Case-control studies of genotypic relative risks using children of cases as controls

The use of a child as a case's control in a case-control study of genetic factors may be advantageous in some situations. We describe three methods of analysing such data. A method based upon the unconditional likelihood using case/child pairings apparently is the most efficient method. However, a conditional likelihood method using case/child pairs is more robust in that it allows for heterogeneity of the genetic trait among subpopulations as long as matings occur only within the same subpopulation. We argue that the child can be considered a genetic surrogate for the missing spouse and hence such designs are as valid as are those using spouses.     

The use of hierarchical models for estimating relative risks of individual genetic variants: an application to a study of melanoma

For major genes known to influence the risk of cancer, an important task is to determine the risks conferred by individual variants, so that one can appropriately counsel carriers of these mutations. This is a challenging task, since new mutations are continually being identified, and there is typically relatively little empirical evidence available about each individual mutation. Hierarchical modeling offers a natural strategy to leverage the collective evidence from these rare variants with sparse data. This can be accomplished when there are available higher-level covariates that characterize the variants in terms of attributes that could distinguish their association with disease. In this article, we explore the use of hierarchical modeling for this purpose using data from a large population-based study of the risks of melanoma conferred by variants in the CDKN2A gene. We employ both a pseudo-likelihood approach and a Bayesian approach using Gibbs sampling. The results indicate that relative risk estimates tend to be primarily influenced by the individual case-control frequencies when several cases and/or controls are observed with the variant under study, but that relative risk estimates for variants with very sparse data are more influenced by the higher-level covariate values, as one would expect. The analysis offers encouragement that we can draw strength from the aggregating power of hierarchical models to provide guidance to medical geneticists when they offer counseling to patients with rare or even hitherto unobserved variants. However, further research is needed to validate the application of asymptotic methods to such sparse data.     

医院内菌血症危险因素病例对照研究

目的：探讨医院内菌血症的危险因素,方法：于1999年4－12月在福州市对某医院1994年1月至1997年12月间发生医院内菌血症住院病人进行1：1配对病例对照研究,结果：单因素卡方分析发现,住院时间超过30天,应用丙种球蛋白,应用抗生素,重症监护,导尿,动脉静脉导,其它介入性诊治,血白蛋白低,贫血,输血等10个因素与病人医院内菌务 有显性关联,条件Logistic多元回归模型分析表明动脉脉导管,贫血,重症监护和住院时间超过30天是引起医院内菌血症的主要独立危险因素,而且趋势X2分析发现,贫血程度越严重,住院时间越长,病人发生医院内菌血症的风险就越大。结论：减少动脉脉导管或缩短其留置时间,积极治疗贫血对预防和控制医院内菌血症有十分重要的意义。     

Population-attributable risk estimates for risk factors associated with Campylobacter infection, australia

In 2001-2002, a multicenter, prospective case-control study involving 1,714 participants > or =5 years of age was conducted in Australia to identify risk factors for Campylobacter infection. Adjusted population-attributable risks (PARs) were derived for each independent risk factor contained within the final multivariable logistic regression model. Estimated PARs were combined with adjusted (for the > or =5 years of age eligibility criterion) notifiable disease surveillance data to estimate annual Australian Campylobacter case numbers attributable to each risk factor. Simulated distributions of "credible values" were then generated to model the uncertainty associated with each case number estimate. Among foodborne risk factors, an estimated 50,500 (95% credible interval 10,000-105,500) cases of Campylobacter infection in persons > or =5 years of age could be directly attributed each year to consumption of chicken in Australia. Our statistical technique could be applied more widely to other communicable diseases that are subject to routine surveillance.     

Analysis of case-control studies of genetic and environmental factors with missing genetic information and haplotype-phase ambiguity

Case-control studies of unrelated subjects are now widely used to study the role of genetic susceptibility and gene-environment interactions in the etiology of complex diseases. Exploiting an assumption of gene-environment independence, and treating the distribution of environmental exposures as completely nonparametric, Chatterjee and Carroll recently developed an efficient retrospective maximum-likelihood method for analysis of case-control studies. In this article, we develop an extension of the retrospective maximum-likelihood approach to studies where genetic information may be missing on some study subjects. In particular, special emphasis is given to haplotype-based studies where missing data arise due to linkage-phase ambiguity of genotype data. We use a profile likelihood technique and an appropriate expectation-maximization (EM) algorithm to derive a relatively simple procedure for parameter estimation, with or without a rare disease assumption, and possibly incorporating information on the marginal probability of the disease for the underlying population. We also describe two alternative robust approaches that are less sensitive to the underlying gene-environment independence and Hardy-Weinberg-equilibrium assumptions. The performance of the proposed methods is studied using simulation studies in the context of haplotype-based studies of gene-environment interactions. An application of the proposed method is illustrated using a case-control study of ovarian cancer designed to investigate the interaction between BRCA1/2 mutations and reproductive risk factors in the etiology of ovarian cancer.     

