Predicting lymph node metastasis in non-small cell lung cancer using clinical and PET/CT-derived morphological features: An interpretable machine-learning study
- 1The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University/Hunan Cancer Hospital, Changsha, Hunan, People’s Republic of China
- 2Department of Radiological Diagnosis, The 970 Hospital of the Joint Logistics Support Force of the People’s Liberation Army of China, Yantai City, Shandong Province, China
- 3Department of Clinical Nursing, Xiangya Hospital, Central South University, Changsha, China
Abstract
Background: Accurate prediction of lymph node metastasis (LNM) in non-small cell lung cancer (NSCLC) is crucial for staging and treatment planning. This study aimed to establish a standardized machine learning workflow based on routinely available clinical, serological, and PET/CT-derived parameters to enhance preoperative LNM risk stratification. Methods: This retrospective study included 255 patients with histologically confirmed NSCLC, all of whom underwent systematic lymph-node dissection. Patients were randomly divided, with stratification by pathological lymph-node status, into a training cohort (n = 178) and an internal held-out test test cohort (n = 77). Candidate predictors were screened using univariable and multivariable logistic regression in the training cohort. Six machine-learning algorithms were trained and optimized using repeated nested five-fold cross-validation. After model development was completed, all six models were applied without modification to the test cohort. Test-set AUCs were compared using paired DeLong tests with Holm correction. The primary model was further evaluated for calibration, clinical utility, and feature contribution using SHAP. A conventional multivariable logistic regression model using the same four predictors was added as a simple reference model, and its discrimination and calibration were compared with those of XGBoost. Results: Central tumor location, elevated carcinoembryonic antigen, elevated squamous cell carcinoma antigen, and solid nodule status were retained as predictors; none of the quantitative PET metabolic parameters remained independently associated with LNM. XGBoost achieved the highest cross-validated AUC among the six candidate machine-learning algorithms in the training cohort (0.735; 95% CI, 0.653–0.813) and was therefore designated the primary model. In the internal held-out test cohort, XGBoost achieved an AUC of 0.747 (95% CI, 0.631–0.846). The conventional logistic regression reference model achieved a test AUC of 0.733 (95% CI, 0.612–0.841), with no significant difference from XGBoost (DeLong P = 0.301). Its Brier score was 0.152, compared with 0.198 for XGBoost. Conclusion: XGBoost model showed moderate discrimination and a high negative predictive value for pathological LNM in NSCLC. However, its limited positive predictive value and the absence of significant differences among the candidate algorithms support cautious interpretation. External multicenter evaluation is required before clinical implementation.
Related
- An interpretable machine learning model for MRI-based morphological classification of lumbar disc herniation using functional biomechanical features.
- Cumulative Sonographic Features From the Morphological Uterus Sonographic Assessment (MUSA) System and Clinical Severity of Adenomyosis in Congolese Women: A Multicenter Study in Kinshasa, Democratic Republic of the Congo
- A Pathological Image-Based Pathomics Signature Combined with Clinicopathological Features for Predicting Lymph Node Metastasis in Esophageal Squamous Cell Carcinoma: A Development and External Validation Study
- The clinical value of ultrasound radiomics combined with clinical data nomogram in predicting cervical lymph node metastasis of papillary thyroid carcinoma.
- Development and internal validation of a clinical-MRI nomogram for predicting lymph node metastasis in rectal adenocarcinoma.
BibTeX
@article{xu2026predicting,
title = {{Predicting lymph node metastasis in non-small cell lung cancer using clinical and PET/CT-derived morphological features: An interpretable machine-learning study}},
author = {Yunchao Xu and Jiajun Hao and Yujiao Dou and Biao Zeng},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0361043},
url = {https://doi.org/10.1371/journal.pone.0361043},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Predicting lymph node metastasis in non-small cell lung cancer using clinical and PET/CT-derived morphological features: An interpretable machine-learning study
AU - Yunchao Xu
AU - Jiajun Hao
AU - Yujiao Dou
AU - Biao Zeng
PY - 2026
DA - 2026/10/15
JO - PLOS One
DO - 10.1371/journal.pone.0361043
UR - https://doi.org/10.1371/journal.pone.0361043
AB - Background: Accurate prediction of lymph node metastasis (LNM) in non-small cell lung cancer (NSCLC) is crucial for staging and treatment planning. This study aimed to establish a standardized machine learning workflow based on routinely available clinical, serological, and PET/CT-derived parameters to enhance preoperative LNM risk stratification. Methods: This retrospective study included 255 patients with histologically confirmed NSCLC, all of whom underwent systematic lymph-node dissection. Patients were randomly divided, with stratification by pathological lymph-node status, into a training cohort (n = 178) and an internal held-out test test cohort (n = 77). Candidate predictors were screened using univariable and multivariable logistic regression in the training cohort. Six machine-learning algorithms were trained and optimized using repeated nested five-fold cross-validation. After model development was completed, all six models were applied without modification to the test cohort. Test-set AUCs were compared using paired DeLong tests with Holm correction. The primary model was further evaluated for calibration, clinical utility, and feature contribution using SHAP. A conventional multivariable logistic regression model using the same four predictors was added as a simple reference model, and its discrimination and calibration were compared with those of XGBoost. Results: Central tumor location, elevated carcinoembryonic antigen, elevated squamous cell carcinoma antigen, and solid nodule status were retained as predictors; none of the quantitative PET metabolic parameters remained independently associated with LNM. XGBoost achieved the highest cross-validated AUC among the six candidate machine-learning algorithms in the training cohort (0.735; 95% CI, 0.653–0.813) and was therefore designated the primary model. In the internal held-out test cohort, XGBoost achieved an AUC of 0.747 (95% CI, 0.631–0.846). The conventional logistic regression reference model achieved a test AUC of 0.733 (95% CI, 0.612–0.841), with no significant difference from XGBoost (DeLong P = 0.301). Its Brier score was 0.152, compared with 0.198 for XGBoost. Conclusion: XGBoost model showed moderate discrimination and a high negative predictive value for pathological LNM in NSCLC. However, its limited positive predictive value and the absence of significant differences among the candidate algorithms support cautious interpretation. External multicenter evaluation is required before clinical implementation.
SN - 1932-6203
ER -