Reparameterized flexible cure models with direct interpretation via the lambert W function

Diego I. Gallardo; Yolanda M. Gómez; Marcelo Bourguignon; Héctor J. Gómez; Diego I. Gallardo; Yolanda M. Gómez; Marcelo Bourguignon; Héctor J. Gómez

doi:10.3934/math.2025991

AIMS Mathematics

2025, Volume 10, Issue 9: 22249-22264. doi: 10.3934/math.2025991

Previous Article Next Article

Research article Special Issues

Reparameterized flexible cure models with direct interpretation via the lambert W function

1.
Departamento de Estadística, Facultad de Ciencias, Universidad del Bío-Bío, Concepción, Chile
2.
Department of Statistics, Universidade Federal do Rio Grande do Norte, Natal, RN, Brazil
3.
Departamento de Ciencias Matemáticas y Físicas, Facultad de Ingeniería, Universidad Católica de Temuco, Temuco, Chile

Received: 26 May 2025 Revised: 22 July 2025 Accepted: 31 July 2025 Published: 26 September 2025
MSC : 62E10, 62F10

This article discusses the practical limitations of the flexible cure rate model proposed by Milienos (2022) in ^[1] [On a reparameterization of a flexible family of cure models, Statistics in Medicine 41, 4091–4111]. Although the model is structurally flexible, it has problems with interpretability and identifiability when covariates are included. To address these problems, we propose a novel reparameterization that directly links the cure fraction to meaningful parameters based on cancer cell counting mechanisms. This approach improves interpretability and resolves the identification problems present in the original model. Our new models facilitate straightforward inference within covariate structures while maintaining desirable flexibility. Parameter estimation is conducted using maximum likelihood methods. Through extensive simulation studies, we demonstrate that reparameterized models exhibit superior empirical performance. Their practical applicability is further illustrated through two melanoma datasets, where our models significantly outperform classical approaches in terms of fit and interpretability.
- cure rate models,
- reparameterization,
- melanoma data set,
- Lambert function
Citation: Diego I. Gallardo, Yolanda M. Gómez, Marcelo Bourguignon, Héctor J. Gómez. Reparameterized flexible cure models with direct interpretation via the lambert W function[J]. AIMS Mathematics, 2025, 10(9): 22249-22264. doi: 10.3934/math.2025991

Related Papers:

Abstract

This article discusses the practical limitations of the flexible cure rate model proposed by Milienos (2022) in ^[1] [On a reparameterization of a flexible family of cure models, Statistics in Medicine 41, 4091–4111]. Although the model is structurally flexible, it has problems with interpretability and identifiability when covariates are included. To address these problems, we propose a novel reparameterization that directly links the cure fraction to meaningful parameters based on cancer cell counting mechanisms. This approach improves interpretability and resolves the identification problems present in the original model. Our new models facilitate straightforward inference within covariate structures while maintaining desirable flexibility. Parameter estimation is conducted using maximum likelihood methods. Through extensive simulation studies, we demonstrate that reparameterized models exhibit superior empirical performance. Their practical applicability is further illustrated through two melanoma datasets, where our models significantly outperform classical approaches in terms of fit and interpretability.

