Case-control studies: research in reverse

doi:10.1016/S0140-6736(02)07605-5

The Lancet

Volume 359, Issue 9304, 2 February 2002, Pages 431-434

https://doi.org/10.1016/S0140-6736(02)07605-5 Get rights and content

Summary

Epidemiologists benefit greatly from having case-control study designs in their research armamentarium. Case-control studies can yield important scientific findings with relatively little time, money, and effort compared with other study designs. This seemingly quick road to research results entices many newly trained epidemiologists. Indeed, investigators implement case-control studies more frequently than any other analytical epidemiological study. Unfortunately, case-control designs also tend to be more susceptible to biases than other comparative studies. Although easier to do, they are also easier to do wrong. Five main notions guide investigators who do, or readers who assess, case-control studies. First, investigators must explicitly define the criteria for diagnosis of a case and any eligibility criteria used for selection. Second, controls should come from the same population as the cases, and their selection should be independent of the exposures of interest. Third, investigators should blind the data gatherers to the case or control status of participants or, if impossible, at least blind them to the main hypothesis of the study. Fourth, data gatherers need to be thoroughly trained to elicit exposure in a similar manner from cases and controls; they should use memory aids to facilitate and balance recall between cases and controls. Finally, investigators should address confounding in case-control studies, either in the design stage or with analytical techniques. Devotion of meticulous attention to these points enhances the validity of the results and bolsters the reader's confidence in the findings.

Section snippets

Basic case-control study design

Case-control designs might seem easy to understand, but many clinicians stumble over them. Because this type of study runs backwards by comparison with most other studies, it often confuses researchers and readers alike. In cohort studies, for example, study groups are defined by exposure. In case-control studies, however, study groups are defined by outcome (figure). To study the association between smoking and lung cancer, therefore, people with lung cancer are enrolled to form the case

Advantages and disadvantages

Epidemiologists often tout case-control studies as the most efficient design in terms of time, money, and effort. This recommendation makes sense when the incidence rate of an outcome is low, since in a cohort design the researchers would have to follow up many individuals to identify one with the outcome. Case-control studies are also efficient in the investigation of diseases that have a long latency period—eg, cancer—in which instance a cohort study would involve many years of follow-up

Case group

All the cases from a population could, theoretically, be included as participants in a case-control study. For practical reasons, however, only a sample is frequently studied.²² Investigators should, therefore, state how the sample was selected, providing a clear definition of the outcome being studied including, for example, clinical symptoms, laboratory results, and diagnostic methods used. Furthermore, researchers should detail eligibility criteria used for selection, such as age range and

Measurement of exposure information

Another difficulty in case-control studies involves the measurement of exposure information. Participants, both cases and controls, might inaccurately remember past exposures, especially those that happened a long time ago. Furthermore, cases often remember exposures to putative risk factors differently than controls. This differential recall (recall bias) causes information bias.²⁵

In the study of breast cancer and oral contraceptive use,²⁷ for example, investigators asked participants about

Control for confounding

Case-control studies need to address confounding bias.21, 22, 29 This type of bias can be dealt with in the design phase by restriction or matching, but researchers generally prefer to handle it in the analysis phase with analytical techniques such as logistic regression or stratification with Mantel-Haenszel approaches.21, 22, 25 If this second approach is used, investigators should plan carefully in advance what potentially confounding variables to obtain data for; irrespective of the

Conclusion

Case-control studies that are well designed and carefully done can provide useful and reliable results. Investigators must, however, devote meticulous attention to the selection of control groups and to measurement of exposure information. Awareness of these key elements should help readers to identify the strengths and weaknesses of a properly reported study. Accurate and thorough description of methods by investigators will result in reader confidence in their results.

References (29)

Fuller TorreyE et al.
The antecedents of psychoses: a case-control study of selected risk factors
Schizophr Res
(2000)
AvidanB et al.
Risk factors for erosive reflux esophagitis: a case-control study
Am J Gastroenterol
(2001)
TraversoHP et al.
Ghee applications to the umbilical cord: a risk factor for neonatal tetanus
Lancet
(1989)
ChengKK et al.
Pickled vegetables in the aetiology of oesophageal cancer in Hong Kong Chinese
Lancet
(1992)
FriedmanGD et al.
Case-control study of screening for prostatic cancer by digital rectal examinations
Lancet
(1991)
JickH et al.
Statins and the risk of dementia
Lancet
(2000)
CramerDW et al.
Over-the-counter analgesics and risk of ovarian cancer
Lancet
(1998)
IngramD et al.
Case-control study of phyto-oestrogens and breast cancer
Lancet
(1997)
GrimesDA et al.
An overview of clinical research: the lay of the land
Lancet
(2002)
GrimesDA et al.
Cohort studies: marching towards outcomes
Lancet
(2002)

StadelBV et al.

