Module One It Case Study Review and Selection
Indian J Dermatol. 2016 Mar-Apr; 61(ii): 146–151.
Methodology Series Module two: Example-control Studies
Maninder Singh Setia
Epidemiologist, MGM Institute of Health Sciences, Navi Mumbai, Maharashtra, India
Received 2016 Jan; Accustomed 2016 Jan.
Abstract
Case-Control report design is a type of observational study. In this pattern, participants are selected for the study based on their consequence status. Thus, some participants have the outcome of involvement (referred to as cases), whereas others practise not have the event of involvement (referred to equally controls). The investigator so assesses the exposure in both these groups. The investigator should define the cases as specifically every bit possible. Sometimes, definition of a disease may be based on multiple criteria; thus, all these points should be explicitly stated in case definition. An important aspect of selecting a control is that they should be from the aforementioned 'report base' as that of the cases. We tin can select controls from a variety of groups. Some of them are: Full general population; relatives or friends; and hospital patients. Matching is often used in case-control control studies to ensure that the cases and controls are similar in sure characteristics, and it is a useful technique to increase the efficiency of the written report. Example-Control studies can usually be conducted relatively faster and are inexpensive – particularly when compared with cohort studies (prospective). Information technology is useful to study rare outcomes and outcomes with long latent periods. This design is not very useful to study rare exposures. Furthermore, they may too exist decumbent to sure biases – selection bias and call up bias.
Keywords: Instance-command studies, blueprint, limitations, strengths
Introduction
Case-Command study design is a type of observational study design. In an observational study, the investigator does not alter the exposure status. The investigator measures the exposure and upshot in report participants, and studies their association.
Blueprint
In a case-control study, participants are selected for the study based on their outcome status. Thus, some participants have the event of interest (referred to as cases), whereas others do not take the outcome of involvement (referred to as controls). The investigator then assesses the exposure in both these groups. Thus, by pattern, in a case-control study the outcome has to occur in some of the participants that accept been included in the report.
As seen in Effigy 1, at the fourth dimension of entry into the study (sampling of participants), some of the written report participants have the outcome (cases) and others do non have the outcome (controls). During the study procedures, we will examine the exposure of interest in cases also as controls. We will then study the association between the exposure and event in these study participants.
Example of a case-control study
Examples of Instance-Command Studies
Smoking and lung cancer report
In their landmark study, Doll and Hill (1950) evaluated the association betwixt smoking and lung cancer. They included 709 patients of lung carcinoma (divers as cases). They also included 709 controls from general medical and surgical patients. The selected controls were similar to the cases with respect to age and sexual practice. Thus, they included 649 males and 60 females in cases as well as controls.
They institute that only 0.3% of males were non-smokers among cases. Even so, the proportion of not-smokers among controls was 4.2%; the different was statistically pregnant (P = 0.00000064). Similarly they plant that about 31.vii% of the female were not-smokers in cases compared with 53.3% in controls; this deviation was as well statistically pregnant (0.01< p <0.02).
Melanoma and tanning (Lazovic et al., 2010)
The authors conducted a case-control study to study the association betwixt melanoma and tanning. The 1167 cases - individuals with invasive cutaneous melanoma – were selected from Minnesota Cancer Surveillance System. The 1101 controls were selected randomly from Minnesota State Driver's License list; they were matched for age (+/- 5 years) and sex activity.
The data were collected by self administered questionnaires and telephone interviews. The investigators assessed the use of tanning devices (using photographs), number of years, and frequency of use of these devices. They also collected information on other variables (such as dominicus exposure; presence of freckles and moles; and color of pare, hair, amongst other exposures.
They institute that melanoma was college in individuals who used UVB enhances and primarily UVA-emitting devices. The risk of melanoma likewise increased with increment in years of use, hours of use, and sessions.
Risk factors for erysipelas (Pitché et al, 2015)
Pitché et al (2015) conducted a case-control written report to assess the factors associated with leg erysipelas in sub-Saharan Africa. This was a multi-centre report; the cases and controls were recruited from viii countries in sub-Saharan Africa.
They recruited cases of astute leg cellulitis in these eight countries. They recruited two controls for each case; these were matched for age (+/- 5 years) and sexual activity. Thus, the terminal report has 364 cases and 728 controls. They institute that leg erysipelas was associated with obesity, lympoedema, neglected traumatic wound, toe-web intertrigo, and voluntary cosmetic depigmentation.
We take provided details of all the 3 studies in the bibliography. Nosotros strongly encourage the readers to read the papers to understand some practical aspects of example-command studies.
Selection of Cases and Controls
Pick of cases and controls is an important part of this design. Wacholder and colleagues (1992 a, b, and c) accept published wonderful manuscripts on design and conduct of instance-control of studies in the American Journal of Epidemiology. The discussion in the side by side few sections is based on these manuscripts.
Selection of case
The investigator should define the cases equally specifically as possible. Sometimes, definition of a disease may be based on multiple criteria; thus, all these points should be explicitly stated in case definition.
For case, in the above mentioned Melanoma and Tanning report, the researchers defined their population as any histologic variety of invasive cutaneous melanoma. However, they added another important criterion – these individuals should have a driver's license or Land identity carte du jour. This probably is not directly related to the clinic status, and then why did they add this criterion? We volition talk over this in detail in the next few paragraphs.
Selection of a command
The adjacent important point in designing a instance-control report is the selection of control patients.
In fact, Wacholder and colleagues accept extensively discussed aspects of design of case control studies and selection of controls in their article.
According to them, an important attribute of selecting a control is that they should be from the same 'study base' every bit that of the cases. Thus, the pool of population from which the cases and controls will exist enrolled should be same. For instance, in the Tanning and Melanoma study, the researchers recruited cases from Minnesota Cancer Surveillance System; yet, it was as well required that these cases should either have a State identity card or Commuter's license. This was important since controls were randomly selected from Minnesota State Driver's license listing (this as well included the list of individuals who accept the State identity carte).
Another important aspect of a instance-control study is that we should measure the exposure similarly in cases and controls. For instance, if nosotros pattern a enquiry protocol to report the association betwixt metabolic syndrome (exposure) and psoriasis (upshot), nosotros should ensure that we use the same criteria (clinically and biochemically) for evaluating metabolic syndrome in cases and controls. If we use unlike criteria to measure the metabolic syndrome, then it may cause data bias.
Types of Controls
We can select controls from a variety of groups. Some of them are: General population; relatives or friends; or hospital patients.
Hospital controls
An important source of controls is patients attention the hospital for diseases other than the outcome of involvement. These controls are easy to recruit and are more than probable to have similar quality of medical records.
Nevertheless, we have to be careful while recruiting these controls. In the above example of metabolic syndrome and psoriasis, we recruit psoriasis patients from the Dermatology department of the hospital equally controls. Nosotros recruit patients who do not have psoriasis and present to the Dermatology as controls. Some of these individuals have presented to the Dermatology department with tinea pedis. Do we recruit these individuals as controls for the study? What is the trouble if we recruit these patients? Some studies accept suggested that diabetes mellitus and obesity are predisposing factors for tinea pedis. Every bit we know, fasting plasma glucose of >100 mg/dl and raised trigylcerides (>=150 mg/dl) are criteria for diagnosis of metabolic syndrome. Thus, it is quite likely that if we recruit many of these tinea pedis patients, the exposure of involvement may turn out to be like in cases and controls; this exposure may non reflect the truth in the population.
Relative and friend controls
Relative controls are relatively easy to recruit. They tin exist particularly useful when we are interested in trying to ensure that some of the measurable and non-measurable confounders are relatively every bit distributed in cases and controls (such every bit domicile environment, socio-economic status, or genetic factors).
Another source of controls is a list of friends referred by the cases. These controls are easy to recruit and they are also more likely to exist like to the cases in socio-economical condition and other demographic factors. Nonetheless, they are besides more than likely to have similar behaviours (booze use, smoking etc.); thus, it may not exist prudent to use these as controls if we want to study the outcome of these exposures on the effect.
Population controls
These controls can be easily conducted the list of all individuals is available. For example, listing from state identity cards, voter'southward registration list, etc., In the Tanning and melanoma study, the researchers used population controls. They were identified from Minnesota state driver's list.
