Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes

Abstract This study aimed to develop an intraoperative prediction model to evaluate the risk of non-sentinel lymph node (NSLN) metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes (SLNs). The clinicopathologic data of 714 patients with 1–2 positive SLNs were investigat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lei Meng, Ting Zheng, Yuanyuan Wang, Zhao Li, Qi Xiao, Junfeng He, Jinxiang Tan
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0e2ec0f378ba44d18a7158c45c87b056
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0e2ec0f378ba44d18a7158c45c87b056
record_format	dspace
spelling	oai:doaj.org-article:0e2ec0f378ba44d18a7158c45c87b0562021-12-02T19:16:14ZDevelopment of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes10.1038/s41598-021-99522-32045-2322https://doaj.org/article/0e2ec0f378ba44d18a7158c45c87b0562021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-99522-3https://doaj.org/toc/2045-2322Abstract This study aimed to develop an intraoperative prediction model to evaluate the risk of non-sentinel lymph node (NSLN) metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes (SLNs). The clinicopathologic data of 714 patients with 1–2 positive SLNs were investigated. Univariate and multivariate analyses were performed to identify the risk factors of NSLN metastasis. A new mathematical prediction model was developed based on LASSO and validated in an independent cohort of 131 patients. The area under the receiver operating characteristic curve (AUC) was used to quantify performance of the model. Patients with NSLN metastasis accounted for 37.3% (266/714) and 34.3% (45/131) of the training and validation cohorts, respectively. A LASSO regression-based prediction model was developed and included the 13 most powerful factors (age group, clinical tumour stage, histologic type, number of positive SLNs, number of negative SLNs, number of SLNs dissected, SLN metastasis ratio, ER status, PR status, HER2 status, Ki67 staining percentage, molecular subtype and P53 status). The AUCs of training and validation cohorts were 0.764 (95% CI 0.729–0.798) and 0.777 (95% CI 0.692–0.862), respectively. We presented a new prediction model with excellent clinical applicability and diagnostic performance for use by clinicians as an intraoperative clinical tool to predict risk of NSLN metastasis in Chinese breast cancer patients with 1–2 positive SLNs and make the final decisions regarding axillary lymph node dissection.Lei MengTing ZhengYuanyuan WangZhao LiQi XiaoJunfeng HeJinxiang TanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Lei Meng Ting Zheng Yuanyuan Wang Zhao Li Qi Xiao Junfeng He Jinxiang Tan Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
description	Abstract This study aimed to develop an intraoperative prediction model to evaluate the risk of non-sentinel lymph node (NSLN) metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes (SLNs). The clinicopathologic data of 714 patients with 1–2 positive SLNs were investigated. Univariate and multivariate analyses were performed to identify the risk factors of NSLN metastasis. A new mathematical prediction model was developed based on LASSO and validated in an independent cohort of 131 patients. The area under the receiver operating characteristic curve (AUC) was used to quantify performance of the model. Patients with NSLN metastasis accounted for 37.3% (266/714) and 34.3% (45/131) of the training and validation cohorts, respectively. A LASSO regression-based prediction model was developed and included the 13 most powerful factors (age group, clinical tumour stage, histologic type, number of positive SLNs, number of negative SLNs, number of SLNs dissected, SLN metastasis ratio, ER status, PR status, HER2 status, Ki67 staining percentage, molecular subtype and P53 status). The AUCs of training and validation cohorts were 0.764 (95% CI 0.729–0.798) and 0.777 (95% CI 0.692–0.862), respectively. We presented a new prediction model with excellent clinical applicability and diagnostic performance for use by clinicians as an intraoperative clinical tool to predict risk of NSLN metastasis in Chinese breast cancer patients with 1–2 positive SLNs and make the final decisions regarding axillary lymph node dissection.
format	article
author	Lei Meng Ting Zheng Yuanyuan Wang Zhao Li Qi Xiao Junfeng He Jinxiang Tan
author_facet	Lei Meng Ting Zheng Yuanyuan Wang Zhao Li Qi Xiao Junfeng He Jinxiang Tan
author_sort	Lei Meng
title	Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
title_short	Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
title_full	Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
title_fullStr	Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
title_full_unstemmed	Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes
title_sort	development of a prediction model based on lasso regression to evaluate the risk of non-sentinel lymph node metastasis in chinese breast cancer patients with 1–2 positive sentinel lymph nodes
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0e2ec0f378ba44d18a7158c45c87b056
work_keys_str_mv	AT leimeng developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT tingzheng developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT yuanyuanwang developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT zhaoli developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT qixiao developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT junfenghe developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes AT jinxiangtan developmentofapredictionmodelbasedonlassoregressiontoevaluatetheriskofnonsentinellymphnodemetastasisinchinesebreastcancerpatientswith12positivesentinellymphnodes
_version_	1718376954966573056

Development of a prediction model based on LASSO regression to evaluate the risk of non-sentinel lymph node metastasis in Chinese breast cancer patients with 1–2 positive sentinel lymph nodes

Ejemplares similares