Related Experiment Video
Updated: Aug 14, 2026
07:13
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Integration of Preoperative Neutrophil-to-Lymphocyte Ratio into Machine Learning Models for Predicting Lymph Node
Yaqi Zhang1,2,3, Yujing He1,2,3, Ziyu Wang4
1Department of Colorectal Surgery, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou 310016, China.
Cancers
|August 13, 2026
Summary
Elevated preoperative neutrophil-to-lymphocyte ratio (NLR) independently predicts lymph node metastasis (LNM) in T1 colorectal cancer (CRC). Machine learning models integrating NLR offer accurate risk stratification for T1 CRC patients.
Area of Science:
- Oncology
- Biomarkers
- Machine Learning
Background:
- Accurate prediction of lymph node metastasis (LNM) is crucial for T1 colorectal cancer (CRC) treatment.
- The neutrophil-to-lymphocyte ratio (NLR) is an inflammatory biomarker, but its role in predicting LNM in T1 CRC within machine learning (ML) models is unclear.
Purpose of the Study:
- To evaluate the independent predictive value of preoperative NLR for LNM in T1 CRC.
- To develop and validate interpretable ML models for stratifying LNM risk in T1 CRC.
Main Methods:
- Retrospective analysis of 533 T1 CRC patients.
- Calculation of NLR and identification of independent predictors using multivariable logistic regression.
- Development and validation of six ML models (LR, RF, XGBoost, LightGBM, CatBoost, LR-Spline) with SHAP for interpretability.
Main Results:
- Elevated preoperative NLR was an independent predictor of LNM (aOR=2.83, P=0.002).
- The optimized LightGBM model achieved an AUC of 0.768, demonstrating superior performance and clinical utility.
- NLR association with LNM was consistent across subgroups.
Conclusions:
- Preoperative NLR is a robust, independent predictor of LNM in T1 CRC.
- An optimized LightGBM model integrating NLR and clinicopathological data provides accurate risk stratification.
- This approach may refine surgical decisions and prevent overtreatment in low-risk T1 CRC patients.