despite the aforementioned accumulated data, quantification of the association between CD and the development of subsequent PG is yet to be outlined. This stems from the fact that controlled observational studies comparing patients with PG and control individuals with regard to the presence of CD are yet to be carried out. Our case-control study, therefore, provides a novel epidemiological feature and shows that a preceding diagnosis of CD is associated with an increase of 22- and 28-folds in the multivariate and crude odds of having PG, respectively. To simplify this epidemiological finding, individuals with CD have 22- to 28-fold higher odds to present with PG as compared to individuals without a diagnosis of CD. This conclusion is grounded upon the ‘rare disease assumption’ in case-control studies, hypothesizing that the OR approximates the RR in rare diseases (with a prevalence rate of less than 10%) [11].
There is no single gold standard study design (RCTs are not the gold standard)
Published in Expert Opinion on Drug Safety, 2023
The ‘trohoc fallacy’ assumes that case-control studies are inherently ‘backward looking’ by comparing prior exposures in cases and controls [18]. This is false. A more meaningful conceptualization of the function of the control series in case-control studies is as a stochastic estimate of exposed-to-nonexposed person-time in the underlying study population (incidence density sampling). This permits a meaningful statistical estimate of the rate ratio in the source population – no rare disease assumption required [20]. It also provides a scientific basis for selecting controls in case-control studies. In effect, properly conducted case-control studies provide the same estimates of risk as properly conducted cohort studies.
Vitiligo and Crohn′s disease form an autoimmune cluster: insights from a population-based study
Published in Scandinavian Journal of Gastroenterology, 2023
Khalaf Kridin, Daniel Goral, Wesal Shihade, Dana Tzur-Bitan, Erez Onn, Lilach Zoller, Arnon D. Cohen
The current study aimed to investigate the bidirectional epidemiological relationship between vitiligo and CD. Since the study population consisted of patients with vitiligo and their controls, two study designs were implemented in order to answer the question of interest. First, a retrospective cohort study design enabling to longitudinally follow patients with vitiligo and estimate the incidence of new-onset CD. Second, a case-control study design that allows evaluating the prevalence of preexisting CD (exposure) in patients with subsequent vitiligo (outcome). In accordance with the rare disease assumption, the second study design ought to reflect the odds of vitiligo after CD [24].