Adapting SIMEX to correct for bias due to interval-censored outcomes in survival analysis with time-varying exposure.
Cox model
pharmacoepidemiology
simulations
time-varying covariates
Journal
Biometrical journal. Biometrische Zeitschrift
ISSN: 1521-4036
Titre abrégé: Biom J
Pays: Germany
ID NLM: 7708048
Informations de publication
Date de publication:
Dec 2022
Dec 2022
Historique:
revised:
16
05
2022
received:
10
01
2021
accepted:
28
05
2022
pubmed:
7
9
2022
medline:
15
12
2022
entrez:
6
9
2022
Statut:
ppublish
Résumé
Many clinical and epidemiological applications of survival analysis focus on interval-censored events that can be ascertained only at discrete times of clinic visits. This implies that the values of time-varying covariates are not correctly aligned with the true, unknown event times, inducing a bias in the estimated associations. To address this issue, we adapted the simulation-extrapolation (SIMEX) methodology, based on assessing how the estimates change with the artificially increased time between clinic visits. We propose diagnostics to choose the extrapolating function. In simulations, the SIMEX-corrected estimates reduced considerably the bias to the null and generally yielded a better bias/variance trade-off than conventional estimates. In a real-life pharmacoepidemiological application, the proposed method increased by 27% the excess hazard of the estimated association between a time-varying exposure, representing the 2-year cumulative duration of past use of a hypertensive medication, and the hazard of nonmelanoma skin cancer (interval-censored events). These simulation-based and real-life results suggest that the proposed SIMEX-based correction may help improve the accuracy of estimated associations between time-varying exposures and the hazard of interval-censored events in large cohort studies where the events are recorded only at relatively sparse times of clinic visits/assessments. However, these advantages may be less certain for smaller studies and/or weak associations.
Identifiants
pubmed: 36065586
doi: 10.1002/bimj.202100013
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1467-1485Subventions
Organisme : Natural Sciences and Engineering Research Council of Canada
ID : 228203
Organisme : CIHR
ID : PJT-148946
Pays : Canada
Organisme : CIHR
ID : TD3-137716
Pays : Canada
Organisme : CIHR
ID : PJT-148946
Pays : Canada
Organisme : CIHR
ID : TD3-137716
Pays : Canada
Informations de copyright
© 2022 Wiley-VCH GmbH.
Références
Abrahamowicz, M., Beauchamp, M. E., & Sylvestre, M. P. (2012). Comparison of alternative models for linking drug exposure with adverse effects. Statistics in Medicine, 31, 1014-1030. https://doi.org/10.1002/sim.4343
Abrahamowicz, M., & Tamblyn, R. (2005). Drug utilization patterns. In P. Armitage & T. Colton (Eds.), Encyclopedia of biostatistics, 2nd edition, vol 4, (pp. 1533-1553). Wiley.
Ahn, S., Lim, J., Paik, M. C., Sacco, R. L., & Elkind, M. S. (2018). Cox model with interval-censored covariate in cohort studies. Biometrical Journal, 60, 797-814. https://doi.org/10.1002/bimj.201700090
Andersen, P. K., & Liestol, K. (2003). Attenuation caused by infrequently updated covariates in survival analysis. Biostatistics, 4, 633-649. https://doi.org/10.1093/biostatistics/4.4.633
Andersen, P. K., Pohar Perme, M., van Houwelingen, H. C., Cook, R. J., Joly, P., Martinussen, T., Taylor, J. M. G., Abrahamowicz, M., & Therneau, T. M. (2021). Analysis of time-to-event for observational studies: Guidance to the use of intensity models. Statistics in Medicine, 40, 185-211. https://doi.org/10.1002/sim.8757
Avorn, J. (2007). In defense of pharmacoepidemiology-Embracing the yin and yan of drug research. New England Journal of Medicine, 357, 2219-2221. https://doi.org/10.1056/NEJMp0706892
Bacchetti, P., & Quale, C. (2002). Generalized additive models with interval-censored data and time-varying covariates: Application to human immunodeficiency virus infection in hemophiliacs. Biometrics, 58, 443-447. https://doi.org/10.1111/j.0006-341X.2002.00443.x
Blakely, K. M., Drucker, A. M., & Rosen, C. F. (2019). Drug-induced photosensitivity-an update: Culprit drugs, prevention and management. Drug Safety, 42, 827-847. https://doi.org/10.1007/s40264-019-00806-5
Boulesteix, A. L., Binder, H., Abrahamowicz, M., & Sauerbrei, W. (2018). On the necessity and design of studies comparing statistical methods. Biometrical Journal, 60, 216-218. https://doi.org/10.1002/bimj.201700129
Brenner, H., & Blettner, M. (1997). Controlling for continuous confounders in epidemiologic research. Epidemiology, 8, 429-434. https://doi.org/10.1097/00001648-199707000-00014
Brookhart, M. A., Wang, P. S., Solomon, D. H., & Schneeweiss, S. (2006). Evaluating short-term drug effects using a physician-specific prescribing preference as an instrumental variable. Epidemiology, 17, 268-275. https://doi.org/10.1097/01.ede.0000193606.58671.c5
Campbell, K. R., Juarez-Colunga, E., Grunwald, G. K., Cooper, J., Davis, S., & Gralla, J. (2019). Comparison of a time-varying covariate model and a joint model of time-to-event outcomes in the presence of measurement error and interval censoring: Application to kidney transplantation. BMC Medical Research Methodology, 19, 130. https://doi.org/10.1186/s12874-019-0773-1
Carroll, R. J., Ruppert, D., Stefanski, L. A., & Crainiceanu, C. M. (2006). Measurement error in nonlinear models: A modern perspective. CRC Press.
