Survival analysis with high-dimensional covariates

Witten, Daniela M.; Tibshirani, Robert
February 2010
Statistical Methods in Medical Research;Feb2010, Vol. 19 Issue 1, p29
Academic Journal
In recent years, breakthroughs in biomedical technology have led to a wealth of data in which the number of features (for instance, genes on which expression measurements are available) exceeds the number of observations (e.g. patients). Sometimes survival outcomes are also available for those same observations. In this case, one might be interested in (a) identifying features that are associated with survival (in a univariate sense), and (b) developing a multivariate model for the relationship between the features and survival that can be used to predict survival in a new observation. Due to the high dimensionality of this data, most classical statistical methods for survival analysis cannot be applied directly. Here, we review a number of methods from the literature that address these two problems.


Related Articles

  • Flexible survival regression modelling. Cortese, Giuliana; Scheike, Thomas H.; Martinussen, Torben // Statistical Methods in Medical Research;Feb2010, Vol. 19 Issue 1, p5 

    Regression 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...

  • Evaluation of EMMPRIN and MMP-2 in the prognosis of primary cutaneous malignant melanoma. Chen, Tiefu; Zhu, Jie // Medical Oncology;Dec2010, Vol. 27 Issue 4, p1185 

    The aim of the study was to investigate whether the presence of matrix metalloproteinase-2 (MMP-2) and its inducer, extracellular matrix metalloproteinase inducer (EMMPRIN), in primary cutaneous malignant melanoma (PCMM) might help to predict patient prognosis. Immunohistochemical staining was...

  • Recent developments in survival analysis. Andersen, Per Kragh // Statistical Methods in Medical Research;Feb2010, Vol. 19 Issue 1, p3 

    The article discusses various reports published within the issue, including one on regression models for survival data, one on the role of Cox model in regression analysis, and one on the application of pseudo-observations in survival analysis.

  • Survival Analysis Part II: Multivariate data analysis - an introduction to concepts and methods. Bradburn, M J; Clark, T G; Love, S B; Altman, D G // British Journal of Cancer;8/4/2003, Vol. 89 Issue 3, p431 

    Studies various statistical models for analyzing and summarizing survival data with reference to hazard and survival functions. Need for multivariate statistical modeling; Estimation of effect of factors that may predict survival; Description of Cox proportional hazards model.

  • Multivariate gene-set testing based on graphical models. Städler, Nicolas; Mukherjee, Sach // Biostatistics;Jan2015, Vol. 16 Issue 1, p47 

    The identification of predefined groups of genes (“gene-sets”) which are differentially expressed between two conditions (“gene-set analysis”, or GSA) is a very popular analysis in bioinformatics. GSA incorporates biological knowledge by aggregating over genes that are...

  • Leisure participation predicts survival:a population-based study in Finland. Hyyppä, Markku T.; Mäki, Juhani; Impivaara, Olli; Aromaa, Arpo // Health Promotion International;Mar2006, Vol. 21 Issue 1, p5 

    The authors study whether leisure participation is an independent predictor of survival over 20 years. Of the nationally representative sample of 8000 adult Finns (Mini-Finland Health Survey), aged ⩾ 30 years, the cohort of 30-59 years (n 5087) was chosen for the Cox proportional survival...

  • A latent variable model for discrete multivariate psychometric waiting times. DOUGLAS, JEFFREY A.; KOSOROK, MICHAEL R.; CHEWNING, BETTY A. // Psychometrika;Mar1999, Vol. 64 Issue 1, p69 

    A version of the discrete proportional hazards model is developed for psychometrical applications. In such applications, a primary covariate that influences failure times is a latent variable representing a psychological construct. The Metropolis-Hastings algorithm is studied as a method for...

  • SURVIVAL IN GASTRIC CANCER PATIENTS: UNIVARIATE AND MULTIVARIATE ANALYSIS. Moghimi-Dehkordi, B.; Safaee, A.; Ghiasi, S.; Zali, M. R. // East African Journal of Public Health;Apr2009 Supplement, p41 

    Background and Aim: Cancer for a long time has been recognized as a fatal disease. Thus it is known to be major health problem in many countries throughout the world. In recent years, cancer morbidity and mortality increased in our country and especially gastric cancer has second order among all...

  • Marginal hazards model for case-cohort studies with multiple disease outcomes. Kang, S.; Cai, J. // Biometrika;Dec2009, Vol. 96 Issue 4, p887 

    Case-cohort study designs are widely used to reduce the cost of large cohort studies while achieving the same goals, especially when the disease rate is low. A key advantage of the case-cohort study design is its capacity to use the same subcohort for several diseases or for several subtypes of...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics