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

OBJECTIVE: 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). METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

Integrating Ecosystem Health and Services for Assessing Ecological Risk and its Response to Typical Land-Use Patterns in the Eco-fragile Region, North China.

Changes in land-use patterns may increase the ecological risks faced by Eco-Fragile regions. It is vital for regional ecological restoration and management of Eco-Fragile regions to reasonably assess ecological risk and study its response to typical land-use patterns. Existing study on regional ecological risk largely ignored the internal representation of ecosystem health and ecosystem services to ecological risk, and also ignored the internal relationship between ecological risk and land use patterns. This study developed a regional ecological assessment model by describing the relationship between ecosystem health, ecosystem services and ecological risks. Among them, the ecosystem health assessment used the Net Primary Productivity, landscape index and ecosystem elasticity coefficient based on different land use patterns to build Vigor-Organization-Resilience (VOR) model, and the improved equivalent factor method was used to calculate the ecosystem service value. Taking the Fen River Basin (FRB), a typical Eco-Fragile region of the Loess Plateau, as a study region, spatial auto-correlation analysis was used to reveal the temporal and spatial changes and spatial clustering characteristics of regional ecological risk, and regression analysis was used to study the relationship between typical land use patterns and ecological risks, which was included in the consideration of ecological and environmental risk management strategies. The results show that the regions with high ecological risk are mainly distributed in the middle and southwest of the FRB; the regions with low ecological risk are mainly distributed in the north, east and west of the FRB. Both high-risk and low-risk areas show significant spatial clustering effects. The change of ecological risk in FRB is related to the land use patterns. The ecological risk is negatively related to the expansion of construction land and cultivated land at the county and patch scales. On this basis, the environmental management strategies at different scales are discussed. This study can helpful deepen the understanding of the impact of land use patterns on ecological risk, and can also provide important reference for regional ecological risk management and land use policies.