A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data

Simple item page
dc.contributor.authorNasejje, Justine B
dc.contributor.authorMwambi, Henry
dc.contributor.authorSabur, Natasha F
dc.contributor.authorLesosky, Maia
dc.date.accessioned2021-10-08T06:54:42Z
dc.date.available2021-10-08T06:54:42Z
dc.date.issued2017
dc.description.abstractAbstract Background Random survival forest (RSF) models have been identified as alternative methods to the Cox proportional hazards model in analysing time-to-event data. These methods, however, have been criticised for the bias that results from favouring covariates with many split-points and hence conditional inference forests for time-to-event data have been suggested. Conditional inference forests (CIF) are known to correct the bias in RSF models by separating the procedure for the best covariate to split on from that of the best split point search for the selected covariate. Methods In this study, we compare the random survival forest model to the conditional inference model (CIF) using twenty-two simulated time-to-event datasets. We also analysed two real time-to-event datasets. The first dataset is based on the survival of children under-five years of age in Uganda and it consists of categorical covariates with most of them having more than two levels (many split-points). The second dataset is based on the survival of patients with extremely drug resistant tuberculosis (XDR TB) which consists of mainly categorical covariates with two levels (few split-points). Results The study findings indicate that the conditional inference forest model is superior to random survival forest models in analysing time-to-event data that consists of covariates with many split-points based on the values of the bootstrap cross-validated estimates for integrated Brier scores. However, conditional inference forests perform comparably similar to random survival forests models in analysing time-to-event data consisting of covariates with fewer split-points. Conclusion Although survival forests are promising methods in analysing time-to-event data, it is important to identify the best forest model for analysis based on the nature of covariates of the dataset in question.
dc.identifier.apacitationNasejje, J. B., Mwambi, H., Sabur, N. F., & Lesosky, M. (2017). A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data. <i>BMC Medical Research Methodology</i>, 17(1), 174 - 177. http://hdl.handle.net/11427/34315en_ZA
dc.identifier.chicagocitationNasejje, Justine B, Henry Mwambi, Natasha F Sabur, and Maia Lesosky "A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data." <i>BMC Medical Research Methodology</i> 17, 1. (2017): 174 - 177. http://hdl.handle.net/11427/34315en_ZA
dc.identifier.citationNasejje, J.B., Mwambi, H., Sabur, N.F. & Lesosky, M. 2017. A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data. <i>BMC Medical Research Methodology.</i> 17(1):174 - 177. http://hdl.handle.net/11427/34315en_ZA
dc.identifier.issn1471-2288
dc.identifier.ris TY - Journal Article AU - Nasejje, Justine B AU - Mwambi, Henry AU - Sabur, Natasha F AU - Lesosky, Maia AB - Abstract Background Random survival forest (RSF) models have been identified as alternative methods to the Cox proportional hazards model in analysing time-to-event data. These methods, however, have been criticised for the bias that results from favouring covariates with many split-points and hence conditional inference forests for time-to-event data have been suggested. Conditional inference forests (CIF) are known to correct the bias in RSF models by separating the procedure for the best covariate to split on from that of the best split point search for the selected covariate. Methods In this study, we compare the random survival forest model to the conditional inference model (CIF) using twenty-two simulated time-to-event datasets. We also analysed two real time-to-event datasets. The first dataset is based on the survival of children under-five years of age in Uganda and it consists of categorical covariates with most of them having more than two levels (many split-points). The second dataset is based on the survival of patients with extremely drug resistant tuberculosis (XDR TB) which consists of mainly categorical covariates with two levels (few split-points). Results The study findings indicate that the conditional inference forest model is superior to random survival forest models in analysing time-to-event data that consists of covariates with many split-points based on the values of the bootstrap cross-validated estimates for integrated Brier scores. However, conditional inference forests perform comparably similar to random survival forests models in analysing time-to-event data consisting of covariates with fewer split-points. Conclusion Although survival forests are promising methods in analysing time-to-event data, it is important to identify the best forest model for analysis based on the nature of covariates of the dataset in question. DA - 2017 DB - OpenUCT DP - University of Cape Town IS - 1 J1 - BMC Medical Research Methodology LK - https://open.uct.ac.za PY - 2017 SM - 1471-2288 T1 - A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data TI - A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data UR - http://hdl.handle.net/11427/34315 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/34315
dc.identifier.vancouvercitationNasejje JB, Mwambi H, Sabur NF, Lesosky M. A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data. BMC Medical Research Methodology. 2017;17(1):174 - 177. http://hdl.handle.net/11427/34315.en_ZA
dc.language.isoeng
dc.publisher.departmentDepartment of Medicine
dc.publisher.facultyFaculty of Health Sciences
dc.sourceBMC Medical Research Methodology
dc.source.journalissue1
dc.source.journalvolume17
dc.source.pagination174 - 177
dc.source.urihttps://dx.doi.org/10.1186/s12874-017-0383-8
dc.subject.otherConditional inference forests
dc.subject.otherRandom survival forests
dc.subject.otherSplit-points
dc.subject.otherSurvival analysis
dc.subject.otherSurvival trees
dc.subject.otherAlgorithms
dc.subject.otherChild
dc.subject.otherDrug Resistance
dc.subject.otherHumans
dc.subject.otherModels, Statistical
dc.subject.otherProportional Hazards Models
dc.subject.otherSurvival Analysis
dc.subject.otherTuberculosis
dc.subject.otherUganda
dc.titleA comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data
dc.typeJournal Article
uct.type.publicationResearch
uct.type.resourceJournal Article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
NasejjeJustineB_A_comparisoncon_2017.pdf
Size:
1.59 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Journal Articles