Oral contraceptives and breast cancer in young women

Lancet

(1985)

GrimesDA et al.

Bias and causal associations in observational research

Lancet

(2002)

SilvermanDT

Risk factors for pancreatic cancer: a case-control study based on direct interviews

Teratog Carcinog Mutagen

(2001)

OsakiY et al.

Factors associated with earthquake deaths in the great Hanshin-Awaji earthquake, 1995

Am J Epidemiol

(2001)

Cited by (340)

Invited review: Good practices in genome-wide association studies to identify candidate sequence variants in dairy cattle
2023, Journal of Dairy Science
Genotype data from dairy cattle selection programs have greatly facilitated GWAS to identify variants related to economic traits. Results can enhance the accuracy of genomic prediction, analyze more complex models that go beyond additive effects, elucidate the genetic architecture of a trait, and finally, decipher the underlying biology of traits. The entire process, comprising data generation, quality control, statistical analyses, interpretation of association results, and linking results to biology should be designed and executed to minimize the generation of false-positive and false-negative associations and misleading links to biological processes. This review aims to provide general guidelines for data analysis that address data quality control, association tests, adjustment for population stratification, and significance evaluation to improve the reliability of conclusions. We also provide guidance on post-GWAS strategy and the interpretation of results. These guidelines are tailored to dairy cattle, which are characterized by long-range linkage disequilibrium, large half-sib families, and routinely collected phenotypes, requiring different approaches than those applied in human GWAS. We discuss common limitations and challenges that have been overlooked in the analysis and interpretation of GWAS to identify candidate sequence variants in dairy cattle.
The added effect of non-pharmaceutical interventions and lifestyle behaviors on vaccine effectiveness against severe COVID-19 in Chile: A matched case-double control study
2023, Vaccine
World Health Organization approved vaccines have demonstrated relatively high protection against moderate to severe COVID-19. Prospective vaccine effectiveness (VE) designs with first-hand data and population-based controls are nevertheless rare. Neighborhood compared to hospitalized controls, may differ in compliance to non-pharmacuetical interventions (NPI) compliance, which may influence VE results in real-world settings. We aimed to determine VE against COVID-19 intensive-care-unit (ICU) admission using hospital and community-matched controls in a prospective design.
We conducted a multicenter, observational study of matched cases and controls (1:3) in adults ≧18 years of age from May to July 2021. For each case, a hospital control and two community controls were matched by age, gender, and hospital admission date or neighborhood of residence. Conditional logistic regression models were built, including interaction terms between NPIs, lifestyle behaviors, and vaccination status; the model’s β coefficients represent the added effect these terms had on COVID-19 VE.
Cases and controls differed in several factors including education level, obesity prevalence, and behaviors such as compliance with routine vaccinations, use of facemasks, and routine handwashing. VE was 98·2% for full primary vaccination and 85·6% for partial vaccination when compared to community controls, and somewhat lower, albeit not significantly, compared to hospital controls. A significant added effect to vaccination in reducing COVID-19 ICU admission was regular facemask use and VE was higher among individuals non-compliant with the national vaccine program, and/or tonroutine medical visits during the prior year.
VE against COVID-19 ICU admission in this stringent prospective case-double control study reached 98% two weeks after full primary vaccination, confirming the high effectiveness provided by earlier studies. Face mask use and hand washing were independent protective factors, the former adding additional benefit to VE. VE was significantly higher in subjects with increased risk behaviors.
Case-control study
2023, Translational Radiation Oncology
Case-control studies are an efficient means of investigating the relationship between an exposure and an outcome, and identifying possible predictors of outcome in the patient population being studied. While case-control studies cannot prove causality, they can establish the strength of the association between an exposure and an outcome. Given that a case-control study is conducted retrospectively with available patient data, it is a relatively cost-effective and efficient study design for establishing evidence in support of future prospective studies, or further developing new hypotheses. In a case-control study, one can study multiple exposures in one patient population, which is especially useful when exposure data is difficult to obtain. Case-control studies are feasible with a small sample size and can often be performed relatively quickly. Compared to a cohort study, a case-control study is more effective for proving the association between an exposure and an outcome in rare diseases or in a patient population with a long induction or latent period between the exposure and outcome. Indeed, case-control studies are sometimes the only viable study design for investigating the relationship between an exposure and an outcome. In this chapter, we will review what a case-control study is, when a case-control study is an appropriate choice for study design, and how to avoid common pitfalls associated with case-control studies. We will review three simple, recently published examples of case-control studies in radiation oncology. Using these examples as a template, we will outline the steps involved in approaching case-control study design.
