Dataset Information

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms.

ABSTRACT:

Background

Axillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omission of ALND.

Methods

Data from 2217 BC patients who underwent SLN biopsy at Shantou University Medical College were analyzed, with 634 having positive SLNs. Patients were categorized into those with ≤ 2 positive SLNs and those with ≥ 3 positive SLNs. We applied nine ML algorithms to predict non-SLN metastasis. Model performance was evaluated using ROC curves, precision-recall curves, and calibration curves. Decision Curve Analysis (DCA) assessed the clinical utility of the models.

Results

The RF model showed superior predictive performance, achieving an AUC of 0.987 in the training set and 0.828 in the validation set. Key predictive features included size of positive SLNs, tumor size, number of SLNs, and ER status. In external validation, the RF model achieved an AUC of 0.870, demonstrating robust predictive capabilities.

Conclusion

The developed RF model accurately predicts non-SLN metastasis in BC patients with ≥ 3 positive SLNs, suggesting that ALND might be avoided in selected patients by applying additional axillary radiotherapy. This approach could reduce the incidence of postoperative complications and improve patient quality of life. Further validation in prospective clinical trials is warranted.

SUBMITTER: Xie X

PROVIDER: S-EPMC11370100 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms.

Xie Xiangli X Fang Yutong Y He Lifang L Chen Zexiao Z Chen Chunfa C Zeng Huancheng H Chen Bingfeng B Huang Guangsheng G Guo Cuiping C Zhang Qunchen Q Wu Jundong J

BMC cancer 20240902 1

<h4>Background</h4>Axillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omi ...[more]

PMID: 39223574

Similar Datasets

Project description:IntroductionBreast cancer surgery currently focuses on de-escalating treatment without compromising patient survival. Axillary radiotherapy (ART) now replaces axillary lymph node dissection (ALND) in patients with limited sentinel lymph node (SLN) involvement during the primary surgery, and this has significantly reduced the incidence of lymphedema without worsening the prognosis. However, patients treated with neoadjuvant systemic treatment (NST) cannot benefit from this option despite the low incidence of residual disease in the armpit in most cases. Data regarding the use of radiotherapy instead of ALND in this population are lacking. This study will assess whether ART is non-inferior to ALND in terms of recurrence and overall survival in patients with positive SLN after NST, including whether it reduces surgery-related adverse effects.Methods and analysesThis multicenter, randomized, open-label, phase 3 trial will enroll 1660 patients with breast cancer and positive SLNs following NST in approximately 50 Spanish centers over 3 years. Patients will be stratified by NST regimen and nodal involvement (isolated tumoral cells or micrometastasis versus macrometastasis) and randomly assigned 1:1 to ART without ALND (study arm) or ALND alone (control arm). Level 3 and supraclavicular radiotherapy will be added in both arms. The primary outcome is the 5-year axillary recurrence determined by clinical and radiological examination. The secondary outcomes include lymphedema or arm dysfunction, quality of life based (EORTC QLQ-C30 and QLQ-BR23 questionnaires), disease-free survival, and overall survival.DiscussionThis study aims to provide data to confirm the efficacy and safety of ART over ALND in patients with a positive SLN after NST, together with the impact on morbidity.Ethics and disseminationThe Research Ethics Committee of Bellvitge University Hospital approved this trial (Protocol Record PR148/21, version 3, 1/2/2022) and all patients must provide written informed consent. The involvement of around 50 centers across Spain will facilitate the dissemination of our results.Trial registrationClinicalTrials.gov, identifier number NCT04889924.

Project description:BackgroundAxillary surgical management in patients with node-positive breast cancer at the time of diagnosis converted to negative nodes through neoadjuvant chemotherapy (NAC) remains unclear. Removal of more than two sentinel nodes (SLNs) in these patients may decrease the false negative rate (FNR) of sentinel lymph node biopsies (SLNBs). We aim to analyse the detection rate (DR) and the FNR of SLNB assessment according to the number of SLNs removed.MethodsA retrospective study was performed from October 2012 to December 2018. Patients with invasive breast cancer who had a clinically node-positive disease at diagnosis and with a complete axillary response after neoadjuvant chemotherapy were selected. Patients included underwent SLNB and axillary lymph node dissection (ALND) after NAC. The SLN was considered positive if any residual disease was detected. Descriptive statistics were used to describe the clinicopathologic features and the results of SLNB and ALND. The DR of SLNB was defined as the number of patients with successful identification of SLN. Presence of residual disease in ALND and negative SLN was considered false negative.ResultsA total of 368 patients with invasive breast cancer who underwent surgery after complete NAC were studied. Of them, 85 patients met the eligibility criteria and were enrolled in the study. The mean age at diagnosis was 50.8 years. Systematic lymphadenectomy was performed in all patients, with an average of 10 lymph nodes removed. The DR of SLNB was 92.9%, and the FNR was 19.1. The median number of SLNs removed was 3, and at least, three SLNs were obtained in 42 patients (53.2%). When at least three sentinel nodes were removed, the FNR decreased to 8.7%.ConclusionsIn this cohort, the SLN assessment was associated with an adequate DR and a high FNR. Removing three or more SLNs decreased the FNR from 19.1% to 8.7%. Complementary approaches may be considered for axillary lymph node staging after neoadjuvant chemotherapy. The study was approved by our institution's ethics committee (Instituto de Investigacion Sanitaria Hospital 12 de Octubre (imas12), Universidad Complutense de Madrid, Madrid, Spain) (https://clinicaltrials.gov/ct2/show/NCEI:20/0048).

