Flexible Parametric Accelerated Failure Time Models With Cure.
Gespeichert in:
| Titel: | Flexible Parametric Accelerated Failure Time Models With Cure. |
|---|---|
| Autoren: | Akynkozhayev B; Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden., Christoffersen B; Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden., Liu X; Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden., Humphreys K; Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden., Clements M; Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden. |
| Quelle: | Biometrical journal. Biometrische Zeitschrift [Biom J] 2025 Oct; Vol. 67 (5), pp. e70074. |
| Publikationsart: | Journal Article |
| Sprache: | English |
| Info zur Zeitschrift: | Publisher: Wiley-VCH Verlag GmbH & Co. KGaA Country of Publication: Germany NLM ID: 7708048 Publication Model: Print Cited Medium: Internet ISSN: 1521-4036 (Electronic) Linking ISSN: 03233847 NLM ISO Abbreviation: Biom J Subsets: MEDLINE |
| Imprint Name(s): | Publication: <2005-> : Weinheim : Wiley-VCH Verlag GmbH & Co. KGaA Original Publication: Weinheim, Wiley-VCH Verlag GmbH & Co. KGaA |
| MeSH-Schlagworte: | Biometry*/methods , Models, Statistical*, Humans ; Time Factors ; Survival Analysis ; Proportional Hazards Models |
| Abstract: | Accelerated failure time (AFT) models offer an attractive alternative to Cox proportional hazards models. AFT models are collapsible and, unlike hazard ratios in proportional hazards models, the acceleration factor-a key effect measure in AFT models-is collapsible, meaning its value remains unchanged when adjusting for additional covariates. In addition, AFT models provide an intuitive interpretation directly on the survival time scale. From the recent development of smooth parametric AFT models, we identify potential issues with their applications and note several desired extensions that have not yet been implemented. To enrich this tool and its application in clinical research, we improve the AFT models within a flexible parametric framework in several ways: we adopt monotone natural splines to constrain the log cumulative hazard to be a monotonic function across its support; allow for time-varying acceleration factors, possibly include cure and accommodating more than one time-varying effect; and implement both mixture and nonmixture cure models. We implement all of these extensions in the rstpm2 package, which is publicly available on CRAN. Simulations highlight a varying success in estimating cure fractions. However, in terms of covariate-effect estimation, flexible AFT models appear to be more robust than the Cox model even when there is a high proportion of cured individuals in the data, regardless of whether cure is reached within the observed data. We also apply some of our extensions of AFT models to real-world survival data. (© 2025 The Author(s). Biometrical Journal published by Wiley‐VCH GmbH.) |
| References: | Biom J. 2020 Jul;62(4):989-1011. (PMID: 31957910) Stat Med. 2013 Dec 30;32(30):5286-300. (PMID: 24038155) Stat Med. 2007 Oct 15;26(23):4352-74. (PMID: 17342754) Stat Med. 2011 Aug 30;30(19):2409-21. (PMID: 21611958) Lifetime Data Anal. 2004 Dec;10(4):335-50. (PMID: 15690989) Stat Methods Med Res. 2021 Nov;30(11):2526-2542. (PMID: 34547928) Int J Cancer. 1998 Jul 29;77(3):322-9. (PMID: 9663589) Stat Med. 2008 Sep 20;27(21):4301-12. (PMID: 18407568) Stat Med. 2019 May 20;38(11):2074-2102. (PMID: 30652356) Biostatistics. 2023 Jul 14;24(3):811-831. (PMID: 35639824) Mach Learn. 2018;107(12):1895-1922. (PMID: 30393425) Biom J. 2025 Oct;67(5):e70074. (PMID: 40931385) |
| Grant Information: | 874662 European Commission; 2022-00684_VR Vetenskapsrådet; Swedish e-Science Research Centre; CAN21/1512 Cancerfonden; Prostatacancerförbundet |
| Contributed Indexing: | Keywords: accelerated failure time models; cure models; flexible parametric models; splines |
| Entry Date(s): | Date Created: 20250910 Date Completed: 20250911 Latest Revision: 20250913 |
| Update Code: | 20250913 |
| PubMed Central ID: | PMC12423370 |
| DOI: | 10.1002/bimj.70074 |
| PMID: | 40931385 |
| Datenbank: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Accelerated failure time (AFT) models offer an attractive alternative to Cox proportional hazards models. AFT models are collapsible and, unlike hazard ratios in proportional hazards models, the acceleration factor-a key effect measure in AFT models-is collapsible, meaning its value remains unchanged when adjusting for additional covariates. In addition, AFT models provide an intuitive interpretation directly on the survival time scale. From the recent development of smooth parametric AFT models, we identify potential issues with their applications and note several desired extensions that have not yet been implemented. To enrich this tool and its application in clinical research, we improve the AFT models within a flexible parametric framework in several ways: we adopt monotone natural splines to constrain the log cumulative hazard to be a monotonic function across its support; allow for time-varying acceleration factors, possibly include cure and accommodating more than one time-varying effect; and implement both mixture and nonmixture cure models. We implement all of these extensions in the rstpm2 package, which is publicly available on CRAN. Simulations highlight a varying success in estimating cure fractions. However, in terms of covariate-effect estimation, flexible AFT models appear to be more robust than the Cox model even when there is a high proportion of cured individuals in the data, regardless of whether cure is reached within the observed data. We also apply some of our extensions of AFT models to real-world survival data.<br /> (© 2025 The Author(s). Biometrical Journal published by Wiley‐VCH GmbH.) |
|---|---|
| ISSN: | 1521-4036 |
| DOI: | 10.1002/bimj.70074 |