Adjustment of Fragility Models and Proportional Risks Applied to Diabetic Retinopathy Data
DOI:
https://doi.org/10.33448/rsd-v9i8.5691Keywords:
Survival Analysis; Cox Model; Heterogeneity.Abstract
Survival analysis is currently one of the fastest-growing areas in the field of statistical analysis, with a solid theory for adjusting regression models to study certain phenomena, which have, in their structure, the characteristic of having incomplete observations in the sample called censorship. Although such models can efficiently represent the phenomenon under study in many situations, some of them do not take into account the existence of an unobservable variable present in most studies, called frailty. This fragility denotes the susceptibility of the event to occur by a determined individual or object under investigation. The objective of this work was to show that in situations where frailty is present, the use of models that capture the variability of this variable is more viable for the analysis of these data when compared to conventional models in survival studies. For this purpose, a comparative analysis was performed between these models, adjusted for a set of data from patients diagnosed with Diabetic Retinopathy, and a simulation study was also carried out for the gamma fragility model with different percentages of censorship and heterogeneity. After adjusting the models, it can be seen that the fragility models performed better when compared to the Cox model, with an emphasis on the gamma fragility model, which generated the lowest value for AIC and BIC. The simulation study showed that high censorship rates impair the degree of predictability of the fragility model and that high heterogeneity rates contribute to parameter estimates.
References
Borgan, Ø. (2000). Modeling survival data: extending the cox model. Terry M. Therneau and Patricia M. Grambsch.
Blair, A. L., Hadden, D. R., Weaver, J. A., Archer, D. B., Johnston, P. B., & Maguire, C. J. (1980). The 5-year prognosis for vision in diabetes. The Ulster medical journal, 49(2), 139.
Colosimo, E.A. & Giolo, S. (2006). Análise de sobrevivência aplicada. São Paulo: Editora Edgard Blücher.
Cox, D. R. (1972). Regression models and life‐tables. Journal of the Royal Statistical Society: Series B (Methodological), 34(2), 187-202.
Duchateau, L., & Janssen, P. (2007). The frailty model. Springer Science & Business Media.
Clayton, D. G. (1978). A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika, 65(1), 141-151.
Harrell Jr, Frank E (2019) rms: Regression Modeling Strategies, R package version 5.1-3.
Kaplan, E. L., & Meier, P. (1958). Nonparametric estimation from incomplete observations. Journal of the American statistical association, 53(282), 457-481.
Hess, K., & Gentleman, R. (2010). muhaz: Hazard function estimation in survival analysis. R package version, 1(5), 277.
Klein, J. P., & Moeschberger, M. L. (2006). Survival analysis: techniques for censored and truncated data. Springer Science & Business Media.
Krug, E. G. (2016). Trends in diabetes: sounding the alarm. The Lancet, 387(10027), 1485-1486.
Leasher, J. L., Bourne, R. R., Flaxman, S. R., Jonas, J. B., Keeffe, J., Naidoo, K., ... & Resnikoff, S. (2016). Global estimates on the number of people blind or visually impaired by diabetic retinopathy: a meta-analysis from 1990 to 2010. Diabetes care, 39(9), 1643-1649.
Monaco, J. V., Gorfine, M., & Hsu, L. (2018). General semiparametric shared frailty model: estimation and simulation with frailtySurv. Journal of statistical software, 86.
Moore, D. F. (2016). Applied survival analysis using R. Switzerland: Springer.
Pereira A.S. et al (2018). Methodology of cientific research. [e-Book]. Santa Maria City. UAB / NTE / UFSM Editors. Accessed on: July, 23th, 2020.Available at: https://repositorio.ufsm.br/bitstream/handle/1/15824/Lic_Computacao_Metodologia-Pesquisa-Cientifica.pdf?sequence=1.
Peto, R., & Peto, J. (1972). Asymptotically efficient rank invariant test procedures. Journal of the Royal Statistical Society: Series A (General), 135(2), 185-198.
Prentice, R. L. (1978). Linear rank tests with right censored data. Biometrika, 65(1), 167-179.
Team, R. C. (2013). R: A language and environment for statistical computing.
Therneau, T. M. (2015). A Package for Survival Analysis in S; 2015. Version 2.38. URL: https://CRAN. R-project. org/package= survival.
Vaupel, J. W., Manton, K. G., & Stallard, E. (1979). The impact of heterogeneity in individual frailty on the dynamics of mortality. Demography, 16(3), 439-454.
Yau, J. W., Rogers, S. L., Kawasaki, R., Lamoureux, E. L., Kowalski, J. W., Bek, T., ... & Haffner, S. (2012). Global prevalence and major risk factors of diabetic retinopathy. Diabetes care, 35(3), 556-564.
World Health Organization. (2016). Global report on diabetes: executive summary (No. WHO/NMH/NVI/16.3). World Health Organization.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
