Search

Model selection in high-dimensional settings has received substantial attention in recent years, however, similar advancements in the low-dimensional setting have been lacking. In this article, we introduce a new variable selection procedure for low to moderate scale regressions (n>p). This method repeatedly splits the data into two sets, one for estimation and one for validation, to obtain an empirically optimized threshold which is then used to screen for variables to include in the final model. In an extensive simulation study, we show that the proposed variable selection technique enjoys superior performance compared with candidate methods (backward elimination via repeated data splitting, univariate screening at 0.05 level, adaptive LASSO, SCAD), being amongst those with the lowest inclusion of noisy predictors while having the highest power to detect the correct model and being unaffected by correlations among the predictors. We illustrate the methods by applying them to a cohort of patients undergoing hepatectomy at our institution. [ABSTRACT FROM AUTHOR]

Summary: Evidence on the relationship between the vitamin D pathway and outcomes in melanoma is growing, although it is not always clear. We investigated the impact of measured levels of sun exposure at diagnosis on associations of vitamin D receptor gene (VDR) polymorphisms and melanoma death in 3336 incident primary melanoma cases. Interactions between six SNPs and a common 3′‐end haplotype were significant (p < .05). These SNPs, and a haplotype, had a statistically significant association with survival among subjects exposed to high UVB in multivariable regression models and exerted their effect in the opposite direction among those with low UVB. SNPs rs1544410/BsmI and rs731236/TaqI remained significant after adjustment for multiple testing. These results suggest that the association between VDR and melanoma‐specific survival is modified by sun exposure around diagnosis, and require validation in an independent study. Whether the observed effects are dependent or independent of vitamin D activation remains to be determined. [ABSTRACT FROM AUTHOR]

A cancer in the contralateral breast in a woman with a previous or synchronous breast cancer is typically considered to be an independent primary tumor. Emerging evidence suggests that in a small subset of these cases the second tumor represents a metastasis. We sought to investigate the issue using massively parallel sequencing targeting 254 genes recurrently mutated in breast cancer. We examined the tumor archives at Memorial Sloan Kettering Cancer Center for the period 1995-2006 to identify cases of contralateral breast cancer where surgery for both tumors was performed at the Center. We report results from 49 patients successfully analyzed by a targeted massively parallel sequencing assay. Somatic mutations and copy number alterations were defined by state-of-the-art algorithms. Clonal relatedness was evaluated by statistical tests specifically designed for this purpose. We found evidence that the tumors in contralateral breasts were clonally related in three cases (6%) on the basis of matching mutations at codons where somatic mutations are rare. Clinical data and the presence of similar patterns of gene copy number alterations were consistent with metastasis for all three cases. In three additional cases, there was a solitary matching mutation at a common PIK3CA locus. The results suggest that a subset of contralateral breast cancers represent metastases rather than independent primary tumors. Massively parallel sequencing analysis can provide important evidence to clarify the diagnosis. However, given the inter-tumor mutational heterogeneity in breast cancer, sufficiently large gene panels need to be employed to define clonality convincingly in all cases. [ABSTRACT FROM AUTHOR]

Cancer epidemiologic research has traditionally been guided by the premise that certain diseases share an underlying etiology, or cause. However, with the rise of molecular and genomic profiling, attention has increasingly focused on identifying subtypes of disease. As subtypes are identified, it is natural to ask the question of whether they share a common etiology or in fact arise from distinct sets of risk factors. In this context, epidemiologic questions of interest include (1) whether a risk factor of interest has the same effect across all subtypes of disease and (2) whether risk factor effects differ across levels of each individual tumor marker of which the subtypes are comprised. A number of statistical models have been proposed to address these questions. In an effort to determine the similarities and differences among the proposed methods, and to identify any advantages or disadvantages, we use a simplified data example to elucidate the interpretation of model parameters and available hypothesis tests, and we perform a simulation study to assess bias in effect size, type I error, and power. The results show that when the number of tumor markers is small enough that the cross-classification of markers can be evaluated in the traditional polytomous logistic regression framework, then the statistical properties are at least as good as the more complex modeling approaches that have been proposed. The potential advantage of more complex methods is in the ability to accommodate multiple tumor markers in a model of reduced parametric dimension. [ABSTRACT FROM AUTHOR]