The performance of different propensity-score methods for estimating relative risks

OBJECTIVES: The propensity score is the probability of treatment conditional on observed variables. Conditioning on the propensity-score results in unbiased estimation of the expected difference in observed responses to two treatments. The performance of propensity-score methods for estimating relative risks has not been studied. STUDY DESIGN AND SETTING: Monte Carlo simulations were used to assess the performance of matching, stratification, and covariate adjustment using the propensity score to estimate relative risks. RESULTS: Matching on the propensity score and stratification on the quintiles of the propensity score resulted in estimates of relative risk with similar mean squared error (MSE). Propensity-score matching resulted in estimates with less bias, whereas stratification on the propensity score resulted in estimates of with greater precision. Including only variables associated with the outcome or including only the true confounders in the propensity-score model resulted in estimates with lower MSE than did including all variables associated with treatment or all measured variables in the propensity-score model. CONCLUSIONS: When estimating relative risks, propensity-score matching resulted in estimates with less bias than did stratification on the quintiles of the propensity score, but stratification on the quintiles of the propensity score resulted in estimates with greater precision.     

A plea to stop using the case-control design in retrospective database studies

The case-control design is widely used in retrospective database studies, often leading to spectacular findings. However, results of these studies often cannot be replicated, and the advantage of this design over others is questionable. To demonstrate the shortcomings of applications of this design, we replicate two published case-control studies. The first investigates isotretinoin and ulcerative colitis using a simple case-control design. The second focuses on dipeptidyl peptidase-4 inhibitors and acute pancreatitis, using a nested case-control design. We include large sets of negative control exposures (where the true odds ratio is believed to be 1) in both studies. Both replication studies produce effect size estimates consistent with the original studies, but also generate estimates for the negative control exposures showing substantial residual bias. In contrast, applying a self-controlled design to answer the same questions using the same data reveals far less bias. Although the case-control design in general is not at fault, its application in retrospective database studies, where all exposure and covariate data for the entire cohort are available, is unnecessary, as other alternatives such as cohort and self-controlled designs are available. Moreover, by focusing on cases and controls it opens the door to inappropriate comparisons between exposure groups, leading to confounding for which the design has few options to adjust for. We argue that this design should no longer be used in these types of data. At the very least, negative control exposures should be used to prove that the concerns raised here do not apply.     

Converting relative risks to absolute risks: a graphical approach

This paper presents a graphical method for converting relative risks to absolute risks. These absolute risk estimates are a function of the patient's current age, the patient's risk of developing cancer relative to some baseline population, the age specific cancer hazard in the baseline population, and the patient's competing mortal risk from all other causes. Graphs for breast cancer morbidity in women, cardiovascular mortality in men, and lung cancer morbidity in men illustrate the method. These graphs provide the probability of developing cancer in the next twenty years given the patient's current age and relative risk. They are derived under the proportional hazards model. A graph for lung cancer in men that uses a plausible exponential hazards model is also provided. The paper illustrates the importance of competing mortal hazard from other causes on absolute cancer risk. The strengths and weaknesses of this method are discussed. The graphs presented in this paper may be used as an aid in clinical decision making and in patient counselling.     

Multilevel modelling for measuring interaction of effects between multiple categorical variables: An illustrative application using risk factors for preeclampsia

Background

Measuring multiple and higher-order interaction effects between multiple categorical variables proves challenging.

Objectives

To illustrate a multilevel modelling approach to studying complex interactions.

Methods

We apply a two-level random-intercept linear regression to a binary outcome for individuals (level-1) nested within strata (level-2) defined by all observed combinations of multiple categorical exposure variables. As a pedagogic application, we analyse 36 strata defined by five risk factors of preeclampsia (parity, previous preeclampsia, chronic hypertension, multiple pregnancies, body mass index category) among 652,603 women in the Swedish Medical Birth Registry between 2002 and 2010.

Results

The absolute risk of preeclampsia was 4% but was predicted to vary from 1% to 44% across strata. The stratum discriminatory accuracy was 30% according to the variance partition coefficient (VPC) and 0.73 according to the area under the receiver operating characteristic curve (AUC). While the risk heterogeneity across strata was primarily due to the main effects of the categories defining the strata, 5% of the variation was attributable to their two- and higher-way interaction effects. One stratum presented a positive interaction, and two strata presented negative interaction.