Project description:BackgroundCurrent practice is to perform a completion axillary lymph node dissection (ALND) for breast cancer patients with tumor-involved sentinel lymph nodes (SLNs), although fewer than half will have non-sentinel node (NSLN) metastasis. Our goal was to develop new models to quantify the risk of NSLN metastasis in SLN-positive patients and to compare predictive capabilities to another widely used model.MethodsWe constructed three models to predict NSLN status: recursive partitioning with receiver operating characteristic curves (RP-ROC), boosted Classification and Regression Trees (CART), and multivariate logistic regression (MLR) informed by CART. Data were compiled from a multicenter Northern California and Oregon database of 784 patients who prospectively underwent SLN biopsy and completion ALND. We compared the predictive abilities of our best model and the Memorial Sloan-Kettering Breast Cancer Nomogram (Nomogram) in our dataset and an independent dataset from Northwestern University.Results285 patients had positive SLNs, of which 213 had known angiolymphatic invasion status and 171 had complete pathologic data including hormone receptor status. 264 (93%) patients had limited SLN disease (micrometastasis, 70%, or isolated tumor cells, 23%). 101 (35%) of all SLN-positive patients had tumor-involved NSLNs. Three variables (tumor size, angiolymphatic invasion, and SLN metastasis size) predicted risk in all our models. RP-ROC and boosted CART stratified patients into four risk levels. MLR informed by CART was most accurate. Using two composite predictors calculated from three variables, MLR informed by CART was more accurate than the Nomogram computed using eight predictors. In our dataset, area under ROC curve (AUC) was 0.83/0.85 for MLR (n = 213/n = 171) and 0.77 for Nomogram (n = 171). When applied to an independent dataset (n = 77), AUC was 0.74 for our model and 0.62 for Nomogram. The composite predictors in our model were the product of angiolymphatic invasion and size of SLN metastasis, and the product of tumor size and square of SLN metastasis size.ConclusionWe present a new model developed from a community-based SLN database that uses only three rather than eight variables to achieve higher accuracy than the Nomogram for predicting NSLN status in two different datasets.

Project description:Purpose: Sentinel lymph node biopsy (SLNB) has emerged as the preferred standard procedure in patients with breast cancer, melanoma and other types of cancer. Herein, we developed a method to intra-operatively map SLNs and differentiate tumor metastases within SLNs at the same time, with the aim to provide more accurate and real-time intraoperative guidance. Experimental Design: Hyaluronic acid (HA), a ligand of lymphatic vessel endothelial hyaluronan receptor (LYVE)-1, is employed as a SLN mapping agent after being conjugated with a near-infrared fluorophore (Cy5.5). Different sized HAs (5, 10 and 20K) were tested in normal mice and mice with localized inflammation to optimize LN retention time and signal to background ratio. Cetuximab, an antibody against epidermal growth factor receptor (EGFR), and trastuzumab, an antibody against human epidermal growth factor receptor 2 (HER2), were labeled with near-infrared fluorophore (IRDye800) for detecting metastatic tumors. LN metastasis model was developed by hock injection of firefly luciferase engineered human head neck squamous carcinoma cancer UM-SCC-22B cells or human ovarian cancer SKOV-3 cells. The metastases within LNs were confirmed by bioluminescence imaging (BLI). IRDye800-Antibodies were intravenously administered 24 h before local administration of Cy5.5-HA. Optical imaging was then performed to identify nodal metastases. Results: Binding of HA with LYVE-1 was confirmed by ELISA and fluorescence staining. HA with a size of 10K was chosen based on the favorable migration and retention profile. After sequential administration of IRDye800-antibodies intravenously and Cy5.5-HA locally to a mouse model with LN metastases and fluorescence optical imaging, partially metastasized LNs were successfully distinguished from un-metastasized LNs and fully tumor occupied LNs, based on the different signal patterns. Conclusions: Fluorophore conjugated HA is a potential lymphatic mapping agent for SLNB. Dual-tracer imaging with the combination of lymphatic mapping agents and tumor targeting agents can identify tumor metastases within SLNs, thus may provide accurate and real-time intra-operative guidance to spare the time spent waiting for a biopsy result.

Dataset Information

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms.

Background

Methods

Results

Conclusion

Publications

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets