Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa

Simple item page
dc.contributor.authorMasconi, Katya Len_ZA
dc.contributor.authorMatsha, Tandi Een_ZA
dc.contributor.authorErasmus, Rajiv Ten_ZA
dc.contributor.authorKengne, Andre Pen_ZA
dc.date.accessioned2015-11-18T07:11:44Z
dc.date.available2015-11-18T07:11:44Z
dc.date.issued2015en_ZA
dc.description.abstractBACKGROUND: Imputation techniques used to handle missing data are based on the principle of replacement. It is widely advocated that multiple imputation is superior to other imputation methods, however studies have suggested that simple methods for filling missing data can be just as accurate as complex methods. The objective of this study was to implement a number of simple and more complex imputation methods, and assess the effect of these techniques on the performance of undiagnosed diabetes risk prediction models during external validation. METHODS: Data from the Cape Town Bellville-South cohort served as the basis for this study. Imputation methods and models were identified via recent systematic reviews. Models’ discrimination was assessed and compared using C-statistic and non-parametric methods, before and after recalibration through simple intercept adjustment. RESULTS: The study sample consisted of 1256 individuals, of whom 173 were excluded due to previously diagnosed diabetes. Of the final 1083 individuals, 329 (30.4%) had missing data. Family history had the highest proportion of missing data (25%). Imputation of the outcome, undiagnosed diabetes, was highest in stochastic regression imputation (163 individuals). Overall, deletion resulted in the lowest model performances while simple imputation yielded the highest C-statistic for the Cambridge Diabetes Risk model, Kuwaiti Risk model, Omani Diabetes Risk model and Rotterdam Predictive model. Multiple imputation only yielded the highest C-statistic for the Rotterdam Predictive model, which were matched by simpler imputation methods. CONCLUSIONS: Deletion was confirmed as a poor technique for handling missing data. However, despite the emphasized disadvantages of simpler imputation methods, this study showed that implementing these methods results in similar predictive utility for undiagnosed diabetes when compared to multiple imputation.en_ZA
dc.identifier.apacitationMasconi, K. L., Matsha, T. E., Erasmus, R. T., & Kengne, A. P. (2015). Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa. <i>PLoS One</i>, http://hdl.handle.net/11427/15142en_ZA
dc.identifier.chicagocitationMasconi, Katya L, Tandi E Matsha, Rajiv T Erasmus, and Andre P Kengne "Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa." <i>PLoS One</i> (2015) http://hdl.handle.net/11427/15142en_ZA
dc.identifier.citationMasconi, K. L., Matsha, T. E., Erasmus, R. T., & Kengne, A. P. (2015). Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa. PloS one, 10(9), e0139210. doi:10.1371/journal.pone.0139210en_ZA
dc.identifier.ris TY - Journal Article AU - Masconi, Katya L AU - Matsha, Tandi E AU - Erasmus, Rajiv T AU - Kengne, Andre P AB - BACKGROUND: Imputation techniques used to handle missing data are based on the principle of replacement. It is widely advocated that multiple imputation is superior to other imputation methods, however studies have suggested that simple methods for filling missing data can be just as accurate as complex methods. The objective of this study was to implement a number of simple and more complex imputation methods, and assess the effect of these techniques on the performance of undiagnosed diabetes risk prediction models during external validation. METHODS: Data from the Cape Town Bellville-South cohort served as the basis for this study. Imputation methods and models were identified via recent systematic reviews. Models’ discrimination was assessed and compared using C-statistic and non-parametric methods, before and after recalibration through simple intercept adjustment. RESULTS: The study sample consisted of 1256 individuals, of whom 173 were excluded due to previously diagnosed diabetes. Of the final 1083 individuals, 329 (30.4%) had missing data. Family history had the highest proportion of missing data (25%). Imputation of the outcome, undiagnosed diabetes, was highest in stochastic regression imputation (163 individuals). Overall, deletion resulted in the lowest model performances while simple imputation yielded the highest C-statistic for the Cambridge Diabetes Risk model, Kuwaiti Risk model, Omani Diabetes Risk model and Rotterdam Predictive model. Multiple imputation only yielded the highest C-statistic for the Rotterdam Predictive model, which were matched by simpler imputation methods. CONCLUSIONS: Deletion was confirmed as a poor technique for handling missing data. However, despite the emphasized disadvantages of simpler imputation methods, this study showed that implementing these methods results in similar predictive utility for undiagnosed diabetes when compared to multiple imputation. DA - 2015 DB - OpenUCT DO - 10.1371/journal.pone.0139210 DP - University of Cape Town J1 - PLoS One LK - https://open.uct.ac.za PB - University of Cape Town PY - 2015 T1 - Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa TI - Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa UR - http://hdl.handle.net/11427/15142 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/15142
dc.identifier.urihttp://dx.doi.org/10.1371/journal.pone.0139210
dc.identifier.vancouvercitationMasconi KL, Matsha TE, Erasmus RT, Kengne AP. Effects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africa. PLoS One. 2015; http://hdl.handle.net/11427/15142.en_ZA
dc.language.isoengen_ZA
dc.publisherPublic Library of Scienceen_ZA
dc.publisher.departmentDepartment of Medicineen_ZA
dc.publisher.facultyFaculty of Health Sciencesen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.rightsThis is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.en_ZA
dc.rights.holder© 2015 Masconi et alen_ZA
dc.rights.urihttp://creativecommons.org/licenses/by/4.0en_ZA
dc.sourcePLoS Oneen_ZA
dc.source.urihttp://journals.plos.org/plosoneen_ZA
dc.subject.otherDiabetes mellitusen_ZA
dc.subject.otherForecastingen_ZA
dc.subject.otherBlood pressureen_ZA
dc.subject.otherDatabase and informatics methodsen_ZA
dc.subject.otherBody mass indexen_ZA
dc.subject.otherHypertensionen_ZA
dc.subject.otherParenting behavioren_ZA
dc.subject.otherSouth Africaen_ZA
dc.titleEffects of different missing data imputation techniques on the performance of undiagnosed diabetes risk prediction models in a mixed-ancestry population of South Africaen_ZA
dc.typeJournal Articleen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceArticleen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Masconi_Effects_Missing_Data_2015.pdf
Size:
674.68 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Journal Articles