Identification of prognostic signatures in remnant gastric cancer through an interpretable risk model based on machine learning: a multicenter cohort study

• Published in: BMC cancer 2024-04, Vol.24 (1), p.547-547, Article 547
• Main Authors: Zhan, Zhouwei, Chen, Bijuan, Cheng, Hui, Xu, Shaohua, Huang, Chunping, Zhou, Sijing, Chen, Haiting, Lin, Xuanping, Lin, Ruyu, Huang, Wanting, Ma, Xiaohuan, Fu, Yu, Chen, Zhipeng, Zheng, Hanchen, Shi, Songchang, Guo, Zengqing, Zhang, Lihui
• Format: Article
• Language: English
• Subjects: Accuracy; Aged; Algorithms; Artificial intelligence; Cancer; Care and treatment; Classification; Decision making; Ethics; Female; Forecasts and trends; Gastrectomy; Gastric cancer; Gastric Stump - pathology; Gastrointestinal surgery; Health aspects; Health risk assessment; Hospitals; Humans; Interpretable; Learning algorithms; Lymph nodes; Lymphatic system; Machine Learning; Male; Medical prognosis; Metastases; Methods; Middle Aged; Mortality; Multicenter; Oncology, Experimental; Patients; Prediction model; Prediction models; Prognosis; Regression analysis; Remnant gastric cancer; Retinal ganglion cells; Retrospective Studies; Risk assessment; Risk Assessment - methods; Risk factors; ROC Curve; Stomach cancer; Stomach Neoplasms - mortality; Stomach Neoplasms - pathology; Stomach Neoplasms - surgery; Surgical outcomes; Tumors
• ISSN: 1471-2407; 1471-2407
• DOI: 10.1186/s12885-024-12303-9

The purpose of this study was to develop an individual survival prediction model based on multiple machine learning (ML) algorithms to predict survival probability for remnant gastric cancer (RGC). Clinicopathologic data of 286 patients with RGC undergoing operation (radical resection and palliative resection) from a multi-institution database were enrolled and analyzed retrospectively. These individuals were split into training (80%) and test cohort (20%) by using random allocation. Nine commonly used ML methods were employed to construct survival prediction models. Algorithm performance was estimated by analyzing accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC), confusion matrices, five-fold cross-validation, decision curve analysis (DCA), and calibration curve. The best model was selected through appropriate verification and validation and was suitably explained by the SHapley Additive exPlanations (SHAP) approach. Compared with the traditional methods, the RGC survival prediction models employing ML exhibited good performance. Except for the decision tree model, all other models performed well, with a mean ROC AUC above 0.7. The DCA findings suggest that the developed models have the potential to enhance clinical decision-making processes, thereby improving patient outcomes. The calibration curve reveals that all models except the decision tree model displayed commendable predictive performance. Through CatBoost-based modeling and SHAP analysis, the five-year survival probability is significantly influenced by several factors: the lymph node ratio (LNR), T stage, tumor size, resection margins, perineural invasion, and distant metastasis. This study established predictive models for survival probability at five years in RGC patients based on ML algorithms which showed high accuracy and applicative value.