On variable selection in a semiparametric AFT mixture cure model

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

On variable selection in a semiparametric AFT mixture cure model. / Parsa, Motahareh; Taghavi-Shahri, Seyed Mahmood; Van Keilegom, Ingrid.

In: Lifetime Data Analysis, Vol. 30, 2024, p. 472–500.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Parsa, M, Taghavi-Shahri, SM & Van Keilegom, I 2024, 'On variable selection in a semiparametric AFT mixture cure model', Lifetime Data Analysis, vol. 30, pp. 472–500. https://doi.org/10.1007/s10985-024-09619-w

APA

Parsa, M., Taghavi-Shahri, S. M., & Van Keilegom, I. (2024). On variable selection in a semiparametric AFT mixture cure model. Lifetime Data Analysis, 30, 472–500. https://doi.org/10.1007/s10985-024-09619-w

Vancouver

Parsa M, Taghavi-Shahri SM, Van Keilegom I. On variable selection in a semiparametric AFT mixture cure model. Lifetime Data Analysis. 2024;30:472–500. https://doi.org/10.1007/s10985-024-09619-w

Author

Parsa, Motahareh ; Taghavi-Shahri, Seyed Mahmood ; Van Keilegom, Ingrid. / On variable selection in a semiparametric AFT mixture cure model. In: Lifetime Data Analysis. 2024 ; Vol. 30. pp. 472–500.

Bibtex

@article{2574793986c145148c7dde0d231c49ce,
title = "On variable selection in a semiparametric AFT mixture cure model",
abstract = "In clinical studies, one often encounters time-to-event data that are subject to right censoring and for which a fraction of the patients under study never experience the event of interest. Such data can be modeled using cure models in survival analysis. In the presence of cure fraction, the mixture cure model is popular, since it allows to model probability to be cured (called the incidence) and the survival function of the uncured individuals (called the latency). In this paper, we develop a variable selection procedure for the incidence and latency parts of a mixture cure model, consisting of a logistic model for the incidence and a semiparametric accelerated failure time model for the latency. We use a penalized likelihood approach, based on adaptive LASSO penalties for each part of the model, and we consider two algorithms for optimizing the criterion function. Extensive simulations are carried out to assess the accuracy of the proposed selection procedure. Finally, we employ the proposed method to a real dataset regarding heart failure patients with left ventricular systolic dysfunction.",
author = "Motahareh Parsa and Taghavi-Shahri, {Seyed Mahmood} and {Van Keilegom}, Ingrid",
note = "{\textcopyright} 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.",
year = "2024",
doi = "10.1007/s10985-024-09619-w",
language = "English",
volume = "30",
pages = "472–500",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - On variable selection in a semiparametric AFT mixture cure model

AU - Parsa, Motahareh

AU - Taghavi-Shahri, Seyed Mahmood

AU - Van Keilegom, Ingrid

N1 - © 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

PY - 2024

Y1 - 2024

N2 - In clinical studies, one often encounters time-to-event data that are subject to right censoring and for which a fraction of the patients under study never experience the event of interest. Such data can be modeled using cure models in survival analysis. In the presence of cure fraction, the mixture cure model is popular, since it allows to model probability to be cured (called the incidence) and the survival function of the uncured individuals (called the latency). In this paper, we develop a variable selection procedure for the incidence and latency parts of a mixture cure model, consisting of a logistic model for the incidence and a semiparametric accelerated failure time model for the latency. We use a penalized likelihood approach, based on adaptive LASSO penalties for each part of the model, and we consider two algorithms for optimizing the criterion function. Extensive simulations are carried out to assess the accuracy of the proposed selection procedure. Finally, we employ the proposed method to a real dataset regarding heart failure patients with left ventricular systolic dysfunction.

AB - In clinical studies, one often encounters time-to-event data that are subject to right censoring and for which a fraction of the patients under study never experience the event of interest. Such data can be modeled using cure models in survival analysis. In the presence of cure fraction, the mixture cure model is popular, since it allows to model probability to be cured (called the incidence) and the survival function of the uncured individuals (called the latency). In this paper, we develop a variable selection procedure for the incidence and latency parts of a mixture cure model, consisting of a logistic model for the incidence and a semiparametric accelerated failure time model for the latency. We use a penalized likelihood approach, based on adaptive LASSO penalties for each part of the model, and we consider two algorithms for optimizing the criterion function. Extensive simulations are carried out to assess the accuracy of the proposed selection procedure. Finally, we employ the proposed method to a real dataset regarding heart failure patients with left ventricular systolic dysfunction.

U2 - 10.1007/s10985-024-09619-w

DO - 10.1007/s10985-024-09619-w

M3 - Journal article

C2 - 38436831

VL - 30

SP - 472

EP - 500

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

ER -

ID: 385644256