Contrasting treatment‐specific survival using double‐robust estimators
30 Dec 2012-
About: The article was published on 2012-12-30 and is currently open access. It has received 1248 citations till now. The article focuses on the topics: Estimator.
Citations
More filters
TL;DR: Bayesian Additive Regression Trees (BART) as discussed by the authors is a Bayesian nonparametric modeling procedure, which can handle a large number of predictors, yields coherent uncertainty intervals, and fluidly handles continuous treatment variables and missing data for the outcome variable.
Abstract: Researchers have long struggled to identify causal effects in nonexperimental settings. Many recently proposed strategies assume ignorability of the treatment assignment mechanism and require fitting two models—one for the assignment mechanism and one for the response surface. This article proposes a strategy that instead focuses on very flexibly modeling just the response surface using a Bayesian nonparametric modeling procedure, Bayesian Additive Regression Trees (BART). BART has several advantages: it is far simpler to use than many recent competitors, requires less guesswork in model fitting, handles a large number of predictors, yields coherent uncertainty intervals, and fluidly handles continuous treatment variables and missing data for the outcome variable. BART also naturally identifies heterogeneous treatment effects. BART produces more accurate estimates of average treatment effects compared to propensity score matching, propensity-weighted estimators, and regression adjustment in the nonlinear ...
1,051 citations
TL;DR: Prospective risk estimates for breast cancer, ovarian cancer, and contralateral breast cancer in a prospective series of mutation carriers confirm findings from retrospective studies that common breast cancer susceptibility alleles in combination are predictive of breast cancer risk for BRCA2 carriers.
Abstract: Background: Reliable estimates of cancer risk are critical for guiding management of BRCA1 and BRCA2 mutation carriers. The aims of this study were to derive penetrance estimates for breast cancer, ovarian cancer, and contralateral breast cancer in a prospective series of mutation carriers and to assess how these risks are modified by common breast cancer susceptibility alleles. Methods: Prospective cancer risks were estimated using a cohort of 978 BRCA1 and 909 BRCA2 carriers from the United Kingdom. Nine hundred eighty-eight women had no breast or ovarian cancer diagnosis at baseline, 1509 women were unaffected by ovarian cancer, and 651 had been diagnosed with unilateral breast cancer. Cumulative risks were obtained using Kaplan–Meier estimates. Associations between cancer risk and covariables of interest were evaluated using Cox regression. All statistical tests were two-sided. Results: The average cumulative risks by age 70 years for BRCA1 carriers were estimated to be 60% (95% confidence interval [CI] = 44% to 75%) for breast cancer, 59% (95% CI = 43% to 76%) for ovarian cancer, and 83% (95% CI = 69% to 94%) for contralateral breast cancer. For BRCA2 carriers, the corresponding risks were 55% (95% CI = 41% to 70%) for breast cancer, 16.5% (95% CI = 7.5% to 34%) for ovarian cancer, and 62% (95% CI = 44% to 79.5%) for contralateral breast cancer. BRCA2 carriers in the highest tertile of risk, defined by the joint genotype distribution of seven single nucleotide polymorphisms associated with breast cancer risk, were at statistically significantly higher risk of developing breast cancer than those in the lowest tertile (hazard ratio = 4.1, 95% CI = 1.2 to 14.5; P = .02). Conclusions: Prospective risk estimates confirm that BRCA1 and BRCA2 carriers are at high risk of developing breast, ovarian, and contralateral breast cancer. Our results confirm findings from retrospective studies that common breast cancer susceptibility alleles in combination are predictive of breast cancer risk for BRCA2 carriers.
793 citations
TL;DR: A broad research agenda for understanding the relationships among social media, business, and society is outlined and it is hoped that the flexible framework outlined will help guide future research and develop a cumulative research tradition in this area.
Abstract: Social media are fundamentally changing the way we communicate, collaborate, consume, and create. They represent one of the most transformative impacts of information technology on business, both within and outside firm boundaries. This special issue was designed to stimulate innovative investigations of the relationship between social media and business transformation. In this paper we outline a broad research agenda for understanding the relationships among social media, business, and society. We place the papers comprising the special issue within this research framework and identify areas where further research is needed. We hope that the flexible framework we outline will help guide future research and develop a cumulative research tradition in this area.
