Background: Develop the best machine learning (ML) model to predict nonsentinel lymph node metastases (NSLNM) in breast cancer patients.
Methods: From June 2016 to August 2022, 1005 breast cancer patients were included in this retrospective study. Univariate and multivariate analyses were performed using logistic regression. Six ML models were introduced, and their performance was compared.
Results: NSLNM occurred in 338 (33.6%) of 1005 patients. The best ML model was XGBoost, whose average area under the curve (AUC) based on 10-fold cross-verification was 0.722. It performed better than the nomogram, which was based on logistic regression (AUC: 0.764 vs. 0.706).
Conclusions: The ML model XGBoost can well predict NSLNM in breast cancer patients.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10416453 | PMC |
| http://dx.doi.org/10.1186/s12957-023-03109-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
V474I germline variant drives breast cancer metastasis.
Life Metab
February 2025
Key Laboratory of Breast Cancer in Shanghai, Department of Breast Surgery, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China.
Macro- and micro-nutrient-based multiplex stress conditions modulate in vitro tumorigenesis and aggressive behavior of breast cancer spheroids.
In Vitro Model
February 2022
Institute of Bioinformatics & Biotechnology, Savitribai Phule Pune University, Pune, India.
Purpose: The aggressive nature of a tumor is presumably its inherent one, but different environmental cues can manipulate it in many ways. In this context, the influence of metabolic stresses on tumor behavior needs to be analyzed to understand their far-reaching implications on tumor aggression and dormancy. This work investigates different facets of the tumor, such as tumorigenic capacity, tumor phenotype, and migration, under multiple metabolic stress conditions.
View Article and Find Full Text PDFErratum: Publisher Correction: The protective effect of endurance running against the pro-invasive effects of ageing in breast cancer cells and mesenchymal stem cells in vitro.
In Vitro Model
June 2024
School of Sport, Exercise and Health Sciences, Loughborough University, Towers Way, Loughborough, LE11 3TU UK.
[This corrects the article DOI: 10.1007/s44164-023-00055-y.].
View Article and Find Full Text PDFComparative study of clinical efficacy of laparoscopic proximal gastrectomy with double-channel anastomosis and tubular gastroesophageal anastomosis.
World J Gastrointest Surg
January 2025
Department of Gastrointestinal Surgery, The Second People's Hospital of Lianyungang, Lianyungang 222000, Jiangsu Province, China.
Background: According to statistics, the incidence of proximal gastric cancer has gradually increased in recent years, posing a serious threat to human health. Tubular gastroesophageal anastomosis and double-channel anastomosis are two relatively mature anti-reflux procedures. A comparison of these two surgical procedures, tubular gastroesophageal anastomosis and double-channel anastomosis, has rarely been reported.
View Article and Find Full Text PDFAn Optimized Protocol for Simultaneous Propagation of Patient-derived Organoids and Matching CAFs.
Bio Protoc
January 2025
Department of Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
Recurrent hormone receptor-positive (HR+) breast cancer is a leading cause of cancer mortality in women. Recurrence and resistance to targeted therapies have been difficult to study due to the long clinical course of the disease, the complex nature of resistance, and the lack of clinically relevant model systems. Existing models are limited to a few HR+ cell lines, organoid models, and patient-derived xenograft models, all lacking components of the human tumor microenvironment.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!