A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma

Abstract After surgery of localized renal cell carcinoma, over 20% of the patients will develop distant metastases. Our aim was to develop an easy-to-use prognostic model for predicting metastasis-free survival after radical or partial nephrectomy of localized clear cell RCC. Model training was perf...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kalle E. Mattila, Teemu D. Laajala, Sara V. Tornberg, Tuomas P. Kilpeläinen, Paula Vainio, Otto Ettala, Peter J. Boström, Harry Nisen, Laura L. Elo, Panu M. Jaakkola
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/f097036ba65447a59e243f07da006031
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f097036ba65447a59e243f07da006031
record_format dspace
spelling oai:doaj.org-article:f097036ba65447a59e243f07da0060312021-12-02T17:32:56ZA three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma10.1038/s41598-021-88177-92045-2322https://doaj.org/article/f097036ba65447a59e243f07da0060312021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88177-9https://doaj.org/toc/2045-2322Abstract After surgery of localized renal cell carcinoma, over 20% of the patients will develop distant metastases. Our aim was to develop an easy-to-use prognostic model for predicting metastasis-free survival after radical or partial nephrectomy of localized clear cell RCC. Model training was performed on 196 patients. Right-censored metastasis-free survival was analysed using LASSO-regularized Cox regression, which identified three key prediction features. The model was validated in an external cohort of 714 patients. 55 (28%) and 134 (19%) patients developed distant metastases during the median postoperative follow-up of 6.3 years (interquartile range 3.4–8.6) and 5.4 years (4.0–7.6) in the training and validation cohort, respectively. Patients were stratified into clinically meaningful risk categories using only three features: tumor size, tumor grade and microvascular invasion, and a representative nomogram and a visual prediction surface were constructed using these features in Cox proportional hazards model. Concordance indices in the training and validation cohorts were 0.755 ± 0.029 and 0.836 ± 0.015 for our novel model, which were comparable to the C-indices of the original Leibovich prediction model (0.734 ± 0.035 and 0.848 ± 0.017, respectively). Thus, the presented model retains high accuracy while requiring only three features that are routinely collected and widely available.Kalle E. MattilaTeemu D. LaajalaSara V. TornbergTuomas P. KilpeläinenPaula VainioOtto EttalaPeter J. BoströmHarry NisenLaura L. EloPanu M. JaakkolaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Kalle E. Mattila
Teemu D. Laajala
Sara V. Tornberg
Tuomas P. Kilpeläinen
Paula Vainio
Otto Ettala
Peter J. Boström
Harry Nisen
Laura L. Elo
Panu M. Jaakkola
A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
description Abstract After surgery of localized renal cell carcinoma, over 20% of the patients will develop distant metastases. Our aim was to develop an easy-to-use prognostic model for predicting metastasis-free survival after radical or partial nephrectomy of localized clear cell RCC. Model training was performed on 196 patients. Right-censored metastasis-free survival was analysed using LASSO-regularized Cox regression, which identified three key prediction features. The model was validated in an external cohort of 714 patients. 55 (28%) and 134 (19%) patients developed distant metastases during the median postoperative follow-up of 6.3 years (interquartile range 3.4–8.6) and 5.4 years (4.0–7.6) in the training and validation cohort, respectively. Patients were stratified into clinically meaningful risk categories using only three features: tumor size, tumor grade and microvascular invasion, and a representative nomogram and a visual prediction surface were constructed using these features in Cox proportional hazards model. Concordance indices in the training and validation cohorts were 0.755 ± 0.029 and 0.836 ± 0.015 for our novel model, which were comparable to the C-indices of the original Leibovich prediction model (0.734 ± 0.035 and 0.848 ± 0.017, respectively). Thus, the presented model retains high accuracy while requiring only three features that are routinely collected and widely available.
format article
author Kalle E. Mattila
Teemu D. Laajala
Sara V. Tornberg
Tuomas P. Kilpeläinen
Paula Vainio
Otto Ettala
Peter J. Boström
Harry Nisen
Laura L. Elo
Panu M. Jaakkola
author_facet Kalle E. Mattila
Teemu D. Laajala
Sara V. Tornberg
Tuomas P. Kilpeläinen
Paula Vainio
Otto Ettala
Peter J. Boström
Harry Nisen
Laura L. Elo
Panu M. Jaakkola
author_sort Kalle E. Mattila
title A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
title_short A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
title_full A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
title_fullStr A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
title_full_unstemmed A three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
title_sort three-feature prediction model for metastasis-free survival after surgery of localized clear cell renal cell carcinoma
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/f097036ba65447a59e243f07da006031
work_keys_str_mv AT kalleemattila athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT teemudlaajala athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT saravtornberg athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT tuomaspkilpelainen athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT paulavainio athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT ottoettala athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT peterjbostrom athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT harrynisen athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT lauralelo athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT panumjaakkola athreefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT kalleemattila threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT teemudlaajala threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT saravtornberg threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT tuomaspkilpelainen threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT paulavainio threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT ottoettala threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT peterjbostrom threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT harrynisen threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT lauralelo threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
AT panumjaakkola threefeaturepredictionmodelformetastasisfreesurvivalaftersurgeryoflocalizedclearcellrenalcellcarcinoma
_version_ 1718380158132420608