Machine learning models for prediction of lymph node metastasis in patients with T1b gastric cancer.

Abstract

The prognosis of early gastric cancer (EGC) patients is associated with lymph node metastasis (LNM). Considering the relatively high rate of LNM in T1b EGC patients, it is crucial to determine the factors associated with LNM. In this study, we constructed and validated predictive models based on machine learning (ML) algorithms for LNM in patients with T1b EGC. Data from patients with T1b gastric cancer were extracted from the Korean Gastric Cancer Association database. ML algorithms such as logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) were applied for model construction utilizing five-fold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical applicability. Moreover, external validation of XGBoost models was performed using the T1b gastric cancer database of The Catholic University Medical Center. In total, 3,468 T1b EGC patients were included in the analysis, whom 550 (15.9%) had LNM. Eleven variables were selected to construct the models. The LR, RF, XGBoost, and SVM models were established, revealing area under the receiver operating characteristic curve values of 0.8284, 0.7921, 0.8776, and 0.8323, respectively. Among the models, the XGBoost model exhibited the best predictive performance in terms of discrimination, calibration, and clinical applicability. ML models are reliable for predicting LNM in T1b EGC patients. The XGBoost model exhibited the best predictive performance and can be used by surgeons for the identification of EGC patients with a high-risk of LNM, thereby facilitating treatment selection.