The landscape for early phase cancer clinical trials is changing dramatically because of the advent of targeted therapy. Increasingly, new drugs are designed to work against a target such as the presence of a specific tumor mutation. Because typically only a small proportion of cancer patients will possess the mutational target, but the mutation is present in many different cancers, a new class of basket trials is emerging, whereby the drug is tested simultaneously in different baskets, that is, subgroups of different tumor types. Investigators desire not only to test whether the drug works but also to determine which types of tumors are sensitive to the drug. A natural strategy is to conduct parallel trials, with the drug 's effectiveness being tested separately, using for example, the popular Simon two-stage design independently in each basket. The work presented is motivated by the premise that the efficiency of this strategy can be improved by assessing the homogeneity of the baskets ' response rates at an interim analysis and aggregating the baskets in the second stage if the results suggest the drug might be effective in all or most baskets. Via simulations, we assess the relative efficiencies of the two strategies. Because the operating characteristics depend on how many tumor types are sensitive to the drug, there is no uniformly efficient strategy. However, our investigation demonstrates that substantial efficiencies are possible if the drug works in most or all baskets, at the cost of modest losses of power if the drug works in only a single basket. Copyright © 2017 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Autophagy has been linked with melanoma risk and survival, but no polymorphisms in autophagy-related ( ATG) genes have been investigated in relation to melanoma progression. We examined five single-nucleotide polymorphisms ( SNPs) in three ATG genes ( ATG5; ATG10; and ATG16L) with known or suspected impact on autophagic flux in an international population-based case-control study of melanoma. DNA from 911 melanoma patients was genotyped. An association was identified between ( GG) (rs2241880) and earlier stage at diagnosis ( OR 0.47; 95% Confidence Intervals ( CI) = 0.27-0.81, P = 0.02) and a decrease in Breslow thickness ( P = 0.03). The ATG16L heterozygous genotype ( AG) (rs2241880) was associated with younger age at diagnosis ( P = 0.02). Two SNPs in ATG5 were found to be associated with increased stage (rs2245214 CG, OR 1.47; 95% CI = 1.11-1.94, P = 0.03; rs510432 CC, OR 1.84; 95% CI = 1.12-3.02, P = 0.05). Finally, we identified inverse associations between ATG5 ( GG rs2245214) and melanomas on the scalp or neck ( OR 0.20, 95% CI = 0.05-0.86, P = 0.03); ATG10 ( CC) (rs1864182) and brisk tumor infiltrating lymphocytes ( TILs) ( OR 0.42; 95% CI = 0.21-0.88, P = 0.02), and ATG5 ( CC) (rs510432) with nonbrisk TILs ( OR 0.55; 95% CI = 0.34-0.87, P = 0.01). Our data suggest that ATG SNPs might be differentially associated with specific host and tumor characteristics including age at diagnosis, TILs, and stage. These associations may be critical to understanding the role of autophagy in cancer, and further investigation will help characterize the contribution of these variants to melanoma progression. [ABSTRACT FROM AUTHOR]

Although nevus count is an established risk factor for melanoma, relationships between nevus number and patient and tumor characteristics have not been well studied and the influence of nevus count on melanoma-specific survival is equivocal. Using data from the Genes, Environment and Melanoma (GEM) study, a large population-based study of primary cutaneous melanoma, we evaluated associations between number of nevi and patient features, including sun-sensitivity summarized in a phenotypic index, and tumor characteristics. We also assessed the association of nevus count with melanoma-specific survival. Higher nevus counts were independently and positively associated with male gender and younger age at diagnosis, and they were inversely associated with lentigo maligna histology. We observed a borderline significant trend of poorer melanoma-specific survival with increasing quartile of nevus count, but little or no association between number of nevi and pigmentary phenotypic characteristics or prognostic tumor features. [ABSTRACT FROM AUTHOR]