A Case-Crossover Phenome-wide association study (PheWAS) for understanding Post-COVID-19 diagnosis patterns
2022, Journal of Biomedical Informatics
Post COVID-19 condition (PCC) is known to affect a large proportion of COVID-19 survivors. Robust study design and methods are needed to understand post-COVID-19 diagnosis patterns in all survivors, not just those clinically diagnosed with PCC.
We applied a case-crossover Phenome-Wide Association Study (PheWAS) in a retrospective cohort of COVID-19 survivors, comparing the occurrences of 1,671 diagnosis-based phenotype codes (PheCodes) pre- and post-COVID-19 infection periods in the same individual using a conditional logistic regression. We studied how this pattern varied by COVID-19 severity and vaccination status, and we compared to test negative and test negative but flu positive controls.
In 44,198 SARS-CoV-2-positive patients, we found enrichment in respiratory, circulatory, and mental health disorders post-COVID-19-infection. Top hits included anxiety disorder (p = 2.8e-109, OR = 1.7 [95 % CI: 1.6–1.8]), cardiac dysrhythmias (p = 4.9e-87, OR = 1.7 [95 % CI: 1.6–1.8]), and respiratory failure, insufficiency, arrest (p = 5.2e-75, OR = 2.9 [95 % CI: 2.6–3.3]). In severe patients, we found stronger associations with respiratory and circulatory disorders compared to mild/moderate patients. Fully vaccinated patients had mental health and chronic circulatory diseases rise to the top of the association list, similar to the mild/moderate cohort. Both control groups (test negative, test negative and flu positive) showed a different pattern of hits to SARS-CoV-2 positives.
Patients experience myriad symptoms more than 28 days after SARS-CoV-2 infection, but especially respiratory, circulatory, and mental health disorders. Our case-crossover PheWAS approach controls for within-person confounders that are time-invariant. Comparison to test negatives and test negative but flu positive patients with a similar design helped identify enrichment specific to COVID-19. This design may be applied other emerging diseases with long-lasting effects other than a SARS-CoV-2 infection. Given the potential for bias from observational data, these results should be considered exploratory. As we look into the future, we must be aware of COVID-19 survivors’ healthcare needs.
History of infertility and long-term weight, body composition, and blood pressure among women in Project Viva
2022, Annals of Epidemiology
To evaluate the association of a history of infertility with long-term weight, body composition, and blood pressure.
We studied 1581 women from the prospective cohort Project Viva. History of infertility was based on self-reported time to pregnancy ≥12 months or use of medical treatment to conceive for the index or any prior pregnancy; a diagnosis of infertility; claims for infertility treatments/prescriptions abstracted from medical records. The outcomes were weight, waist circumference, and body fat assessed through 12 years postpartum; and blood pressure assessed through 3 years postpartum. We used linear mixed-effect models adjusted for age, race/ethnicity, income, education, marital status, parity, and age at menarche.
Three hundred forty-two women (21.6%) had a history of infertility. In adjusted models, women with versus without infertility, had higher average weight (3.29 kg, 95% confidence interval [CI]: 1.35–5.24), waist circumference (2.46 cm, 95% CI: 0.78–4.13) and body fat (1.76 kg, 95% CI: 0.09–3.43). Among younger (18–29 years), but not older (≥30 years) women, infertility was associated with higher systolic (4.08 mmHg, 95% CI: 0.93, 7.23) and diastolic blood pressure (2.16 mmHg, 95% CI: 0.11–4.20).
A history of infertility may serve as a marker to identify women at higher cardiometabolic risk.
Common risk factors for dental caries and impaired glucose regulation in Guangxi, China
2024, International Journal of Dental Hygiene

View all citing articles on Scopus

View full text

SeriesCase-control studies: research in reverse

Summary

Section snippets

Basic case-control study design

Advantages and disadvantages

Case group

Measurement of exposure information

Control for confounding

Conclusion

Schizophr Res

Am J Gastroenterol

Lancet

Lancet

Lancet

Lancet

Lancet

Lancet

Lancet

Lancet

Lancet

Lancet

Risk factors for pancreatic cancer: a case-control study based on direct interviews

Teratog Carcinog Mutagen

Factors associated with earthquake deaths in the great Hanshin-Awaji earthquake, 1995

Am J Epidemiol

Series
Case-control studies: research in reverse