Prostate cancer: net survival and cause-specific survival rates after multiple imputation

BMC Medical Research Methodology

Jean-Pierre Daurès²  Brigitte Trétarre³  Xavier Rébillard¹  Paul Landais²  Faïza Bessaoud³  Adeline Morisot² 

[1] Department of Urology - BeauSoleil Clinic, 119 avenue de Lodève, Montpellier 34070, France;University of Montpellier, Laboratory of Biostatistics, Epidemiology and Public Health (EA2415), 641, avenue du doyen Gaston Giraud, Montpellier Cedex 5 34093, France;Hérault Cancer Registry, 208, rue des Apothicaires, Montpellier Cedex 5 34298, France

关键词: ERSPC;    Cause-specific survival;    Net survival;    Multiple imputation;   

Others  :  1222443
DOI  :  10.1186/s12874-015-0048-4

 received in 2015-03-29, accepted in 2015-07-13,  发布年份 2015

【 摘 要 】

Background

Estimations of survival rates are diverse and the choice of the appropriate method depends on the context. Given the increasing interest in multiple imputation methods, we explored the interest of a multiple imputation approach in the estimation of cause-specific survival, when a subset of causes of death was observed.

Methods

By using European Randomized Study of Screening for Prostate Cancer (ERSPC), 20 multiply imputed datasets were created and analyzed with a Multivariate Imputation by Chained Equation (MICE) algorithm. Then, cause-specific survival was estimated on each dataset with two methods: Kaplan-Meier and competing risks. The two pooled cause-specific survival and confidence intervals were obtained using Rubin’s rules after complementary log-log transformation. Net survival was estimated using Pohar-Perme’s estimator and was compared to pooled cause-specific survival. Finally, a sensitivity analysis was performed to test the robustness of our constructed multiple imputation model.

Results

Cause-specific survival performed better than net survival, since this latter exceeded 100 % for almost the first 2 years of follow-up and after 9 years whereas the cause-specific survival decreased slowly and than stabilized at around 94 % at 9 years. Sensibility study results were satisfactory.

Conclusions

On our basis of prostate cancer data, the results obtained by cause-specific survival after multiple imputation appeared to be better and more realistic than those obtained using net survival.