778 citations
TL;DR: It is demonstrated that addition of cetuximab to fluorouracil, leucovorin, and irinotecan (FOLFIRI) significantly improved overall survival, progression-free survival, and objective response in the first-line treatment of patients with KRAS codon 12/13 (exon 2) wild-type metastatic colorectal cancer.
Abstract: Purpose The phase III CRYSTAL study demonstrated that addition of cetuximab to fluorouracil, leucovorin, and irinotecan (FOLFIRI) significantly improved overall survival, progression-free survival, and objective response in the first-line treatment of patients with KRAS codon 12/13 (exon 2) wild-type metastatic colorectal cancer (mCRC). Outcome was reassessed in subgroups defined by extended RAS mutation testing. Patients and Methods Existing DNA samples from KRAS exon 2 wild-type tumors from CRYSTAL study patients were reanalyzed for other RAS mutations in four additional KRAS codons (exons 3 and 4) and six NRAS codons (exons 2, 3, and 4) using beads, emulsion, amplification, and magnetics technology. No tissue microdissection was performed. A ≥ 5% mutant allele cutoff was used to call mutations. Results Mutation status was evaluable in 430 (64.6%) of 666 patients with KRAS exon 2 wild-type tumors. Other RAS mutations were detected in 63 (14.7%) of 430 patients. In those with RAS wild-type tumors, a sign...
639 citations
TL;DR: This 30th adult heart transplant report is based on data submitted on 110,486 heart transplants in recipients of all ages by 407 centers worldwide since 1982 through June 30, 2012, with follow-up until June 30- 2012.
Abstract: This 30th adult heart transplant report is based on data submitted on 110,486 heart transplants in recipients of all ages (including 99,008 adults) by 407 centers worldwide since 1982 through June 30, 2012, with follow-up until June 30, 2012. Summary data are provided for the entire cohort of patients, whereas a number of additional analyses focus on cohorts who received transplants more recently. Detailed data analyses can be viewed in the International Society for Heart and Lung Transplantation (ISHLT) Registry slide sets available online (www.ishlt.org/registries). The report is divided into several sections:
594 citations
References
More filters
TL;DR: In this paper, a new class of semiparametric estimators, based on inverse probability weighted estimating equations, were proposed for parameter vector α 0 of the conditional mean model when the data are missing at random in the sense of Rubin and the missingness probabilities are either known or can be parametrically modeled.
Abstract: In applied problems it is common to specify a model for the conditional mean of a response given a set of regressors. A subset of the regressors may be missing for some study subjects either by design or happenstance. In this article we propose a new class of semiparametric estimators, based on inverse probability weighted estimating equations, that are consistent for parameter vector α0 of the conditional mean model when the data are missing at random in the sense of Rubin and the missingness probabilities are either known or can be parametrically modeled. We show that the asymptotic variance of the optimal estimator in our class attains the semiparametric variance bound for the model by first showing that our estimation problem is a special case of the general problem of parameter estimation in an arbitrary semiparametric model in which the data are missing at random and the probability of observing complete data is bounded away from 0, and then deriving a representation for the efficient score...
2,638 citations
TL;DR: In this article, the conditional hazard of dropout is modeled semiparametrically and no restrictions are placed on the joint distribution of the outcome and other measured variables, and it is shown how to make inferences about the marginal mean μ0 when the continuous dropout time Q is modeled semi-parameterically.
Abstract: Consider a study whose design calls for the study subjects to be followed from enrollment (time t = 0) to time t = T, at which point a primary endpoint of interest Y is to be measured. The design of the study also calls for measurements on a vector V t) of covariates to be made at one or more times t during the interval [0, T). We are interested in making inferences about the marginal mean μ0 of Y when some subjects drop out of the study at random times Q prior to the common fixed end of follow-up time T. The purpose of this article is to show how to make inferences about μ0 when the continuous drop-out time Q is modeled semiparametrically and no restrictions are placed on the joint distribution of the outcome and other measured variables. In particular, we consider two models for the conditional hazard of drop-out given (V(T), Y), where V(t) denotes the history of the process V t) through time t, t ∈ [0, T). In the first model, we assume that λQ(t|V(T), Y) exp(α0 Y), where α0 is a scalar paramet...