With the advent of increasingly detailed molecular portraits of tumor specimens, much attention has been directed toward identifying clinically distinct subtypes of cancer. Subtyping of tumors can also be accomplished with the goal of identifying distinct etiologies. We demonstrate the use of new methodologies to identify genes that distinguish etiologically heterogeneous subtypes of breast cancer using data from the case-control Cancer and Steroid Hormone Study. Tumor specimens were evaluated using a breast cancer expression panel of 196 genes. Using a statistical measure that distinguishes the degree of etiologic heterogeneity in tumor subtypes, each gene is ranked on the basis of its ability to distinguish etiologically distinct subtypes. This is accomplished independently using case-control comparisons and by examining the concordance odds ratios in double primaries. The estrogen receptor gene, and others in this pathway with expression levels that correlated strongly with estrogen receptor levels, demonstrate high degrees of etiologic heterogeneity in both methods. Our results are consistent with a growing literature that confirms the distinct etiologies of breast cancers classified on the basis of estrogen receptor expression levels. This proof-of-principle project demonstrates the viability of new strategies to identify genomic features that distinguish subtypes of cancer from an etiologic perspective. [ABSTRACT FROM AUTHOR]

Melanocortin-1 receptor ( MC1R) is a marker of melanoma risk in populations of European ancestry. However, MC1R effects on survival are much less studied. We investigated associations between variation at MC1R and survival in an international, population-based series of single primary melanoma patients enrolled into the Genes, Environment, and Melanoma study. MC1R genotype data was available for 2,200 participants with a first incident primary melanoma diagnosis. We estimated the association of MC1R genotypes with melanoma-specific survival ( i.e., death caused by melanoma) and overall survival using COX proportional hazards modeling, adjusting for established prognostic factors for melanoma. We also conducted stratified analyses by Breslow thickness, tumor site, phenotypic index, and age. In addition, we evaluated haplotypes involving polymorphisms near the Agouti signaling protein gene ( ASIP) locus for their impacts on survival. Melanoma-specific survival was inversely associated with carriage of MC1R variants in the absence of consensus alleles compared to carriage of at least one consensus allele (hazard ratio (HR) = 0.60; 95% confidence interval (CI): 0.40, 0.90). MC1R results for overall survival were consistent with no association. We did not observe any statistical evidence of heterogeneity of effect estimates in stratified analyses. We observed increased hazard of melanoma-specific death among carriers of the risk haplotype TG near the ASIP locus (HR = 1.37; 95% CI: 0.91, 2.04) when compared to carriers of the most common GG haplotype. Similar results were noted for overall survival. Upon examining the ASIP TG/ TG diplotype, we observed considerably increased hazard of melanoma-specific death (HR = 5.11; 95% CI: 1.88, 13.88) compared to carriers of the most common GG/ GG diplotype. Our data suggest improved melanoma-specific survival among carriers of two inherited MC1R variants. [ABSTRACT FROM AUTHOR]

A rare germline variant in the microphthalmia-associated transcription factor ( MITF) gene, E318K, has been reported as associated with melanoma. We confirmed its independent association with melanoma [odds ratio ( OR) 1.7, 95% confidence interval ( CI) = 1.1, 2.7, P = 0.03]; adjusted for age, sex, center, age × sex interaction, pigmentation characteristics, family history of melanoma, and nevus density). In stratified analyses, carriage of MITF E318K was associated with melanoma more strongly in people with dark hair than fair hair (P for interaction, 0.03) and in those with no moles than some or many moles (P for interaction, <0.01). There was no evidence of interaction between MC1R 'red hair variants' and MITF E318K. Moreover, risk of melanoma among carriers with 'low risk' phenotypes was as great or greater than among those with 'at risk' phenotypes with few exceptions. [ABSTRACT FROM AUTHOR]