【 授权许可】

   
2015 Morisot et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

【 参考文献 】

• [1]INCa. ⒸLes cancers en france en 2013. Technical report, Institut National du Cancer.2013. http://www. e-cancer.fr/Expertises-et-publications/Catalogue-despublications/Les-cancers-en-France-Edition-2013 webcite
• [2]Rébillard X, Grosclaude P, Leone N, Velten M, Coureau G, Villers A et al.. Projection de l’incidence et de la mortalité par cancer urologique en France en 2012. Progrès en Urologie. 2013; Suppl. 2:57-66.
• [3]Danieli C, Remontet L, Bossard N, Roche L, Belot A. Estimating net survival: the importance of allowing for informative censoring. Stat Med. 2012; 31(8):775–86. doi:10.1002/sim.4464.
• [4]Roche L, Danieli C, Belot A, Grosclaude P, Bouvier AM, Velten M et al.. Cancer net survival on registry data: Use of the new unbiased pohar-perme estimator and magnitude of the bias with the classical methods. Int J Cancer. 2013; 132(10):2359-369.
• [5]Pohar-Perme M, Stare J, Estève J. On estimation in relative survival. Biometrics. 2012; 68(1):113–20. doi:10.1111/j.1541-0420.2011.01640.x.
• [6]Dickman PW, Lambert PC, Coviello E, Rutherford MJ. Estimating net survival in population-based cancer studies. Int J Cancer. 2013; 133(2):519-21.
• [7]Goetghebeur E, Ryan L. Analysis of competing risks survival data when some failure types are missing. Biometrika. 1995; 82(4):821-33.
• [8]Andersen J, Goetghebeur E, Ryan L. Missing cause of death information in the analysis of survival data. Stat Med. 1996; 15(20):2191-201.
• [9]Lu K, Tsiatis AA. Multiple imputation methods for estimating regression coefficients in the competing risks model with missing cause of failure. Biometrics. 2001; 57(4):1191-7.
• [10]Gao G, Tsiatis AA. Semiparametric estimators for the regression coefficients in the linear transformation competing risks model with missing cause of failure. Biometrika. 2005; 92(4):875-91.
• [11]Lu W, Liang Y. Analysis of competing risks data with missing cause of failure under additive hazards model. Statistica Sinica. 2008; 18(1):219.
• [12]Bakoyannis G, Siannis F, Touloumi G. Modelling competing risks data with missing cause of failure. Stat Med. 2010; 29(30):3172-185.
• [13]Sen A, Banerjee M, Li Y, Noone AM. A bayesian approach to competing risks analysis with masked cause of death. Stat Med. 2010; 29(16):1681-95.
• [14]Lee M, Cronin KA, Gail MH, Dignam JJ, Feuer EJ. Multiple imputation methods for inference on cumulative incidence with missing cause of failure. Biom J. 2011; 53(6):974–3. doi:10.1002/bimj.201000175.
• [15]Lee M, Dignam JJ, Han J. Multiple imputation methods for nonparametric inference on cumulative incidence with missing cause of failure. Stat Med. 2014; 33:4605–626. doi:10.1002/sim.6258.
• [16]Nicolaie M, van Houwelingen H, Putter H. Vertical modeling: analysis of competing risks data with missing causes of failure. Stat Methods Med Res. 2011. doi:10.1177/0962280211432067.
• [17]Moreno-Betancur M, Latouche A. Regression modeling of the cumulative incidence function with missing causes of failure using pseudo-values. Stat Med. 2013; 32(18):3206-23.
• [18]Kaplan EL, Meier P. Nonparametric estimation from incomplete observations. J Am Stat Assoc. 1958; 53(282):457-81.
• [19]Schröder F, Denis L, Roobol M. The story of the European randomized study of screening for prostate cancer. BJU Int. 2003; 92(s2):1-13.
• [20]De Koning H, Blom J, Merkelbach J, Raaijmakers R, Verhaegen H, Van Vliet P et al.. Determining the cause of death in randomized screening trial (s) for prostate cancer. BJU Int. 2003; 92(s2):71-8.
• [21]Otto S, van Leeuwen P, Hoekstra J, Merckelbach J, Blom J, Schröder F et al.. Blinded and uniform causes of death verification in cancer screening: A major influence on the outcome of a prostate cancer screening trial? Eur J Cancer. 2010; 46(17):3061-067.
• [22]D’Amico AV, Whittington R, Malkowicz SB, Schultz D, Blank K, Broderick GA et al.. Biochemical outcome after radical prostatectomy, external beam radiation therapy, or interstitial radiation therapy for clinically localized prostate cancer. J Am Med Assoc. 1998; 280(11):969-74.
• [23]Rubin DB. Inference and missing data. Biometrika. 1976; 63(3):581-92.
• [24]Enders CK. Applied Missing Data Analysis. Guilford Press, New York; 2010.
• [25]Dixon WJ. BMDP Statistical Software Manual. University of California Press, Berkeley; 1988.
• [26]Little RJ. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988; 83(404):1198-202.
• [27]Van Buuren S, Oudshoorn K. Flexible multivariate imputation by mice. TNO Prevention Center, Leiden, The Netherlands; 1999.
• [28]Van Buuren S, Oudshoorn C. Multivariate imputation by chained equations: MICE V1. 0 users’s manual. Technical report, TNO Prevention and Health, Public Health, Leiden; 2000.
• [29]Van Buuren S, Brand JP, Groothuis-Oudshoorn C, Rubin DB. Fully conditional specification in multivariate imputation. J Stat Compu Simul. 2006; 76(12):1049-1064.
• [30]R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria; 2013.
• [31]Van Buuren S, Groothuis-Oudshoorn K. mice: Multivariate imputation by chained equations in r. J Stat Softw. 2011; 45(3):1-67.
• [32]Van Buuren S. Flexible Imputation of Missing Data. Interdisciplinary Statistics Series. Boca Raton: Chapman & Hall/CRC; 2012. http://books. google.fr/books?id=M89TDSml-FoC webcite
• [33]White IR, Royston P. Imputing missing covariate values for the cox model. Stat Med. 2009; 28(15):1982-98.
• [34]Brand JP. Development, implementation and evaluation of multiple imputation strategies for the statistical analysis of incomplete data sets. PhD thesis, Erasmus University, Rotterdam; 1999.
• [35]Von Hippel PT. How to impute interactions, squares, and other transformed variables. Sociol Methodol. 2009; 39(1):265-91.
• [36]Pohar Perme M. Relsurv : Relative Survival. 2013. R package version 2.0-4. http://CRAN. R-project.org/package=relsurv webcite
• [37]Therneau TM. A Package for Survival Analysis in S. 2014. R package version 2.37-7. http://CRAN. R-project.org/package=survival webcite
• [38]Gray B. Cmprsk: Subdistribution Analysis of Competing Risks. 2014. R package version 2.2-7. http://CRAN. R-project.org/package=cmprsk webcite
• [39]Marshall A, Altman DG, Holder RL, Royston P. Combining estimates of interest in prognostic modelling studies after multiple imputation: current practice and guidelines. BMC Med Res Methodol. 2009; 9(1):57. doi:10.1186/1471-2288-9-57.
• [40]Rubin DB. Multiple Imputation for Nonresponse in Surveys. Wiley Classics Library. John Wiley & Sons, New York; 1987.
• [41]Collet D. Modelling Survival Data in Medical Research. Chapman & Hall/CRC, Boca Raton; 2003.
• [42]Gelman A, King G, Liu C. Not asked and not answered: Multiple imputation for multiple surveys. J Am Stat Assoc. 1998; 93(443):846-57.
• [43]Gelman A, Carlin JB, Stern HS, Rubin DB. Bayesian Data Analysis. Chapman & Hall/CRC, London; 2004.
• [44]Su YS, Yajima M, Gelman AE, Hill J. Multiple imputation with diagnostics (mi) in r: opening windows into the black box. J Stat Softw. 2011; 45(2):1-31.