Conclusions

Multilevel modelling is an innovative tool for identifying and analysing higher-order interaction effects. Further work is needed to explore how this approach can best be applied to making causal inferences.     

On the measurement of susceptibility to genetic factors

Geneticists usually measure the phenotypic effects of a single gene trait in terms of penetrance and recurrence risks in relatives of affected individuals, while epidemiologists usually compute measures of relative and attributable risks. These concepts can be merged to measure the proportion of individuals "susceptible" to a genetic factor. In the context of a sufficient cause model, susceptibility can be defined as the underlying factor(s) sufficient to make a person develop disease because of the genetic factor in the absence of other causes. The proportion of susceptibles to the genetic factor in the population differs conceptually and often arithmetically from the penetrance of the genotype especially for common diseases with etiologic heterogeneity. For a wide range of disease and allele frequencies, it can be shown that the proportion of susceptibles can be approximated by the risk difference measure (i.e., difference between penetrance with the genotype and penetrance without the genotype). We also apply the concept of susceptibility to estimate familial recurrence of disease due to a genetic factor. This measure of familial recurrence differs conceptually from simple recurrence risk and can be approximated by the familial risk difference measure (i.e., difference between recurrence risks in relatives of cases and relatives of controls) for a wide range of disease and allele frequencies.     

Smoking patterns by occupation and duration of employment

Lifetime patterns of smoking and occupation based on personal interviews were examined among 3,627 white men and 1,200 white women who were randomly selected from ten areas in the United States during the period 1977-1978. These individuals participated in the control series of the National Bladder Cancer Study. We estimated, based on Axelson's method, the extent to which smoking habits for given occupational groups would confound the estimated relative risk for lung cancer for 62 occupations among men and 18 occupations among women. Among men, confounding by smoking resulted in a 30% or greater increased risk of lung cancer in only three occupational groups--namely, stationary engineers and power station operators (relative risk (RR) = 1.6), printers (RR = 1.3), and fishermen and sailors (RR = 1.3). A decrease in lung cancer risk of 0.8 or less due to smoking habits was observed among the clergy (RR = 0.5) and chemical workers (RR = 0.7). Among women, a 30% increase or greater in the risk of lung cancer based on smoking habits alone was found for food service workers (RR = 1.5), building managers and administrators (RR = 1.3), telephone and telegraph operators (RR = 1.3), and operatives (RR = 1.3). A risk ratio of 0.8 or less was observed for those women employed as farmers (RR = 0.5) and teachers (RR = 0.8). Smoking habits by duration of employment were also examined for 38 occupations among men. The largest increase in the risk of lung cancer based on the smoking habits among long-term workers was only 1.3 and was observed for those men employed 20 or more years as painters and as electricians. These findings suggest that the smoking patterns, in only a few occupational groups that we evaluated, confound estimates of the relative risk by more than 30%, and for most occupational groups under investigation in this study, confounding by smoking alone did not produce trends in relative risks by duration of employment.     

Prioritizing individual genetic variants after kernel machine testing using variable selection

Kernel machine learning methods, such as the SNP‐set kernel association test (SKAT), have been widely used to test associations between traits and genetic polymorphisms. In contrast to traditional single‐SNP analysis methods, these methods are designed to examine the joint effect of a set of related SNPs (such as a group of SNPs within a gene or a pathway) and are able to identify sets of SNPs that are associated with the trait of interest. However, as with many multi‐SNP testing approaches, kernel machine testing can draw conclusion only at the SNP‐set level, and does not directly inform on which one(s) of the identified SNP set is actually driving the associations. A recently proposed procedure, KerNel Iterative Feature Extraction (KNIFE), provides a general framework for incorporating variable selection into kernel machine methods. In this article, we focus on quantitative traits and relatively common SNPs, and adapt the KNIFE procedure to genetic association studies and propose an approach to identify driver SNPs after the application of SKAT to gene set analysis. Our approach accommodates several kernels that are widely used in SNP analysis, such as the linear kernel and the Identity by State (IBS) kernel. The proposed approach provides practically useful utilities to prioritize SNPs, and fills the gap between SNP set analysis and biological functional studies. Both simulation studies and real data application are used to demonstrate the proposed approach.     

Design and conduct of occupational epidemiology studies: III. Design aspects of case-control studies

Currently available approaches for the design of occupational case-control studies are reviewed. An accompanying paper reviews methods of analysis. We commence by drawing a distinction between cohort-based and registry-based studies. Methods for selecting cases and controls are then reviewed, including cumulative incidence and incidence density sampling, matching, sources of controls, and issues in control selection. Finally, the advantages and disadvantages of the case-control approach are summarized.     