We may take to utilize sampling methods (such every bit random digit dialing or multistage sampling methods) to recruit controls from the population. A main advantage is that these controls are likely to satisfy the 'study-base' principle (described higher up) as suggested by Wacholder and colleagues. Nonetheless, they can be expensive and time consuming. Furthermore, many of these controls will not be inclined to participate in the study; thus, the response rate may be very depression.
Matching in a Case-Control Study
Matching is often used in example-control control studies to ensure that the cases and controls are similar in certain characteristics. For example, in the smoking and lung cancer study, the authors selected controls that were similar in historic period and sexual activity to carcinoma cases. Matching is a useful technique to increase the efficiency of study.
'Individual matching' is one common technique used in case-control study. For example, in the in a higher place mentioned metabolic syndrome and psoriasis, nosotros can decide that for each example enrolled in the study, nosotros volition enroll a control that is matched for sex and age (+/- 2 years). Thus, if 40 year male patient with psoriasis is enrolled for the study as a example, we will enroll a 38-42 yr male patient without psoriasis (and who will non be excluded for other reason) as controls.
If the report has used 'individual matching' procedures, then the data should also reflect the same. For instance, if you accept 45 males amongst cases, you should besides have 45 males among controls. If you bear witness 60 males among controls, you should explicate the discrepancy.
Even though matching is used to increment the efficiency in example-control studies, it may have its own problems. Information technology may be difficult to fine the exact matching control for the written report; nosotros may accept to screen many potential enrollees before we are able to recruit one control for each case recruited. Thus, it may increase the time and cost of the report.
Nonetheless, matching may be useful to control for certain types of confounders. For instance, surroundings variables may be accounted for by matching controls for neighbourhood or area of residence. Household environment and genetic factors may be accounted for by enrolling siblings as controls.
If we use controls from the by (fourth dimension menstruum when cases did not occur), then the controls are sometimes referred to historic controls. Such controls may be recruited from past infirmary records.
Strengths of a Case-Control Study
-
Case-Control studies can usually be conducted relatively faster and are inexpensive – particularly when compared with cohort studies (prospective)
-
Information technology is useful to study rare outcomes and outcomes with long latent periods. For instance, if we wish to report the factors associated with melanoma in India, it will be useful to conduct a case-control study. We will recruit cases of melanoma as cases in ane study site or multiple study sites. If we were to comport a accomplice report for this research question, we may to have follow individuals (with the exposure under report) for many years before the occurrence of the upshot
-
Information technology is also useful to report multiple exposures in the aforementioned outcome. For example, in the metabolic syndrome and psoriasis study, we tin can study other factors such as Vitamin D levels or genetic markers
-
Case-control studies are useful to report the association of risk factors and outcomes in outbreak investigations. For case, Freeman and colleagues (2015) in a study published in 2015 conducted a case-control written report to evaluate the function of proton pump inhibitors in an outbreak of non-typhoidal salmonellosis.
Limitations of a Case-control Report
-
The pattern, in general, is not useful to study rare exposures. It may be prudent to conduct a cohort study for rare exposures
-
We are non able to estimate the incidence or prevalence in a case-control report
-
Why can't we comment on the incidence or prevalence of the affliction?
Since the investigator chooses the number of cases and controls, the proportion of cases may non be representative of the proportion in the population. For case if we cull 50 cases of psoriasis and fifty controls, the prevalence of proportion of psoriasis cases in our study volition be 50%. This is not true prevalence. If nosotros had called 50 cases of psoriasis and 100 controls, so the proportion of the cases will be 33%.
-
-
The pattern is not useful to study multiple outcomes. Since the cases are selected based on the upshot, we tin can only report the association betwixt exposures and that particular effect
-
Sometimes the temporality of the exposure and outcome may not be clearly established in case-command studies
-
The case-control studies are also prone to sure biases
-
In general, individuals may not be able to call up all exposures accurately. Furthermore, cases are more than likely to call back detailed exposure history (particularly behaviours such as dietary habits) compared with controls – especially population based controls. Thus, this may lead to recall bias
If the cases and controls are not selected similarly from the study base, then information technology volition lead to selection bias.
