Long-term survivor models have been extensively used for modelling time-to-event data with a significant proportion of patients who do not experience poor outcome. In this paper, we propose a new long-term survivor hazard model, which accommodates comprehensive families of cure rate models as particular cases, including modified Weibull, exponentiated Weibull, Weibull, exponential and Rayleigh distribution, among others. The maximum likelihood estimation procedure is presented. A simulation study evaluates bias and mean square error of the considered estimation procedure as well as the coverage probabilities of the parameters asymptotic and bootstrap confidence intervals. A real Brazilian dataset on breast cancer illustrates the methodology. From the practical point of view, under our modelling, we provide a parameter that works as a metric to quantify and compare the risk between different stages of the disease. We emphasize that, we developed an online platform for oncologists to calculate the probability of survival of patients diagnosed with breast cancer according to the stage of the disease in real time.
OthusMBarlogieBLeBlancMLet al.Cure models as a useful statistical tool for analyzing survival. Clin Cancer Res2012; 18: 3731–3736.
2.
MallerRZhouX. Survival analysis with long-term survivors1996; Volume 1: New York: John Wiley & Sons.
3.
BerksonJGageRP. Survival curve for cancer patients following treatment. J Am Stat Assoc1952; 47: 501–515.
4.
BoagJW. Maximum likelihood estimates of the proportion of patients cured by cancer therapy. J R Stat Soc Ser B (Methodol)1949; 11: 15–53.
5.
FarewellVT. A model for a binary variable with time-censored observations. Biometrika1977; 64: 43–46.
6.
FarewellVT. The use of mixture models for the analysis of survival data with long-term survivors. Biometrics1982; 38: 1041–1041.
7.
FarewellVT. Mixture models in survival analysis: are they worth the risk?Can J Stat1986; 14: 257–262.
8.
GreenhouseJBWolfeRA. A competing risks derivation of a mixture model for the analysis of survival data. Commun Stat Theory Methods1984; 13: 3133–3154.
9.
GhitanyMMallerRZhouS. Exponential mixture models with long-term survivors and covariates. J Multivar Anal1994; 49: 218–241.
10.
GhitanyMMallerRZhouS. Estimating the proportion of immunes in censored samples: a simulation study. Stat Med1995; 14: 39–49.
11.
GamelJWMcLeanIWRosenbergSH. Proportion cured and mean log survival time as functions of tumour size. Stat Med1990; 9: 999–1006.
12.
MackenzieG. Regression models for survival data: the generalized time-dependent logistic family. Statistician1996; 45: 21–34.
13.
PengYDearKBDenhamJet al.A generalized f mixture model for cure rate estimation. Stat Med1998; 17: 813–830.
14.
GamelJWWellerEAWesleyMNet al.Parametric cure models of relative and cause-specific survival for grouped survival times. Comput Methods Programs Biomed2000; 61: 99–110.
15.
ChenMHIbrahimJG. Maximum likelihood methods for cure rate models with missing covariates. Biometrics2001; 57: 43–52.
16.
CanchoVGBolfarineH. Modeling the presence of immunes by using the exponentiated-Weibull model. J Appl Stat2001; 28: 659–671.
17.
SpostoR. Cure model analysis in cancer: an application to data from the children’s cancer group. Stat Med2002; 21: 293–312.
18.
PonsOLemdaniM. Estimation and test in long-term survival mixture models. Comput Stat Data Anal2003; 41: 465–479.
19.
YuBTiwariRCCroninKAet al.Cure fraction estimation from the mixture cure models for grouped survival data. Stat Med2004; 23: 1733–1747.
20.
PerperoglouAKeramopoullosAvan HouwelingenHC. Approaches in modelling long-term survival: an application to breast cancer. Stat Med2007; 26: 2666–2685.
21.
YuBPengY. Mixture cure models for multivariate survival data. Comput Stat Data Anal2008; 52: 1524–1532.
22.
RodriguesJCanchoVGde CastroMet al.On the unification of long-term survival models. Stat Prob Lett2009; 79: 753–759.
23.
KannanNKunduDNairPet al.The generalized exponential cure rate model with covariates. J Appl Stat2010; 37: 1625–1636.
24.
BasuSTiwariRC. Breast cancer survival, competing risks and mixture cure model: a Bayesian analysis. J R Stat Soc Ser A (Stat Soc)2010; 173: 307–329.
25.
CanchoVGLouzadaFBarrigaGD. The geometric Birnbaum–Saunders regression model with cure rate. J Stat Plan Infer2012; 142: 993–1000.
26.
RomanMLouzadaFCanchoVGet al.A new long-term survival distribution for cancer data. J Data Sci2012; 10: 241–258.
27.
YuBTiwariRC. A Bayesian approach to mixture cure models with spatial frailties for population-based cancer relative survival data. Can J Stat2012; 40: 40–54.
28.