1,088 citations
TL;DR: Bayesian Additive Regression Trees (BART) as discussed by the authors is a Bayesian nonparametric modeling procedure, which can handle a large number of predictors, yields coherent uncertainty intervals, and fluidly handles continuous treatment variables and missing data for the outcome variable.
Abstract: Researchers have long struggled to identify causal effects in nonexperimental settings. Many recently proposed strategies assume ignorability of the treatment assignment mechanism and require fitting two models—one for the assignment mechanism and one for the response surface. This article proposes a strategy that instead focuses on very flexibly modeling just the response surface using a Bayesian nonparametric modeling procedure, Bayesian Additive Regression Trees (BART). BART has several advantages: it is far simpler to use than many recent competitors, requires less guesswork in model fitting, handles a large number of predictors, yields coherent uncertainty intervals, and fluidly handles continuous treatment variables and missing data for the outcome variable. BART also naturally identifies heterogeneous treatment effects. BART produces more accurate estimates of average treatment effects compared to propensity score matching, propensity-weighted estimators, and regression adjustment in the nonlinear ...
1,051 citations
TL;DR: Prospective risk estimates for breast cancer, ovarian cancer, and contralateral breast cancer in a prospective series of mutation carriers confirm findings from retrospective studies that common breast cancer susceptibility alleles in combination are predictive of breast cancer risk for BRCA2 carriers.
Abstract: Background: Reliable estimates of cancer risk are critical for guiding management of BRCA1 and BRCA2 mutation carriers. The aims of this study were to derive penetrance estimates for breast cancer, ovarian cancer, and contralateral breast cancer in a prospective series of mutation carriers and to assess how these risks are modified by common breast cancer susceptibility alleles. Methods: Prospective cancer risks were estimated using a cohort of 978 BRCA1 and 909 BRCA2 carriers from the United Kingdom. Nine hundred eighty-eight women had no breast or ovarian cancer diagnosis at baseline, 1509 women were unaffected by ovarian cancer, and 651 had been diagnosed with unilateral breast cancer. Cumulative risks were obtained using Kaplan–Meier estimates. Associations between cancer risk and covariables of interest were evaluated using Cox regression. All statistical tests were two-sided. Results: The average cumulative risks by age 70 years for BRCA1 carriers were estimated to be 60% (95% confidence interval [CI] = 44% to 75%) for breast cancer, 59% (95% CI = 43% to 76%) for ovarian cancer, and 83% (95% CI = 69% to 94%) for contralateral breast cancer. For BRCA2 carriers, the corresponding risks were 55% (95% CI = 41% to 70%) for breast cancer, 16.5% (95% CI = 7.5% to 34%) for ovarian cancer, and 62% (95% CI = 44% to 79.5%) for contralateral breast cancer. BRCA2 carriers in the highest tertile of risk, defined by the joint genotype distribution of seven single nucleotide polymorphisms associated with breast cancer risk, were at statistically significantly higher risk of developing breast cancer than those in the lowest tertile (hazard ratio = 4.1, 95% CI = 1.2 to 14.5; P = .02). Conclusions: Prospective risk estimates confirm that BRCA1 and BRCA2 carriers are at high risk of developing breast, ovarian, and contralateral breast cancer. Our results confirm findings from retrospective studies that common breast cancer susceptibility alleles in combination are predictive of breast cancer risk for BRCA2 carriers.
793 citations
TL;DR: A simple function, in terms of two physically meaningful parameters, has been evolved, which fits survivorship data very well and can be used to compare succinctly the mortality of two groups, different in respect of treatment, type of cancer, or other characteristics.
Abstract: On the basis of experience with calculated survivorships of patients following treatment for cancer, a simple function, in terms of two physically meaningful parameters, has been evolved, which fits such survivorship data very well. These two parameters can be used to compare succinctly the mortality of two groups, different in respect of treatment, type of cancer, or other characteristics. The parameters are c (“cured”), which represents the proportion of the population which is subject only to “normal” death rates, and β, which is the death rate from the cancer, to which the rest of the population [not “cured,” (1–c)] is subject. Thus if one treatment is characterized by c 1 = 0.30, β 1 = 0.25, another by c 2 = 0.20, β 2 = 0.15, this could be interpreted as meaning that while the first treatment “cured” a larger proportion of the population than did the second treatment, it did not ameliorate the deaths attributable to cancer in the patients not cured as much as did the second treatment. If l T...
785 citations