Cancer has traditionally been studied using the disease site of origin as the organizing framework. However, recent advances in molecular genetics have begun to challenge this taxonomy, as detailed molecular profiling of tumors has led to discoveries of subsets of tumors that have profiles that possess distinct clinical and biological characteristics. This is increasingly leading to research that seeks to investigate whether these subtypes of tumors have distinct etiologies. However, research in this field has been opportunistic and anecdotal, typically involving the comparison of distributions of individual risk factors between tumors classified on the basis of candidate tumor characteristics. The purpose of this article is to place this area of investigation within a more general conceptual and analytic framework, with a view to providing more efficient and practical strategies for designing and analyzing epidemiologic studies to investigate etiologic heterogeneity. We propose a formal definition of etiologic heterogeneity and show how classifications of tumor subtypes with larger etiologic heterogeneities inevitably possess greater disease risk predictability overall. We outline analytic strategies for estimating the degree of etiologic heterogeneity among a set of subtypes and for choosing subtypes that optimize the heterogeneity, and we discuss technical challenges that require further methodologic research. We illustrate the ideas by using a pooled case-control study of breast cancer classified by expression patterns of genes known to define distinct tumor subtypes. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Two main classes of methodology have been developed for addressing the analytical intractability of generalized linear mixed models: likelihood-based methods and Bayesian methods. Likelihood-based methods such as the penalized quasi-likelihood approach have been shown to produce biased estimates especially for binary clustered data with small clusters sizes. More recent methods using adaptive Gaussian quadrature perform well but can be overwhelmed by problems with large numbers of random effects, and efficient algorithms to better handle these situations have not yet been integrated in standard statistical packages. Bayesian methods, although they have good frequentist properties when the model is correct, are known to be computationally intensive and also require specialized code, limiting their use in practice. In this article, we introduce a modification of the hybrid approach of Capanu and Begg, 2011, Biometrics 67, 371-380, as a bridge between the likelihood-based and Bayesian approaches by employing Bayesian estimation for the variance components followed by Laplacian estimation for the regression coefficients. We investigate its performance as well as that of several likelihood-based methods in the setting of generalized linear mixed models with binary outcomes. We apply the methods to three datasets and conduct simulations to illustrate their properties. Simulation results indicate that for moderate to large numbers of observations per random effect, adaptive Gaussian quadrature and the Laplacian approximation are very accurate, with adaptive Gaussian quadrature preferable as the number of observations per random effect increases. The hybrid approach is overall similar to the Laplace method, and it can be superior for data with very sparse random effects. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

In constructing predictive models, investigators frequently assess the incremental value of a predictive marker by comparing the ROC curve generated from the predictive model including the new marker with the ROC curve from the model excluding the new marker. Many commentators have noticed empirically that a test of the two ROC areas often produces a non-significant result when a corresponding Wald test from the underlying regression model is significant. A recent article showed using simulations that the widely used ROC area test produces exceptionally conservative test size and extremely low power. In this article, we demonstrate that both the test statistic and its estimated variance are seriously biased when predictions from nested regression models are used as data inputs for the test, and we examine in detail the reasons for these problems. Although it is possible to create a test reference distribution by resampling that removes these biases, Wald or likelihood ratio tests remain the preferred approach for testing the incremental contribution of a new marker. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The vitamin D receptor (VDR) gene has been associated with cancer risk, but only a few polymorphisms have been studied in relation to melanoma risk and the results have been inconsistent. We examined 38 VDR gene single nucleotide polymorphisms (SNPs) in a large international multicenter population-based case-control study of melanoma. Buccal DNAs were obtained from 1,207 people with incident multiple primary melanoma and 2,469 with incident single primary melanoma. SNPs with known or suspected impact on VDR activity, haplotype tagging SNPs with ≥10% minor allele frequency in Caucasians, and SNPs reported as significant in other association studies were examined. Logistic regression was used to calculate the relative risks conferred by the individual SNP. Eight of 38 SNPs in the promoter, coding, and 3′ gene regions were individually significantly associated with multiple primary melanoma after adjusting for covariates. The estimated increase in risk for individuals who were homozygous for the minor allele ranged from 25 to 33% for six polymorphisms: rs10875712 (odds ratios [OR] 1.28; 95% confidence interval (CI), 1.01-1.62), rs4760674 (OR 1.33; 95% CI, 1.06-1.67), rs7139166 (OR 1.26; 95%CI, 1.02-1.56), rs4516035 (OR 1.25; 95%CI, 1.01-1.55), rs11168287 (OR 1.27; 95%CI, 1.03-1.57) and rs1544410 (OR 1.30; 95%CI, 1.04-1.63); for two polymorphisms, homozygous carriers had a decreased risk: rs7305032 (OR 0.81; 95%CI 0.65-1.02) and rs7965281 (OR, 0.78; 95%CI, 0.62-0.99). We recognize the potential false positive findings because of multiple comparisons; however, the eight significant SNPs in our study outnumbered the two significant tests expected to occur by chance. The VDR may play a role in melanomagenesis. [ABSTRACT FROM AUTHOR]