Analysis
-
Odds Ratio: Nosotros are able to calculate the odds ratios (OR) from a instance-control written report. Since we are not able to measure incidence data in case-command study, an odds ratio is a reasonable mensurate of the relative risk (nether some assumptions). Additional details about OR volition be discussed in the biostatistics section.
The OR in the higher up report is 3.v. Since the OR is greater than i, the event is more likely in those exposed (those who are diagnosed with metabolic syndrome) compared with those who are not exposed (those who practise are not diagnosed with metabolic syndrome). Still, nosotros volition require confidence intervals to comment on further interpretation of the OR (This volition be discussed in particular in the biostatistics section).
-
Other analysis: We tin use logistic regression models for multivariate assay in case-control studies. It is important to note that conditional logistic regressions may be useful for matched case-control studies.
Table
Calculating an Odds Ratio (OR)
Tabular array
Hypothetical study of metabolic syndrome and psoriasis
Additional Points in A Case-Control Report
How many controls can I accept for each example?
The nearly optimum case-to-command ratio is 1:one. Jewell (2004) has suggested that for a fixed sample size, the chi square test for independence is most powerful if the number of cases is same as the number of controls. However, in many situations nosotros may non be able recruit a large number of cases and it may exist easier to recruit more controls for the study. It has been suggested that we tin increase the number of controls to increment statistical power (if we take express number of cases) of the study. If data are available at no actress cost, then nosotros may recruit multiple controls for each instance. However, if it is expensive to collect exposure and consequence information from cases and controls, then the optimal ratio is 4 controls: 1 case. Information technology has been argued that the increment in statistical power may exist limited with additional controls (greater than iv) compared with the cost involved in recruiting them beyond this ratio.
I take conducted a randomised controlled trial. I have included a group which received the intervention and another group which did not receive the intervention. Tin can I phone call this a case-control study?
A randomised controlled trial is an experimental study. In contrast, instance-control studies are observational studies. These are two different groups of studies. One should not apply the give-and-take case-control report for a randomised controlled trial (even though you have a control group in the study). Every written report with a control group is not a case-control report. For a study to exist classified as a case-control study, the study should be an observational study and the participants should exist recruited based on their outcome status (some have the affliction and some practise non).
Should I call example-control studies prospective or retrospective studies?
In 'The Dictionary of Epidemiology' by Porta (2014), the authors accept suggested that even though the term 'retrospective' was used for example-control studies, the study participants are often recruited prospectively. In fact, the study on chance factors for erysipelas (Pitché et al., 2015) was a prospective case case-control written report. Thus, it is of import to call up that the nature of the study (case-control or cohort) depends on the sampling method. If nosotros sample the study participants based on exposure and move towards the outcome, information technology is a cohort report. Withal, if we sample the participants based on the outcome (some with upshot and some do not) and study the exposures in both these groups, it is a case-control written report.
Summary
In case-control studies, participants are recruited on the ground of disease status. Thus, some of participants accept the outcome of interest (referred to as cases), whereas others practice not have the outcome of interest (referred to as controls). The investigator and then assesses the exposure in both these groups. Case-control studies are less expensive and quicker to conduct (compared with prospective cohort studies at least). The measure of association in this blazon of study is an odds ratio. This type of design is useful for rare outcomes and those with long latent periods. However, they may also be prone to sure biases – selection bias and think bias.
Fiscal support and sponsorship
Nil.
Conflicts of involvement
In that location are no conflicts of interest.
Bibliography
one. Charles H. Hennekens, Julie E. Buring. Showtime ed. Philadelphia, USA: Lippincott Williams & Wilkins; 1987. Epidemiology in Medicine. [Google Scholar]
two. Cheng South, Chong L. A prospective epidemiological study on tinea pedis and onychomycosis in Hong Kong. Chin Med J (Engl) 2002;115(6):860–865. [PubMed] [Google Scholar]
3. Doll R, Colina A. B. Smoking and carcinoma of the lung; preliminary study. Br Med J. 1950;ii(4682):739–748. [PMC free article] [PubMed] [Google Scholar]
4. Freeman R, Dabrera Thou, Lane C, Adams N, Browning L, Fowler T, et al. Association between utilize of proton pump inhibitors and not-typhoidal salmonellosis identified following investigation into an outbreak of Salmonella Mikawasima in the Great britain, 2013. Epidemiol Infect. 2015:i–8. [PubMed] [Google Scholar]
v. Gail Thousand, Williams R, Byar D. P, Brownish C. How many controls? J Chronic Dis. 1976;29(11):723–731. [PubMed] [Google Scholar]
vii. Jewell N. Boca Raton, US: Chapman and Hall/CRC; 2004. Statistics for Epidemiology. [Google Scholar]
8. Jos Due west. R, Twisk . 2nd ed. Cambridge, Britain: Cambridge University Press; 2013. Applied Longitudinal Information Assay for Epidemiology. [Google Scholar]
nine. Kenneth J. Rothman, Sander Greenland, Timothy L. Lash. Third ed. Philadelphia, Us: Lippincott Williams & Wilkins; 2008. Mod Epidemiology. [Google Scholar]
x. Kleinbaum D, Kupper L, Morgenstern H. New York, US: John Wiley and Sons, Inc; 1982. Epidemiologic inquiry. [Google Scholar]
11. Lazovich D, Vogel R. I, Berwick One thousand, Weinstock M. A, Anderson K. Eastward, Warshaw E. M. Indoor tanning and risk of melanoma: A case-control study in a highly exposed population. Cancer Epidemiol Biomarkers Prev. 2010;xix(vi):1557–1568. [PMC free article] [PubMed] [Google Scholar]
12. Pitché P, Diatta B, Faye O, Diane B. F, Sangare A, Niamba P, et al. Take a chance factors associated with leg erysipelas (cellulitis) in sub-Saharan Africa: A multicentre example-control study. Ann Dermatol Venereol. 2015;142(11):633–638. [PubMed] [Google Scholar]
13. Porto Miquel Assoc, Sander Greenland, Miguel Hernán, Isabel dos Santos Silva, John M. Last; Asst, Andrea Burón, editors. Sixth ed. New York, U.s.a.: International Epidemiological Association, Oxford University Press; 2014. A Dictionary of Epidemiology. [Google Scholar]
14. Song J. W, Chung Chiliad. C. Observational studies: Accomplice and case-control studies. Plast Reconstr Surg. 2010;126(six):2234–2242. [PMC free commodity] [PubMed] [Google Scholar]
15. Stephen B. Hulley, Steven R. Cummings, Warren S. Browner, Deborah Grady, Norman Hearst, Thomas B. Newman. 2nd ed. Philadelphia, The states: Lippincot Williams and Wilkins; 2001. Designing Clinical Inquiry. [Google Scholar]
16. Szklo M, Javier Nieto F. Sudbury, MA: Jones and Bartlett Publishers, Inc; 2004. Epidemiology: Across the basics. [Google Scholar]
17. Wacholder S, McLaughlin J. K, Silverman D. T, Mandel J. S. Selection of controls in case-control studies. I. Principles. Am J Epidemiol. 1992a;135(9):1019–1028. [PubMed] [Google Scholar]
18. Wacholder Due south, Silverman D. T, McLaughlin J. 1000, Mandel J. Due south. Selection of controls in instance-control studies. III. Design options. Am J Epidemiol. 1992b;135(ix):1042–1050. [PubMed] [Google Scholar]
19. Wacholder South, McLaughlin J. Thou, Silverman D. T, Mandel J. Due south. Selection of controls in case-control studies. I. Principles. Am J Epidemiol. 1992c;135(nine):1019–1028. [PubMed] [Google Scholar]
20. Ye D, Shan J, Huang Y, Li J, Li C, Liu X, et al. A gloves-associated outbreak of imipenem-resistant Acinetobacter baumannii in an intensive intendance unit in Guangdong, Communist china. BMC Infect Dis. 2015;fifteen [PMC free article] [PubMed] [Google Scholar]
Articles from Indian Journal of Dermatology are provided here courtesy of Wolters Kluwer -- Medknow Publications
Source: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4817437/
0 Response to "Module One It Case Study Review and Selection"
Publicar un comentario