How to analyze and interpret recurrent events data in the presence of a terminal event: An application on readmission after colorectal cancer surgery
Corresponding Author
Anaïs Charles-Nelson
Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France
Anaïs Charles-Nelson, Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or INSERM, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France.
Email: [email protected]
Search for more papers by this authorSandrine Katsahian
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France
Search for more papers by this authorCatherine Schramm
Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Search for more papers by this authorCorresponding Author
Anaïs Charles-Nelson
Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France
Anaïs Charles-Nelson, Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or INSERM, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; or Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France.
Email: [email protected]
Search for more papers by this authorSandrine Katsahian
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges-Pompidou, Unité d'Épidémiologie et de Recherche Clinique, INSERM, Centre d'Investigation Clinique 1418, Module Épidémiologie Clinique, Paris, France
Search for more papers by this authorCatherine Schramm
Sorbonne Universités, UPMC Univ Paris 06, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
INSERM, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Université Paris Descartes, Sorbonne Paris Cité, UMRS 1138, Centre de Recherche des Cordeliers, Paris, France
Search for more papers by this authorAbstract
Recurrent events arise when an event occurs many times for a subject. Many models have been developed to analyze these kind of data: the Andersen-Gill's model is one of them as well as the Prentice-William and the Peterson's model, the Wei Lee and Weissfeld's model, or even frailty models, all assuming an independent and noninformative censoring. However, in practice, these assumptions may be violated by the existence of a terminal event that permanently stops the recurrent process (eg, death). Indeed, a patient who experiences an early terminal event is more likely to have a lower number of recurrent events than a patient who experiences a terminal event later. Thus, ignoring terminal events in the analysis may lead to biased results. Many methods have been developed to handle terminal events. In this paper, we describe the existing methods classifying into conditional or marginal methods and compare them in a simulation study to highlight bias in results if an inappropriate method is used, when recurrent events and terminal event are correlated. In addition, we apply the different models on a real dataset to show how results should be interpreted. Finally, we provide recommendations for choosing the appropriate method for analyzing recurrent events in the presence of a terminal event.
REFERENCES
- 1Therneau TM, Grambsch PM. Modeling Survival Data: Extending the Cox Model. New York, NY: Springer Science+Business Media; 2000.
10.1007/978-1-4757-3294-8 Google Scholar
- 2Kalbfleisch JD, Prentice RL. Relative risk (Cox) regression models. In: The Statistical Analysis of Failure Time Data. 2nd ed. Hoboken, NJ: John Wiley & Sons, Inc; 2002: 95-147.
10.1002/9781118032985 Google Scholar
- 3Kelly PJ, Lim LL-Y. Survival analysis for recurrent event data: an application to childhood infectious diseases. Statist Med. 2000; 19(1): 13-33.
10.1002/(SICI)1097-0258(20000115)19:1<13::AID-SIM279>3.0.CO;2-5 CAS PubMed Web of Science® Google Scholar
- 4Cook RJ, Lawless JF. Analysis of repeated events. Stat Methods Med Res. 2002; 11(2): 141-166.
- 5Cai J, Schaubel DE. Marginal means/rates models for multiple type recurrent event data. Lifetime Data Anal. 2004; 10(2): 121-138.
- 6Sinha D, Maiti T, Ibrahim JG, Ouyang B. Current methods for recurrent events data with dependent termination: a Bayesian perspective. J Am Stat Assoc. 2008; 103(482): 866-878.
- 7Cook RJ, Lawless J. The Statistical Analysis of Recurrent Events. New York, NY: Springer Science+Business Media; 2007.
- 8Miloslavsky M, Keles S, van der Laan MJ, Butler S. Recurrent events analysis in the presence of time-dependent covariates and dependent censoring. J Royal Stat Soc Stat Methodol Ser B. 2004; 66(1): 239-257.
- 9Andersen PK, Gill RD. Cox's regression model for counting processes: a large sample study. Ann Stat. 1982; 10(4): 1100-1120.