Chen, E. B., & Cook, R. J. (2003). Regression modeling with recurrent events and time-dependent interval-censored marker data. Lifetime Data Analysis, 9, 275-291. https://doi.org/10.1023/A:1025888820636
Chiang, Y. K., Hardy, R. J., Hawkins, C. M., & Kapadia, A. S. (1989). An illness-death process with time-dependent covariates. Biometrics, 45, 669-681. https://doi.org/10.2307/2531509
Clark, D. E., Doolittle, P. C., Winchell, R. J., & Betensky, R. A. (2014). The effect of hospital care on early survival after penetrating trauma. Injury Epidemiology, 1, 24. https://doi.org/10.1186/s40621-014-0024-1
Clark, D. E., Winchell, R. J., & Betensky, R. A. (2013). Estimating the effect of emergency care on early survival after traffic crashes. Accident Analysis & Prevention, 60, 141-147.
Cook, J. R., & Stefanski, L. A. (1994). Simulation-extrapolation estimation in parametric measurement error models. Journal of the American Statistical Association, 89, 1314-1328. https://doi.org/10.1080/01621459.1994.10476871
Cox, D. R. (1972). Regression models and life tables (with discussion). Journal of the Royal Statistical Society, Series B, 34, 187-220.
Danieli, C., Cohen, S., Liu, A., Pilote, L., Guo, L., Beauchamp, M. E., Marelli, A. J., & Abrahamowicz, M. (2019). Flexible modeling of the association between cumulative exposure to low-dose ionizing radiation from cardiac procedures and risk of cancer in adults with congenital heart disease. American Journal of Epidemiology, 188, 1552-1562. https://doi.org/10.1093/aje/kwz114
Esteve, J., Benhamou, E., Croasdale, M., & Raymond, L. (1990). Relative survival and the estimation of net survival: Elements for further discussion. Statistics in Medicine, 9, 529-538. https://doi.org/10.1002/sim.4780090506
Eworuke, E., Haug, N., Bradley, M., Cosgrove, A., Zhang, T., Dee, E. C., Adimadhyam, S., Petrone, A., Lee, H., Woodworth, T., & Toh, S. (2021). Risk of nonmelanoma skin cancer in association with the use of hydrochlorothiazide-containing products in the United States. JNCI Cancer Spectrum, 5, kab009. https://doi.org/10.1093/jncics/pkab009
Finkelstein, D. M. (1986). A proportional hazards model for interval-censored failure time data. Biometrics, 42, 845-854. https://doi.org/10.2307/2530698
Franklin, J. M., Schneeweiss, S., Polinski, J. M., & Rassen, J. A. (2014). Plasmode simulation for the evaluation of pharmacoepidemiologic methods in complex healthcare databases. Computational Statistics and Data Analysis, 72, 219-226. https://doi.org/10.1016/j.csda.2013.10.018
Friedman, O., McAlister, F. A., Yun, L., Campbell, N. R., & Tu, K. (2010). Antihypertensive drug persistence and compliance among newly treated elderly hypertensives in Ontario. American Journal of Medicine, 123, 173-181. https://doi.org/10.1016/j.amjmed.2009.08.008
Gee, M. E., Campbell, N. R., Gwadry-Sridhar, F., Nolan, R. P., Kaczorowski, J., Bienek, A., Robitaille, C., Joffres, M., Dai, S., & Walker, R. L. (2012). Antihypertensive medication use, adherence, stops, and starts in Canadians with hypertension. Canadian Journal of Cardiology, 28, 383-389. https://doi.org/10.1016/j.cjca.2012.01.014
Gentleman, R., & Geyer, C. J. (1994). Maximum likelihood for interval censored data: Consistency and computation. Biometrika, 81, 618-623. https://doi.org/10.1093/biomet/81.3.618
Grambsch, P. M., & Therneau, T. M. (1994). Proportional hazards tests and diagnostics based on weighted residuals. Biometrics, 81, 515-526. https://doi.org/10.1093/biomet/81.3.515
Greene, W. F., & Cai, J. (2004). Measurement error in covariates in the marginal hazards model for multivariate failure time data. Biometrics, 60, 987-996. https://doi.org/10.1111/j.0006-341X.2004.00254.x
He, W., Yi, G. Y., & Xiong, J. (2007). Accelerated failure time models with covariates subject to measurement error. Statistics in Medicine, 26, 4817-4832. https://doi.org/10.1002/sim.2892
Hernan, M. A., Brumback, B., & Robins, J. M. (2000). Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology, 11, 561-570. https://doi.org/10.1097/00001648-200009000-00012
Ionescu-Ittu, R., Delaney, J. A., & Abrahamowicz, M. (2009). Bias-variance trade-off in pharmacoepidemiological studies using physician-preference-based instrumental variables: A simulation study. Pharmacoepidemiology and Drug Safety, 18, 562-571. https://doi.org/10.1002/pds.1757
Kaae, J., Boyd, H. A., Hansen, A. V., Wulf, H. C., Wohlfahrt, J., & Melbye, M. (2010). Photosensitizing medication use and risk of skin cancer. Cancer Epidemiology, Biomarkers & Prevention, 19, 2942-2949.
