Predicting pathologic ≥N2 disease in women with breast cancer

Abstract The distinction between pN1 and ≥pN2 breast cancer impacts treatment decisions. Using data from a single institution on women with cN0 invasive breast cancer who were treated with upfront surgery, had 1-3 positive SLNs, and underwent completion ALND, we used gradient boosted trees (XGBoost)...

Full description

Saved in:
Bibliographic Details
Main Authors: Kerollos Nashat Wanis, Wenli Dong, Yu Shen, Funda Meric-Bernstam, Taiwo Adesoye, Henry M. Kuerer, Abigail S. Caudle, Nina Tamirisa, Sarah M. DeSnyder, Susie X. Sun, Isabelle Bedrosian, Puneet Singh, Solange E. Cox, Kelly K. Hunt, Rosa F. Hwang
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Breast Cancer
Online Access:https://doi.org/10.1038/s41523-025-00757-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850269111990353920
author Kerollos Nashat Wanis
Wenli Dong
Yu Shen
Funda Meric-Bernstam
Taiwo Adesoye
Henry M. Kuerer
Abigail S. Caudle
Nina Tamirisa
Sarah M. DeSnyder
Susie X. Sun
Isabelle Bedrosian
Puneet Singh
Solange E. Cox
Kelly K. Hunt
Rosa F. Hwang
author_facet Kerollos Nashat Wanis
Wenli Dong
Yu Shen
Funda Meric-Bernstam
Taiwo Adesoye
Henry M. Kuerer
Abigail S. Caudle
Nina Tamirisa
Sarah M. DeSnyder
Susie X. Sun
Isabelle Bedrosian
Puneet Singh
Solange E. Cox
Kelly K. Hunt
Rosa F. Hwang
author_sort Kerollos Nashat Wanis
collection DOAJ
description Abstract The distinction between pN1 and ≥pN2 breast cancer impacts treatment decisions. Using data from a single institution on women with cN0 invasive breast cancer who were treated with upfront surgery, had 1-3 positive SLNs, and underwent completion ALND, we used gradient boosted trees (XGBoost) to develop a model for predicting ≥pN2 disease using clinicopathologic variables. Model performance was tested in a held-out subsample (20%) and validated using data from the National Cancer Database (NCDB). Of 3574 patients with cN0 breast cancer, 587 underwent upfront surgery and had 1-3 positive SLNs. Of these, 415 (70.7%) underwent completion ALND, with 64 (15.4%) having ≥pN2 disease. The trained algorithm had an AUC of 0.87 (95% CI: 0.74, 0.97) in the held-out test data, and 0.78 (95% CI: 0.76, 0.79) in recent NCDB data where completion ALND was much less commonly performed. The number of positive SLNs and the total number of SLNs removed had the greatest influence on model predictions in the held-out test data. The developed model effectively estimates the probability of ≥pN2 disease in cN0 patients with positive SLNs, providing guidance for the management of patients with breast cancer.
format Article
id doaj-art-c12f361481f14a4e9496c22cec2365bc
institution OA Journals
issn 2374-4677
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Breast Cancer
spelling doaj-art-c12f361481f14a4e9496c22cec2365bc2025-08-20T01:53:15ZengNature Portfolionpj Breast Cancer2374-46772025-05-011111810.1038/s41523-025-00757-4Predicting pathologic ≥N2 disease in women with breast cancerKerollos Nashat Wanis0Wenli Dong1Yu Shen2Funda Meric-Bernstam3Taiwo Adesoye4Henry M. Kuerer5Abigail S. Caudle6Nina Tamirisa7Sarah M. DeSnyder8Susie X. Sun9Isabelle Bedrosian10Puneet Singh11Solange E. Cox12Kelly K. Hunt13Rosa F. Hwang14Department of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Biostatistics, The University of Texas MD Anderson Cancer CenterDepartment of Biostatistics, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterDepartment of Breast Surgical Oncology, The University of Texas MD Anderson Cancer CenterAbstract The distinction between pN1 and ≥pN2 breast cancer impacts treatment decisions. Using data from a single institution on women with cN0 invasive breast cancer who were treated with upfront surgery, had 1-3 positive SLNs, and underwent completion ALND, we used gradient boosted trees (XGBoost) to develop a model for predicting ≥pN2 disease using clinicopathologic variables. Model performance was tested in a held-out subsample (20%) and validated using data from the National Cancer Database (NCDB). Of 3574 patients with cN0 breast cancer, 587 underwent upfront surgery and had 1-3 positive SLNs. Of these, 415 (70.7%) underwent completion ALND, with 64 (15.4%) having ≥pN2 disease. The trained algorithm had an AUC of 0.87 (95% CI: 0.74, 0.97) in the held-out test data, and 0.78 (95% CI: 0.76, 0.79) in recent NCDB data where completion ALND was much less commonly performed. The number of positive SLNs and the total number of SLNs removed had the greatest influence on model predictions in the held-out test data. The developed model effectively estimates the probability of ≥pN2 disease in cN0 patients with positive SLNs, providing guidance for the management of patients with breast cancer.https://doi.org/10.1038/s41523-025-00757-4
spellingShingle Kerollos Nashat Wanis
Wenli Dong
Yu Shen
Funda Meric-Bernstam
Taiwo Adesoye
Henry M. Kuerer
Abigail S. Caudle
Nina Tamirisa
Sarah M. DeSnyder
Susie X. Sun
Isabelle Bedrosian
Puneet Singh
Solange E. Cox
Kelly K. Hunt
Rosa F. Hwang
Predicting pathologic ≥N2 disease in women with breast cancer
npj Breast Cancer
title Predicting pathologic ≥N2 disease in women with breast cancer
title_full Predicting pathologic ≥N2 disease in women with breast cancer
title_fullStr Predicting pathologic ≥N2 disease in women with breast cancer
title_full_unstemmed Predicting pathologic ≥N2 disease in women with breast cancer
title_short Predicting pathologic ≥N2 disease in women with breast cancer
title_sort predicting pathologic ≥n2 disease in women with breast cancer
url https://doi.org/10.1038/s41523-025-00757-4
work_keys_str_mv AT kerollosnashatwanis predictingpathologicn2diseaseinwomenwithbreastcancer
AT wenlidong predictingpathologicn2diseaseinwomenwithbreastcancer
AT yushen predictingpathologicn2diseaseinwomenwithbreastcancer
AT fundamericbernstam predictingpathologicn2diseaseinwomenwithbreastcancer
AT taiwoadesoye predictingpathologicn2diseaseinwomenwithbreastcancer
AT henrymkuerer predictingpathologicn2diseaseinwomenwithbreastcancer
AT abigailscaudle predictingpathologicn2diseaseinwomenwithbreastcancer
AT ninatamirisa predictingpathologicn2diseaseinwomenwithbreastcancer
AT sarahmdesnyder predictingpathologicn2diseaseinwomenwithbreastcancer
AT susiexsun predictingpathologicn2diseaseinwomenwithbreastcancer
AT isabellebedrosian predictingpathologicn2diseaseinwomenwithbreastcancer
AT puneetsingh predictingpathologicn2diseaseinwomenwithbreastcancer
AT solangeecox predictingpathologicn2diseaseinwomenwithbreastcancer
AT kellykhunt predictingpathologicn2diseaseinwomenwithbreastcancer
AT rosafhwang predictingpathologicn2diseaseinwomenwithbreastcancer