149 research outputs found
Analyzing Competing Risk Data Using the R timereg Package
No full textIn this paper we describe flexible competing risks regression models using the comp.risk() function available in the timereg package for R based on Scheike et al. (2008). Regression models are specified for the transition probabilities, that is the cumulative incidence in the competing risks setting. The model contains the Fine and Gray (1999) model as a special case. This can be used to do goodness-of-fit test for the subdistribution hazardsâ proportionality assumption (Scheike and Zhang 2008). The program can also construct confidence bands for predicted cumulative incidence curves. We apply the methods to data on follicular cell lymphoma from Pintilie (2007), where the competing risks are disease relapse and death without relapse. There is important non-proportionality present in the data, and it is demonstrated how one can analyze these data using the flexible regression models.
Penalized estimation for competing risks regression with applications to high-dimensional covariates
No full textHigh-dimensional regression has become an increasingly important topic for many research fields. For example, biomedical research generates an increasing amount of data to characterize patients' bio-profiles (e.g. from a genomic high-throughput assay). The increasing complexity in the characterization of patients' bio-profiles is added to the complexity related to the prolonged follow-up of patients with the registration of the occurrence of possible adverse events. This information may offer useful insight into disease dynamics and in identifying subset of patients with worse prognosis and better response to the therapy. Although in the last years the number of contributions for coping with high and ultra-high-dimensional data in standard survival analysis have increased (Witten and Tibshirani, 2010. Survival analysis with high-dimensional covariates. Statistical Methods in Medical Research 19(1), 29-51), the research regarding competing risks is less developed (Binder and others, 2009. Boosting for high-dimensional time-to-event data with competing risks. Bioinformatics 25(7), 890-896). The aim of this work is to consider how to do penalized regression in the presence of competing events. The direct binomial regression model of Scheike and others (2008. Predicting cumulative incidence probability by direct binomial regression. Biometrika 95(1), 205-220) is reformulated in a penalized framework to possibly fit a sparse regression model. The developed approach is easily implementable using existing high-performance software to do penalized regression. Results from simulation studies are presented together with an application to genomic data when the endpoint is progression-free survival. An R function is provided to perform regularized competing risks regression according to the binomial model in the package timereg (Scheike and Martinussen, 2006. Dynamic Regression models for survival data. New York: Springer), available through CRAN
Efficient estimation of the marginal mean of recurrent events.
No full textRecurrent events are often encountered in clinical and epidemiological studies where a terminal event is also observed. With recurrent events data it is of great interest to estimate the marginal mean of the cumulative number of recurrent events experienced prior to the terminal event. The standard nonparametric estimator was suggested in Cook and Lawless and further developed in Ghosh and Lin. We here investigate the efficiency of this estimator that, surprisingly, has not been studied before. We rewrite the standard estimator as an inverse probability of censoring weighted estimator. From this representation, we derive an efficient augmented estimator using efficient estimation theory for right-censored data. We show that the standard estimator is efficient in settings with no heterogeneity. In other settings with different sources of heterogeneity, we show theoretically and by simulations that the efficiency can be greatly improved when an efficient augmented estimator based on dynamic predictions is employed, at no extra cost to robustness. The estimators are applied and compared to study the mean number of catheter-related bloodstream infections in heterogeneous patients with chronic intestinal failure who can possibly die, and the efficiency gain is highlighted in the resulting point-wise confidence intervals
Flexible survival regression modelling
No full textRegression analysis of survival data, and more generally event history data, is typically based on Cox's regression model. We here review some recent methodology, focusing on the limitations of Cox's regression model. The key limitation is that the model is not well suited to represent time-varying effects. We start by considering classical and also more recent goodness-of-fit procedures for the Cox model that will reveal when the Cox model does not capture important aspects of the data, such as time-varying effects. We present recent regression models that are able to deal with and describe such time-varying effects. The introduced models are all applied to data on breast cancer from the Norwegian cancer registry, and these analyses clearly reveal the shortcomings of Cox's regression model and the need for other supplementary analyses with models such as those we present here
Efficient estimation of the marginal mean of recurrent events in randomized controlled trials
No full textRecurrent events data are often encountered in biomedical settings, where individuals may also experience a terminal event such as death. A useful estimand to summarize such data is the marginal mean of the cumulative number of recurrent events up to a specific time horizon, allowing also for the possible presence of a terminal event. Recently, it was found that augmented estimators can estimate this quantity efficiently, providing improved inference. Improvement in efficiency by the use of covariate adjustment is increasing in popularity as the methods get further developed, and is supported by regulatory agencies EMA (2015) and FDA (2023). Motivated by these arguments, this article presents novel efficient estimators for clinical data from randomized controlled trials, accounting for additional information from auxiliary covariates. Moreover, in randomized studies when both right censoring and competing risks are present, we propose a novel doubly augmented estimator of the marginal mean , which has two optimal augmentation components due to censoring and randomization. We provide theoretical and asymptotic details for the novel estimators, also confirmed by simulation studies. Then, we discuss how to improve efficiency, both theoretically by computing the expected amount of variance reduction, and practically by showing the performance of different working regression models that are needed in the augmentation, when they are correctly specified or misspecified. The methods are applied to the LEADER study, a randomized controlled trial that studied cardiovascular safety of treatments in type 2 diabetes patients
