Predictive model for assessing malnutrition in elderly hospitalized cancer patients: A machine learning approach

•The study develops a prediction model specifically tailored to accurately assess the malnutrition status of elderly hospitalized cancer patients.•It demonstrates that the XGBoost model is exceptionally effective in identifying malnutrition, providing oncologists with a valuable tool for managing nutritional risks and supporting elderly cancer patients.•The findings underscore the significance of incorporating machine learning techniques into nutritional assessment strategies for elderly cancer patients. Malnutrition is prevalent among elderly cancer patients. This study aims to develop a predictive model for malnutrition in hospitalized elderly cancer patients. Data from January 2022 to January 2023 on cancer patients aged 60+ were collected, involving 22 variables. Key variables were identified using the LASSO (Least Absolute Shrinkage and Selection Operator) method, and nine machine learning models were tested. SHAP was used to interpret the XGBoost model. Malnutrition prevalence was assessed. Among 450 participants, 46.4 % were malnourished. Key predictors identified were ADL (Activities of Daily Living), ALB (Albumin), BMI (Body Mass Index) and age. XGBoost had the highest AUC of 0.945, accuracy of 0.872, and sensitivity of 0.968. Higher ADL and age increased malnutrition risk, while lower ALB and BMI reduced it. The XGBoost model is highly effective in detecting malnutrition in elderly cancer patients, enabling early and rapid nutritional assessments.