Design and conduct of occupational epidemiology studies: I. Design aspects of cohort studies

Cohort and case-control studies are two standard approaches for investigating the etiology of occupational diseases. This paper, which is the first of a four-part series, contains a review of the design features of occupational cohort studies. Topics discussed include the basic features of prospective and historical cohort studies, options for defining the cohort, disease incidence ascertainment, and considerations involved in planning an occupational cohort study. Subsequent papers in this series will focus on data analysis of occupational cohort studies and the design and analysis of occupational case-control studies.     

Genotypic relative risks under ordered restriction

In mapping diseases of complex aetiology, conventional linkage approaches narrow the location of the disease susceptibility locus to quite a large region so that candidate gene association studies are then necessary to further isolate these genes. However, even in the simplest scenario where the candidate locus is bi-allelic, two statistical tests with various correcting factors have been proposed: a chi-square 1 df test (counting chromosomes) which may be slightly conservative and a 2 df chi-square test (counting genotypes) which may lack power because of the extra degree of freedom. This paper introduces a better and more powerful alternative which turns out to be a compromise between the two existing statistical tests. The asymptotic distribution of this test statistic is determined and the efficacy of the 3 tests are compared under different genetic models by simulation. Genet. Epidemiol. 15:135–146,1998. © 1998 Wiley-Liss, Inc.     

Sex differences in genetic and environmental determinants of pulse pressure

Pulse pressure (PP) is an independent risk factor for cardiovascular disease. PP rises with age, more so in women. We examined sex differences in the correlations and variance components of PP in adult subjects from 767 nuclear families, enriched with those containing twins, from the Victorian Family Heart Study. After adjusting for age, we found no significant differences in the means or variances of PP in males and females. Under the assumption of no sex differences, the proportions of variance due to shared genes, shared environment, and individual-specific environment were 20%, 23% and 57%, respectively. However, same-sex relative pairs had significantly higher correlations than opposite-sex pairs (P = 0.005), implying the existence of sex-dependent effects. Extensions to the simple variance components model suggested three possible explanations for these differences: smaller genetic correlation between opposite-sex pairs (rhoG,MF = 0.45, P = 0.007); smaller environmental correlation between opposite-sex pairs (P = 0.0003); or different environmental and genetic correlations obtained by estimating genetic, environmental, and individual variance components separately for males and females (not nested, Akaike's Information Criterion (AIC) smaller by 6.69). Under the last model, the genetic component of PP variance is greater for males (1.62 vs 0.33) while the environmental component is greater for females (1.84 vs 0), which would have implications for the planning of gene discovery studies, since heritability would be higher in males. However, the second (environmental) approach best fits the data according to the AIC. Genetic explanations for sex differences in phenotypic correlations may be misleading unless shared environmental factors are also considered. PP illustrates a phenotype in which sex dependency represents an important component of phenotypic determination that can be revealed by detailed variance components modelling.     

泰兴市胃癌危险因素病例对照研究

目的：探讨胃癌的危险因素。方法：对泰兴市439例胃癌进行1：1配比病例对照研究,通过条件Logistic回归单因素和多因素分析筛选主要危险因素,计算各因素的比值比和95％可信限。结果：胃慢性疾病史、文化程度差、人均收入低、吸烟、不良饮食习惯、情绪较差均与胃癌有明显关系。其中胃慢性疾病史与胃癌发生最为密切（OR＝22．01,95％CL为10．39－46．62）为主要危险因素。结论：应针对上述危险因素采取预防措施。     

The effects of joint misclassification of exposure and disease on the attributable risk

While there is extensive methodological literature analysing the effects of misclassification on the relative risk under various misclassification scenarios, for the attributable risk only the effects of non-differential misclassification either of exposure or disease, and the effects of non-differential independent misclassification of exposure and disease have been discussed for the 2 x 2-situation. The paper investigates the effects of non-differential correlated misclassification of exposure and disease on the attributable risk taking possible correlations of both types of misclassification into account. Furthermore, a comparison with the corresponding effects on the relative risk is drawn. We propose a matrix-based approach to describe the underlying structure of non-differential misclassification. The bias arising from non-differential misclassification in the attributable risk and relative risk is evaluated in four examples assuming under- or overreporting of exposure and disease. In each of the four examples we found scenarios where pronounced differences in degree and, more importantly, in direction of bias occurred. Our results clearly demonstrate the danger lying in the stereotype transfer of findings regarding misclassification effects on the relative risk to other epidemiologic risk measures and underline the necessity of specific analyses of the effects of misclassification on the attributable risk.