Non-Smooth Backfitting for Excess Risk Additive Regression Model with Two Survival Time-Scales
No full textWe consider an extension of Aalen’s additive regression model allowing covariates to have effects that vary on two different time-scales. The two time-scales considered are equal up to a constant that varies for each individual, such as for example follow-up time and age in medical studies or calendar time and age in longitudinal studies. The model has been introduced in Scheike (2001) where it was solved via smoothing techniques. We present a new backfitting 20 algorithm estimating the structured model without having to use smoothing. Estimators of the cumulative regression functions on the two time-scales are suggested by solving local estimating equations jointly on the two time-scales. We provide large sample properties and simultaneous confidence bands. The model is applied to data on myocardial infarction providing a separation of the two effects stemming from time since diagnosis and age
Efficient t0‐year risk regression using the logistic model
No full textIn some clinical studies patient survival beyond a specific point in time, , say, may be of special interest as it may for instance indicate patient cure. To analyze the -year risk for such patients may be accomplished using logistic regression with appropriate weights (IPWCC) that may further be augmented (AIPWCC) to improve efficiency. In this paper, we derive the most efficient estimator for this problem, which is different from the AIPWCC based on the full data efficient influence function. We first give the result for a survival endpoint and then generalize to the competing risk setting. The proposed estimators superior behavior is illustrated using simulations as well as applying it to some real data concerning the survival of blood and marrow transplanted patients.In some clinical studies patient survival beyond a specific point in time, t(0), say, maybe of special interest as it may for instance indicate patient cure. To analyze the t(0)-year risk for such patients may be accomplished using logistic regression with appropriate weights (IPWCC) that may further be augmented (AIPWCC) to improve efficiency. In this paper, we derive the most efficient estimator for this problem, which is different from the AIPWCC based on the full data efficient influence function. We first give the result for a survival endpoint and then generalize to the competing risk setting. The proposed estimators superior behavior is illustrated using simulations as well as applying it to some real data concerning the survival of blood and marrow transplanted patients.</p
CEACAM1 creates a pro-angiogenic tumor microenvironment that supports tumor vessel maturation
No full textWe have studied the effects of carcinoembryonic antigen-related cell adhesion molecule 1 (CEACAM1) on tumor angiogenesis in murine ductal mammary adenocarcinomas. We crossed transgenic mice with whey acidic protein promoter-driven large T-antigen expression (WAP-T mice) with oncogene-induced mammary carcinogenesis with CEA-CAM1null mice, and with Tie2-Ceacam1 transgenics, in which the Tie2 promoter drives endothelial overexpression of CEACAM1 (WAP-T x CEACAM1(endo+) mice), and analyzed tumor vascularization, angiogenesis and vessel maturation in these mice. Using flat-panel volume computed tomography (fpVCT) and histology, we found that WAP-T x CEACAM1(endo+) mice exhibited enhanced tumoral vascularization owing to CEACAM1(+) vessels in the tumor periphery, and increased intratumoral angiogenesis compared with controls. In contrast, vascularization of CEACAM1null/WAP-T-derived tumors was poor, and tumor vessels were dilated, leaky and showed poor pericyte coverage. Consequently, the tumoral vasculature could not be visualized in CEACAM1null/WAP-T mice by fpVCT, and we observed poor organization of the perivascular extracellular matrix (ECM), accompanied by the accumulation of collagen IV-degrading matrix metalloproteinase 9(+) (MMP9(+)) leukocytes and stromal cells. Vascular instability and alterations in ECM structure were accompanied by a significant increase in pulmonary metastases in CEACAM1null/WAP-T mice, whereas only occasional metastases were observed in CEACAM1(+) hosts. In CEACAM1(+) hosts, intratumoral vessels did not express CEACAM1, but they were intact, extensively covered with pericytes and framed by a well-organized perivascular ECM. MMP9(+) accessory cells were largely absent. Orthotopic transplantation of primary WAP-T- and CEACAM1null/WAP-T tumors into all three mouse lines confirmed that a CEACAM1(+) host environment is a prerequisite for productive angiogenic remodeling of the tumor microenvironment. Hence, CEACAM1 expression in the tumor periphery determines the vascular phenotype in a tumor, whereas systemic absence of CEACAM1 interferes with the formation of an organized tumor matrix and intratumoral vessel maturation. Oncogene (2011) 30, 4275-4288; doi: 10.1038/onc.2011.146; published online 2 May 2011German Research Foundation [SPP1190
Anomalous low-temperature saturation effects and negative thermal expansion in the c-axis of highly oriented pyrolytic graphite at the magic angle
No full textWe report a novel T-XRD and Rietveld-refinement investigation of pyrolytic-graphite samples with high degree of graphene-layer-orientation and misfit-rotational-angle of ~ 0.8o in the T-range from 12K to 298K. An anomalous variation of the graphitic c-axis which involves firstly negative-thermal-expansion (from 12K to ~50K), a saturation-effect (from 50K to ~160K) and then a positive expansion (from ~180K to 298K) is evidenced. The reported trend is significantly different with respect to that expected by considering the standard-thermal-expansion α-parameter where no saturation-effect is present. SQUID-magnetometry revealed further presence of superconducting-like hysteresis which resemble those observed by Scheike et al
- …