References

[1]	F. S. Milienos, On a reparameterization of a flexible family of cure models, Stat. Med., 41 (2022), 4091–4111. https://doi.org/10.1002/sim.9498 doi: 10.1002/sim.9498
[2]	J. W. Boag, Maximum Likelihood Estimates of the Proportion of Patients Cured by Cancer Therapy, J. R. Stat. Soc. B, 11 (1949), 15–44. https://doi.org/10.1111/j.2517-6161.1949.tb00020.x doi: 10.1111/j.2517-6161.1949.tb00020.x
[3]	A. Y. Yakovlev, A. D. Tsodikov, Stochastic Models of Tumor Latency and Their Biostatistical Applications, Singapore: World Scientific, 1996. https://doi.org/10.1142/2420
[4]	A. D. Tsodikov, J. G. Ibrahim, A. Y. Yakovlev, Estimating Cure Rates from Survival Data: An Alternative to Two-Component Mixture Models, J. Am. Stat. Assoc. 98 (2003), 1063–1078. https://doi.org/10.1198/01622145030000001007
[5]	J. Rodrigues, M. De Castro, V. G. Cancho, N. Balakrishnan, COM–Poisson cure rate survival models and an application to a cutaneous melanoma data, J. Stat. Plan. Infer., 139 (2009), 3605–3611. https://doi.org/10.1016/j.jspi.2009.04.014 doi: 10.1016/j.jspi.2009.04.014
[6]	V. G. Cancho, F. Louzada, E. M. Ortega, The power series cure rate model: An application to a cutaneous melanoma data, Commun. Stat. Simul. Comput., 42 (2013), 586–602. https://doi.org/10.1080/03610918.2011.639971 doi: 10.1080/03610918.2011.639971
[7]	D. I. Gallardo, J. S. Romeo, R. Meyer, A simplified estimation procedure based on the EM algorithm for the power series cure rate model, Commun. Stat. Simul. Comput., 46 (2017), 6342–6359. https://doi.org/10.1080/03610918.2016.1202276 doi: 10.1080/03610918.2016.1202276
[8]	D. I. Gallardo, Y. M. Gómez, M. De Castro, A flexible cure rate model based on the polylogarithm distribution, J. Stat. Comput. Simul., 88 (2018), 2137–2149. https://doi.org/10.1080/00949655.2018.1451850 doi: 10.1080/00949655.2018.1451850
[9]	J. Rodrigues, V. G. Cancho, M. De Castro, F. Louzada-Neto, On the unification of long-term survival models, Stat. Probab. Lett., 79 (2009), 753–759. https://doi.org/10.1016/j.spl.2008.10.029 doi: 10.1016/j.spl.2008.10.029
[10]	R. Corless, G. Gonnet, D. Hare, D. Jeffrey, D. Knuth, On the Lambert W function, Adv. Comput. Math., 5 (1996), 329–359. https://doi.org/10.1007/BF02124750
[11]	Avraham Adler, lamW: Lambert-W Function, R package version 2.1.0, 2015. Available from: https://cran.r-project.org/web/packages/lamW/.
[12]	H. W. Borchers, pracma: Practical Numerical Math Functions, R package version 2.4.2, 2022. Available from: https://CRAN.R-project.org/package = pracma.
[13]	The R Foundation, R: A Language and Environment for Statistical Computing, 2025. Available from: https://www.R-project.org/.
[14]	M. De Castro, V. G. Cancho, J. Rodrigues, A Bayesian Long-term Survival Model Parametrized in the Cured Fraction, Biometrical J., 51 (2009), 443–455. https://doi.org/10.1002/bimj.200800199 doi: 10.1002/bimj.200800199
[15]	R. C. Mittelhammer, G. G. Judge, D. J. Miller, Econometric Foundations, New York: Cambridge University Press, 2000.
[16]	D. R. Cox, C. V. Hinkley, Theoretical Statistics, New York: Chapman and Hall/CRC, 1974. https://doi.org/10.1201/b14832
[17]	E. L. Lehmann, The Power of Rank Tests, Ann. Math. Stat., 24 (1953), 23–43. https://doi.org/10.1214/aoms/1177729080
[18]	L. Hanin, L. Huang, Identifiability of cure models revisited, J. Multivar. Anal., 130 (2014), 261–274. https://doi.org/10.1016/j.jmva.2014.06.002 doi: 10.1016/j.jmva.2014.06.002
[19]	H. Akaike, A new look at the statistical model identification, IEEE T. Automat. Contr., 19 (1974), 716–723. https://doi.org/10.1109/TAC.1974.1100705 doi: 10.1109/TAC.1974.1100705
[20]	G. Schwarz, Estimating the dimension of a model, Ann. Stat., 6 (1978), 461–464.
[21]	T. H. Scheike, M. Zhang, Analyzing Competing Risk Data Using the R timereg Package, J. Stat. Software, 38 (2011), 1–15. https://doi.org/10.18637/jss.v038.i02 doi: 10.18637/jss.v038.i02

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)