CoonerFBanerjeeSCarlinBPet al.Flexible cure rate modeling under latent activation schemes. J Am Stat Assoc2012; 102: 560–572.
29.
RondeauVSchaffnerECorbièreFet al.Cure frailty models for survival data: application to recurrences for breast cancer and to hospital readmissions for colorectal cancer. Stat Methods Med Res2013; 22: 243–260.
30.
GonzalesJFBTomazellaVLDTaconelliJP. Estimação paramétrica do modelo de mistura com fragilidade gama na presença de covariáveis. Rev Bras Biom2013; 31: 233–247.
31.
HashimotoEMOrtegaEMCordeiroGMet al.The Poisson Birnbaum–Saunders model with long-term survivors. Statistics2014; 48: 1394–1413.
32.
ConlonATaylorJSargentDJ. Multi-state models for colon cancer recurrence and death with a cured fraction. Stat Med2014; 33: 1750–1766.
33.
XuJPengY. Nonparametric cure rate estimation with covariates. Can J Stat2014; 42: 1–17.
34.
ChoiSHuangXCormierJNet al.A semiparametric inverse-gaussian model and inference for survival data with a cured proportion. Can J Stat2014; 42: 635–649.
35.
IbrahimNATaweabFArasanJA parametric non-mixture cure survival model with censored data. In: NikosMValeriM (eds). Computational problems in engineering, Switzerland: Springer, 2014, pp. 231–238.
36.
ChoiSHuangXCormierJN. Efficient semiparametric mixture inferences on cure rate models for competing risks. Can J Stat2015; 43: 420–435.
37.
RodriguesJBalakrishnanNCordeiroGMet al.Latent cure rate model under repair system and threshold effect. J Stat Comput Simul2015; 85: 2860–2873.
38.
GallardoDIBolfarineHPedroso-De-LimaAC. Promotion time cure rate model with bivariate random effects. Commun Stat Simul Comput2015; 45: 1–22.
39.
CordeiroGMOrtegaELemonteA. The Poisson generalized linear failure rate model. Commun Stat Theory Methods2015; 44: 2037–2058.
40.
BalakrishnanNPalS. Likelihood inference for flexible cure rate models with gamma lifetimes. Commun Stat Theory Methods2015; 44: 4007–4048.
41.
Barreto-SouzaW. Long-term survival models with overdispersed number of competing causes. Comput Stat Data Anal2015; 91: 51–63.
42.
TaweabFIbrahimNARizamM. Cure fraction model for interval censoring with a change point based on a covariate threshold. Indian J Sci Technol2015; 8: 1–6.
43.
CanchoVGLouzadaFDeyDKet al.A new lifetime model for multivariate survival data with a surviving fraction. J Stat Comput Simul2016; 86: 279–292.
44.
CanchoVGDeyDKLouzadaF. Unified multivariate survival model with a surviving fraction: an application to a Brazilian customer churn data. J Appl Stat2016; 43: 572–584.
45.
GallardoDIBolfarineHPedroso-de LimaAC. Destructive weighted Poisson cure rate models with bivariate random effects: classical and Bayesian approaches. Comput Stat Data Anal2016; 98: 31–45.
46.
HuTXiangL. Partially linear transformation cure models for interval-censored data. Comput Stat Data Anal2016; 93: 257–269.
47.
BremhorstVLambertP. Flexible estimation in cure survival models using Bayesian p-splines. Comput Stat Data Anal2016; 93: 270–284.
48.
PerdonáGCLouzada-NetoF. A general hazard model for lifetime data in the presence of cure rate. J Appl Stat2011; 38: 1395–1405.
49.
LawlessJF. Statistical models and methods for lifetime data2011; Volume 362: Hoboken,New Jersey: John Wiley & Sons.
50.
LaiCXieMMurthyD. A modified Weibull distribution. IEEE Trans Reliab2003; 52: 33–37.
51.
LouzadaF. Extended hazard regression model for reliability and survival analysis. Lifetime Data Anal1997; 3: 367–381.
52.
MudholkarGSSrivastavaDK. Exponentiated Weibull family for analyzing bathtub failure-rate data. IEEE Trans Reliab1993; 42: 299–302.
53.
CorlessRMGonnetGHHareDEet al.On the Lambert W function. Adv Comput Math1996; 5: 329–359.
NgH. Parameter estimation for a modified Weibull distribution, for progressively type-ii censored samples. IEEE Trans Reliab2005; 54: 374–380.
56.
EfronBTibshiraniR. Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy. Stat Sci1986; 1: 54–75.
57.
DavisonACHinkleyDV. Bootstrap methods and their application1997; Volume 1: New york: Cambridge University Press.
58.
Ross SM. Introduction to probability models, 9th ed. London: Academic Press Elsevier, 2007.
59.
Sun FB and Kececloglu D. A new method for obtaining the ttt plot for a censored sample. In: Proceedings annual reliability and maintainability symposium, Washington, 1999, pp.112–117. IEEE.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