Kooperberg, C., & Clarkson, D. B. (1997). Hazard regression with interval-censored data. Biometrics, 53, 1485-1494. https://doi.org/10.2307/2533514
Kooperberg, C., & Stone, C. J. (1992). Logspline density estimation for censored data. Journal of Computational and Graphical Statistics, 1, 301-328.
Kuchenhoff, H., Mwalili, S. M., & Lesaffre, E. (2006). A general method for dealing with misclassification in regression: The misclassification SIMEX. Biometrics, 62, 85-96. https://doi.org/10.1111/j.1541-0420.2005.00396.x
Kyle, R. P., Moodie, E. E. M., & Abrahamowicz, M. (2016). Correcting for measurement error in time-varying covariates in marginal structural models. American Journal of Epidemiology, 184, 249-258. https://doi.org/10.1093/aje/kww068
Le Teuff, G., Abrahamowicz, M., Bolard, P., & Quantin, C. (2005). Comparison of Cox's and relative survival models when estimating the effects of prognostic factors on disease-specific mortality: A simulation study under proportional excess hazards. Statistics in Medicine, 24, 3887-3909. https://doi.org/10.1002/sim.2392
Lindsey, J. C., & Ryan, L. M. (1998). Tutorial in biostatistics methods for interval-censored data. Statistics in Medicine, 17, 219-238. https://doi.org/10.1002/(SICI)1097-0258(19980130)17:2%3c219::AID-SIM735%3e3.0.CO;2-O
Lomas, A., Leonardi-Bee, J., & Bath-Hextall, F. (2012). A systematic review of worldwide incidence of nonmelanoma skin cancer. British Journal of Dermatology, 166, 1069-1080. https://doi.org/10.1111/j.1365-2133.2012.10830.x
MacMahon, S., & Collins, R. (2001). Reliable assessment of the effects of treatment on mortality and major morbidity, II: Observational studies. Lancet, 357, 455-462. https://doi.org/10.1016/S0140-6736(00)04017-4
Makhzoumi, Z. H., & Arron, S. T. (2013). Photosensitizing agents and the risk of non-melanoma skin cancer: A population-based case-control study. Journal of Investigative Dermatology, 133, 1922-1923. https://doi.org/10.1038/jid.2013.144
Morris, T. P., White, I. R., & Crowther, M. J. (2019). Using simulation studies to evaluate statistical methods. Statistics in Medicine, 38, 2074-2102. https://doi.org/10.1002/sim.8086
Oh, E. J., Shepherd, B. E., Lumley, T., & Shaw, P. A. (2018). Considerations for analysis of time-to-event outcomes measured with error: Bias and correction with SIMEX. Statistics in Medicine, 37, 1276-1289. https://doi.org/10.1002/sim.7554
Oller, R., & Gomez, M. G. (2020). A nonparametric test for the association between longitudinal covariates and censored survival data. Biostatistics, 21, 727-742. https://doi.org/10.1093/biostatistics/kxz002
Patorno, E., Garry, E. M., Patrick, A. R., Schneeweiss, S., Gillet, V. G., Zorina, O., Bartels, D. B., & Seeger, J. D. (2015). Addressing limitations in observational studies of the association between glucose-lowering medications and all-cause mortality: A review. Drug Safety, 38, 295-310. https://doi.org/10.1007/s40264-015-0280-1
Pazzagli, L., Linder, M., Zhang, M., Vago, E., Stang, P., Myers, D., Andersen, M., & Bahmanyar, S. (2018). Methods for time-varying exposure related problems in pharmacoepidemiology: An overview. Pharmacoepidemiology and Drug Safety, 27, 148-160. https://doi.org/10.1002/pds.4372
Pottegard, A., Pedersen, S. A., Schmidt, S. A. J., Lee, C. N., Hsu, C. K., Liao, T. C., Shao, S. C., & Lai, E. C. (2019). Use of hydrochlorothiazide and risk of skin cancer: A nationwide Taiwanese case-control study. British Journal of Cancer, 121, 973-978. https://doi.org/10.1038/s41416-019-0613-4
Ray, W. A. (2005). Observational studies of drugs and mortality. New England Journal of Medicine, 353, 2319-2321. https://doi.org/10.1056/NEJMp058267
