Literature DB >> 29078093

Comparison of variable selection methods for high-dimensional survival data with competing events.

Julia Gilhodes1, Christophe Zemmour2, Soufiane Ajana1, Alejandra Martinez3, Jean-Pierre Delord4, Eve Leconte5, Jean-Marie Boher2, Thomas Filleron6.   

Abstract

BACKGROUND: In the era of personalized medicine, it's primordial to identify gene signatures for each event type in the context of competing risks in order to improve risk stratification and treatment strategy. Until recently, little attention was paid to the performance of high-dimensional selection in deriving molecular signatures in this context. In this paper, we investigate the performance of two selection methods developed in the framework of high-dimensional data and competing risks: Random survival forest and a boosting approach for fitting proportional subdistribution hazards models.
METHODS: Using data from bladder cancer patients (GSE5479) and simulated datasets, stability and prognosis performance of the two methods were evaluated using a resampling strategy. For each sample, the data set was split into 100 training and validation sets. Molecular signatures were developed in the training sets by the two selection methods and then applied on the corresponding validation sets.
RESULTS: Random survival forest and boosting approach have comparable performance for the prediction of survival data, with few selected genes in common. Nevertheless, many different sets of genes are identified by the resampling approach, with a very small frequency of genes occurrence among the signatures. Also, the smaller the training sample size, the lower is the stability of the signatures.
CONCLUSION: Random survival forest and boosting approach give good predictive performance but gene signatures are very unstable. Further works are needed to propose adequate strategies for the analysis of high-dimensional data in the context of competing risks.
Copyright © 2017 Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Boosting; Competing risks; High-dimensional data; Random survival forest; Stability; Variable selection

Mesh:

Year:  2017        PMID: 29078093     DOI: 10.1016/j.compbiomed.2017.10.021

Source DB:  PubMed          Journal:  Comput Biol Med        ISSN: 0010-4825            Impact factor:   4.589


  5 in total

1.  Prognostic gene expression signatures of breast cancer are lacking a sensible biological meaning.

Authors:  Kalifa Manjang; Shailesh Tripathi; Olli Yli-Harja; Matthias Dehmer; Galina Glazko; Frank Emmert-Streib
Journal:  Sci Rep       Date:  2021-01-08       Impact factor: 4.379

2.  Variable selection with Group LASSO approach: Application to Cox regression with frailty model.

Authors:  Jean Claude Utazirubanda; Tomas Leon; Papa Ngom
Journal:  Commun Stat Simul Comput       Date:  2018-02-28       Impact factor: 1.118

3.  Variable selection methods for predicting clinical outcomes following allogeneic hematopoietic cell transplantation.

Authors:  Chloé Pasin; Ryan H Moy; Ran Reshef; Andrew J Yates
Journal:  Sci Rep       Date:  2021-02-05       Impact factor: 4.379

4.  Comparison of Variable Selection Methods for Time-to-Event Data in High-Dimensional Settings.

Authors:  Julia Gilhodes; Florence Dalenc; Jocelyn Gal; Christophe Zemmour; Eve Leconte; Jean-Marie Boher; Thomas Filleron
Journal:  Comput Math Methods Med       Date:  2020-07-01       Impact factor: 2.238

5.  Regularized Weighted Nonparametric Likelihood Approach for High-Dimension Sparse Subdistribution Hazards Model for Competing Risk Data.

Authors:  Leili Tapak; Michael R Kosorok; Majid Sadeghifar; Omid Hamidi; Saeid Afshar; Hassan Doosti
Journal:  Comput Math Methods Med       Date:  2021-09-19       Impact factor: 2.238

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.