- 10Liu L, Wolfe RA, Huang X. Shared frailty models for recurrent events and a terminal event. Biometrics. 2004; 60(3): 747-756.
- 11Robins JM, Finkelstein DM. Correcting for noncompliance and dependent censoring in an AIDS Clinical Trial with inverse probability of censoring weighted (IPCW) log-rank tests. Biometrics. 2000; 56(3): 779-788.
- 12Cox DR. Regression models and life-tables. J Royal Stat Soc Stat Methodol Ser B. 1972; 34(2): 187-202.
- 13Breslow N. Covariance analysis of censored survival data. Biometrics. 1974; 30(1): 89-99.
- 14Rondeau V, Mathoulin-Pelissier S, Jacqmin-Gadda H, Brouste V, Soubeyran P. Joint frailty models for recurring events and death using maximum penalized likelihood estimation: application on cancer events. Biostatistics. 2007; 8(4): 708-721.
- 15Rondeau V, Mazroui Y, Gonzalez J. Frailtypack: an R package for the analysis of correlated survival data with frailty models using penalized likelihood estimation or parametrical estimation. J Stat Softw. 2012; 47(4): 1-28.
- 16Zhangsheng Y, Liu L. A joint model of recurrent events and a terminal event with a nonparametric covariate function. Statist Med. 2011; 30(22): 2683-2695.
- 17Liu L, Huang X, Yaroshinsky A, Cormier JN. Joint frailty models for zero-inflated recurrent events in the presence of a terminal event. Biometrics. 2016; 72(1): 204-214.
- 18Rondeau V, Schaffner E, Corbiere F, Gonzalez JR, Mathoulin-Pelissier S. Cure frailty models for survival data: application to recurrences for breast cancer and to hospital readmissions for colorectal cancer. Stat Methods Med Res. 2013; 22(3): 243-260.
- 19Mazroui Y, Mathoulin-Pelissier S, MacGrogan G, Brouste V, Rondeau V. Multivariate frailty models for two types of recurrent events with a dependent terminal event: application to breast cancer data. Biometrical Journal. 2013; 55(6): 866-884.
- 20Belot A, Rondeau V, Remontet L, Giorgi R, CENSUR working survival group. A joint frailty model to estimate the recurrence process and the disease-specific mortality process without needing the cause of death. Statist Med. 2014; 33(18): 3147-3166.
- 21Mazroui Y, Mathoulin-Pelissier S, Soubeyran P, Rondeau V. General joint frailty model for recurrent event data with a dependent terminal event: application to follicular lymphoma data. Statist Med. 2012; 31(11-12): 1162-1176.
- 22Huang X, Liu L. A joint frailty model for survival and gap times between recurrent events. Biometrics. 2007; 63(2): 389-397.
- 23Liu L, Huang X. Joint analysis of correlated repeated measures and recurrent events processes in the presence of death, with application to a study on acquired immune deficiency syndrome. J Royal Stat Soc Appl Stat Ser C. 2009; 58(1): 65-81.
- 24Zeng D, Lin DY. Semiparametric transformation models with random effects for joint analysis of recurrent and terminal events. Biometrics. 2009; 65(3): 746-752.
- 25Ghosh D, Lin DY. Marginal regression models for recurrent and terminal events. Statistica Sina. 2002; 12(3): 663-688.
- 26Huang C-Y, Wang M-C. Joint modeling and estimation for recurrent event processes and failure time data. J Am Stat Assoc. 2004; 99(468): 1153-1165.
- 27Mao L, Lin DY. Semiparametric regression for the weighted composite endpoint of recurrent and terminal events. Biostatistics. 2016; 17(2): 390-403.
- 28Zhao H, Zhou J, Sun L. A marginal additive rates model for recurrent event data with a terminal event. J Commun Stat Theory Methods. 2013; 42(14): 2567-2583.
- 29Zhao X, Zhou J, Sun L. Semiparametric transformation models with time-varying coefficients for recurrent and terminal events. Biometrics. 2011; 67(2): 404-414.
- 30Cook RJ, Lawless JF. Marginal analysis of recurrent events and a terminating event. Statist Med. 1997; 16(8): 911-924.
10.1002/(SICI)1097-0258(19970430)16:8<911::AID-SIM544>3.0.CO;2-I CAS PubMed Web of Science® Google Scholar
- 31Lin DY, Wei LJ, Yang I, Ying Z. Semiparametric regression for the mean and rate functions of recurrent events. J Royal Stat Soc Stat Methodol Ser B. 2000; 62(4): 711-730.
- 32Wang M-C, Qin J, Chiang C-T. Analyzing recurrent event data with informative censoring. J Am Stat Assoc. 2001; 96(455): 1057-1065.
- 33Sun L, Kang F. An additive-multiplicative rates model for recurrent event data with informative terminal event. Lifetime Data Anal. 2013; 19(1): 117-137.
- 34Zhao XB, Zhou X, Wang JL. Semiparametric model for recurrent event data with excess zeros and informative censoring. J Stat Plan Inference. 2012; 142(1): 289-300.
- 35Huang C-Y, Qin J, Wang M-C. Semiparametric analysis for recurrent event data with time-dependent covariates and informative censoring. Biometrics. 2010; 66(1): 39-49.
- 36Zhu L, Sun J, Tong X, Srivastava DK. Regression analysis of multivariate recurrent event data with a dependent terminal event. Lifetime Data Anal. 2010; 16(4): 478-490.
- 37Zhao X, Liu L, Liu Y, Xu W. Analysis of multivariate recurrent event data with time-dependent covariates and informative censoring. Biometrical Journal. 2012; 54(5): 585-599.
- 38Ye Y, Kalbfleisch JD, Schaubel DE. Semiparametric analysis of correlated recurrent and terminal events. Biometrics. 2007; 63(1): 78-87.
- 39Chen C-M, Chuang Y-W, Shen P-S. Two-stage estimation for multivariate recurrent event data with a dependent terminal event. Biometrical Journal. 2015; 57(2): 215-233.
- 40Chen C-M, Shen P-S, Chuang Y-W. The partly Aalen's model for recurrent event data with a dependent terminal event. Statist Med. 2016; 35(2): 268-281.
- 41Aalen O. A model for nonparametric regression analysis of counting processes. In: W Klonecki, A Kozek, W Rosiński, eds. Mathematical Statistics and Probability Theory. New York, NY: Springer; 1980: 1-25.
10.1007/978-1-4615-7397-5_1 Google Scholar
- 42Li QH, Lagakos SW. Use of the Wei–Lin–Weissfeld method for the analysis of a recurring and a terminating event. Statist Med. 1997; 16(8): 925-940.
10.1002/(SICI)1097-0258(19970430)16:8<925::AID-SIM545>3.0.CO;2-2 CAS PubMed Web of Science® Google Scholar
- 43Wei LJ, Lin DY, Weissfeld L. Regression analysis of multivariate incomplete failure time data by modeling marginal distributions. J Am Stat Assoc. 1989; 84(408): 1065-1073.
- 44González JR, Fernandez E, Moreno V, et al. Sex differences in hospital readmission among colorectal cancer patients. J Epidemiol Community Health. 2005; 59(6): 506-511.
- 45Ghosh D, Lin DY. Semiparametric analysis of recurrent events data in the presence of dependent censoring. Biometrics. 2003; 59(4): 877-885.
- 46Hsieh J-J, Ding AA, Wang W. Regression analysis for recurrent events data under dependent censoring. Biometrics. 2011; 67(3): 719-729.
- 47Zhao HZ, Li Y, Sun J. Analyzing panel count data with a dependent observation process and a terminal event. Can J Stat. 2013; 41(1): 174-191.
- 48Rogers JK, Yaroshinsky A, Pocock SJ, Stokar D, Pogoda J. Analysis of recurrent events with an associated informative dropout time: application of the joint frailty model. Statist Med. 2016; 35(13): 2195-2205.