Richardson, D. B., & Ashmore, J. P. (2005). Investigating time patterns of variation in radiation cancer associations. Occupational and Environmental Medicine, 62, 551-558. https://doi.org/10.1136/oem.2004.017368
Schoenfeld, D. A., Rajicic, N., Ficociello, L. H., & Finkelstein, D. M. (2011). A test for the relationship between a time-varying marker and both recovery and progression with missing data. Statistics in Medicine, 30, 718-724. https://doi.org/10.1002/sim.4145
Seaman, S. R., & Bird, S. M. (2001). Proportional hazards model for interval-censored failure times and time-dependent covariates: Application to hazard of HIV infection of injecting drug users in prison. Statistics in Medicine, 20, 1855-1870. https://doi.org/10.1002/sim.809
Sparling, Y. H., Younes, N., Lachin, J. M., & Bautista, O. M. (2006). Parametric survival models for interval-censored data with time-dependent covariates. Biostatistics, 7, 599-614. https://doi.org/10.1093/biostatistics/kxj028
Stefanski, L. A., & Cook, J. R. (1995). Simulation extrapolation: The measurement error jackknife. Journal of the American Statistical Association, 90, 1247-1256. https://doi.org/10.1080/01621459.1995.10476629
Suissa, S. (2008). Immortal time bias in pharmacoepidemiology. American Journal of Epidemiology, 167, 492-499. https://doi.org/10.1093/aje/kwm324
Sun, X., Li, X., Chen, C., & Song, Y. (2013). A review of statistical issues with progression-free survival as an interval-censored time-to-event endpoint. Journal of Biopharmaceutical Statistics, 23, 986-1003. https://doi.org/10.1080/10543406.2013.813524
Sylvestre, M. P., & Abrahamowicz, M. (2008). Comparison of algorithms to generate event times conditional on time-dependent covariates. Statistics in Medicine, 27, 2618-2634. https://doi.org/10.1002/sim.3092
Sylvestre, M. P., & Abrahamowicz, M. (2009). Flexible modeling of the cumulative effects of time-dependent exposures on the hazard. Statistics in Medicine, 28, 3437-3453. https://doi.org/10.1002/sim.3701
Sylvestre, M. P., Evans, T., MacKenzie, T., & Abrahamowicz, M. (2015). PermAlgo: Permutational algorithm to generate event times conditional on a covariate matrix including time-dependent covariates. R package, version 1.1. https://CRAN.R-project.org/package=PermAlgo
Turnbull, B. W. (1976). The empirical distribution function with arbitrarily grouped, censored and truncated data. Journal of the Royal Statistical Society, Series B, 38, 290-295.
Wang, Y., Beauchamp, M. E., & Abrahamowicz, M. (2020). Nonlinear and time-dependent effects of sparsely measured continuous time-varying covariates in time-to-event analysis. Biometrical Journal, 62, 492-515. https://doi.org/10.1002/bimj.201900042
Xiao, Y., Moodie, E. E. M., & Abrahamowicz, M. (2013). Comparison of approaches to weight truncation for marginal structural Cox models. Epidemiologic Methods, 2, 1-20. https://doi.org/10.1515/em-2012-0006
Zhan, Z., de Bock, G. H., Wiggers, T., & van den Heuvel, E. (2016). The analysis of terminal endpoint events in stepped wedge designs. Statistics in Medicine, 35, 4413-4426. https://doi.org/10.1002/sim.7004
Zhang, J., He, W., & Li, H. (2014). A semiparametric approach for accelerated failure time models with covariates subject to measurement error. Communications in Statistics - Simulation and Computation, 43, 329-341. https://doi.org/10.1080/03610918.2012.703279
Zhang, Z., & Sun, J. (2010). Interval censoring. Statistical Methods in Medical Research, 19, 53-70. https://doi.org/10.1177/0962280209105023
Zhou, Z., Rahme, E., Abrahamowicz, M., & Pilote, L. (2005). Survival bias associated with time-to-treatment initiation in drug effectiveness evaluation: A comparison of methods. American Journal of Epidemiology, 162, 1016-1023. https://doi.org/10.1093/aje/kwi307