Show simple item record

dc.contributor.authorGeldof, Tine
dc.contributor.authorDusan, Popovic
dc.contributor.authorVan Damme, Nancy
dc.contributor.authorHuys, Isabelle
dc.contributor.authorVan Dyck, Walter
dc.date.accessioned2020-01-08T10:54:10Z
dc.date.available2020-01-08T10:54:10Z
dc.date.issued2020en_US
dc.identifier.doi10.1038/s41598-020-57799-w
dc.identifier.urihttp://hdl.handle.net/20.500.12127/6425
dc.description.abstractNearest Neighbour (NN) propensity score (PS) matching methods are commonly used in pharmacoepidemiology to estimate treatment response using observational data. Unfortunately, there is limited evidence on the optimal approach for accurately estimating binary treatment response and, more so, to estimate its variance. Bootstrapping, although commonly used to accurately estimate variance, is rarely used together with PS matching. In this Monte Carlo simulation-based study, we examined the performance of bootstrapping used in conjunction with PS matching, as opposed to diferent NN matching techniques, on a simulated dataset exhibiting varying levels of real world complexity. Thus, an experimental design was set up that independently varied the proportion of patients treated, the proportion of outcomes censored and the amount of PS matches used. Simulation results were externally validated on a real observational dataset obtained from the Belgian Cancer Registry. We found all investigated PS methods to be stable and concordant, with k-NN matching to be optimally dealing with the censoring problem, typically present in chronic cancer-related datasets, whilst being the least computationally expensive. In contrast, bootstrapping used in conjunction with PS matching, being the most computationally expensive, only showed superior results in small patient populations with long-term largely unobserved treatment efects.
dc.description.sponsorshipThis study has been supported by the Vlerick Business School Academic Research Fund and benefitted from the contribution of Yves Moreau, Department of Electrical Engineering (ESAT) STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics Department, University of Leuven, Belgium. We would also like to thank the Belgian Cancer Registry for providing us with unique access to historical observational data and their research assistance. Financial support for this study was provided entirely by a grant from the Vlerick Business School. The funding agreement ensured the authors' independence in designing the study, interpreting the data and publishing the report.
dc.language.isoenen_US
dc.publisherSpringer Nature Limiteden_US
dc.subjectOncologyen_US
dc.titleNearest neighbour propensity score matching and bootstrapping for estimating binary patient response in oncology: A Monte Carlo simulationen_US
dc.identifier.journalScientific Reports: A Nature Research Journalen_US
dc.source.volume10
dc.source.beginpage964
dc.identifier.eissn2045-2322
vlerick.knowledgedomainOperations & Supply Chain Managementen_US
vlerick.knowledgedomainSpecial Industries : Healthcare Managementen_US
vlerick.typearticleJournal article with impact factoren_US
vlerick.vlerickdepartmentTOMen_US
dc.identifier.vperid176581en_US
dc.identifier.vperid31183en_US


This item appears in the following Collection(s)

Show simple item record