Much attention is directed currently to identifying subtypes of cancers that are genetically and clinically distinct. The expectation is that subtyping on the basis of somatic genomic characteristics will supplant traditional pathological subtypes with respect to relevance for targeted therapies and clinical course. Less attention has been paid to the goal of validating subtypes on the basis of the distinctiveness of their etiologies. In this article it is shown that studies of individuals with double primary malignancies provide uniquely valuable information for establishing the etiologic distinctiveness of candidate tumor subtypes. Studies of double primaries have the potential to definitively rank candidate taxonomic systems with respect to their etiological relevance by determining which subtypes are most highly correlated in the double primaries. The concept is illustrated with data from studies of the concordance of estrogen and progestin status in bilateral breast cancers, where it is shown that double primaries are much more likely to be concordant with respect to estrogen receptor (ER) status than for PR status. The high concordance of ER status is consistent with a growing literature demonstrating the etiologic distinctiveness of ER+ and ER− tumors. [ABSTRACT FROM AUTHOR]

When a cancer patient develops a new tumor it is necessary to determine if it is a recurrence (metastasis) of the original cancer, or an entirely new occurrence of the disease. This is accomplished by assessing the histo-pathology of the lesions. However, there are many clinical scenarios in which this pathological diagnosis is difficult. Since each tumor is characterized by a distinct pattern of somatic mutations, a more definitive diagnosis is possible in principle in these difficult clinical scenarios by comparing the two patterns. In this article we develop and evaluate a statistical strategy for this comparison when the data are derived from array copy number data, designed to identify all of the somatic allelic gains and losses across the genome. First a segmentation algorithm is used to estimate the regions of allelic gain and loss. The correlation in these patterns between the two tumors is assessed, and this is complemented with more precise quantitative comparisons of each plausibly clonal mutation within individual chromosome arms. The results are combined to determine a likelihood ratio to distinguish clonal tumor pairs (metastases) from independent second primaries. Our data analyses show that in many cases a strong clonal signal emerges. Sensitivity analyses show that most of the diagnoses are robust when the data are of high quality. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Objectives: Patients diagnosed with melanoma are at risk for developing recurrent and second primary disease. Skin self-examination (SSE) and sun protection are standard clinical recommendations to minimize risk. In this study we examined performance of these behaviors in individuals with melanoma drawn from the general population. Methods: Potential participants (N=148) with a first primary melanoma diagnosed in 2000 were identified through a population-based cancer registry in New Jersey, USA. One hundred and fifteen individuals participated in a 30 min telephone interview concerning behavioral adherence with SSE and sun protection, self-efficacy for performing these behaviors, and perceived risk of developing another skin cancer. We utilized logistic regression to estimate potential associations of demographic, medical, and psychosocial factors with SSE and sun protection, respectively. Results: Seventeen percent of subjects reported performing comprehensive SSE at least once every two months and 23% engaged in regular sun protection. Utilization of SSE was related to the presence of moles (OR=4.2, 95% CI: 1.1–15) and higher SSE self-efficacy (OR=14.4, 95% CI: 1.9–112). Regular sun protection was related to older age (>60 years; OR=3.3, 95% CI: 1.3–8.7), being female (OR=2.8, 95% CI: 1.1–7.3), and higher sun protection self-efficacy (OR=5.0, 95% CI: 1.4–18). These factors remained significant in multivariate models. Conclusion: In this group of primary melanoma survivors, the rates of SSE and sun protection are comparable to, but do not exceed, general population estimates. This study provides justification for further research to address barriers to prevention and control behaviors in melanoma survivors. Copyright © 2009 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The Lorenz curve is a graphical tool that is widely used to characterize the concentration of a measure in a population, such as wealth. It is frequently the case that the measure of interest used to rank experimental units when estimating the empirical Lorenz curve, and the corresponding Gini coefficient, is subject to random error. This error can result in an incorrect ranking of experimental units which inevitably leads to a curve that exaggerates the degree of concentration (variation) in the population. We consider a specific data configuration with a hierarchical structure where multiple observations are aggregated within experimental units to form the outcome whose distribution is of interest. Within this context, we explore this bias and discuss several widely available statistical methods that have the potential to reduce or remove the bias in the empirical Lorenz curve. The properties of these methods are examined and compared in a simulation study. This work is motivated by a health outcomes application that seeks to assess the concentration of black patient visits among primary care physicians. The methods are illustrated on data from this study. Copyright © 2008 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

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. Copyright © 2008 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Copyright of Statistics in Medicine is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)