Survival Modelling Using Machine Learning and Immune-Nutritional Profiles in Advanced Gastric Cancer on Home Parenteral Nutrition.

Background/

Objectives

Patients with stage IV gastric cancer who develop chronic intestinal failure require home parenteral nutrition (HPN). This study aimed to evaluate the prognostic relevance of nutritional and immune-inflammatory biomarkers and to construct an individualised survival prediction model using machine learning techniques.

Methods

A secondary analysis was performed on a cohort of 410 patients with TNM stage IV gastric adenocarcinoma who initiated HPN between 2015 and 2023. Nutritional and inflammatory indices, including the Controlling Nutritional Status (CONUT) score and lymphocyte-to-monocyte ratio (LMR), were assessed. Independent prognostic factors were identified using Cox proportional hazards models. A Random Survival Forest (RSF) model was constructed to estimate survival probabilities and quantify variable importance.

Results

Both the CONUT score and LMR were independently associated with overall survival. In multivariate analysis, higher CONUT scores were linked to increased mortality risk (HR = 1.656, 95% CI: 1.306-2.101, p < 0.001), whereas higher LMR values were protective (HR = 0.632, 95% CI: 0.514-0.777, p < 0.001). The RSF model demonstrated strong predictive accuracy (C-index: 0.985-0.986) and effectively stratified patients by survival risk. The CONUT score exerted the greatest prognostic influence, with the LMR providing additional discriminatory value. A gradual decline in survival probability was observed with an increasing CONUT score and a decreasing LMR.

Conclusions

The application of machine learning to immune-nutritional data offers a robust tool for predicting survival in patients with advanced gastric cancer requiring HPN. This approach may enhance risk stratification, support individualised clinical decision-making regarding nutritional interventions, and inform treatment intensity adjustment.