常州大学学报（自然科学版）2026，Vol.38Issue(3)：82-92,11.DOI:10.3969/j.issn.2095-0411.2026.03.010
基于集成学习白蛋白水平预测模型的可解释性研究
Research on the interpretability of an ensemble learning-based model for predicting albumin levels
摘要
Abstract
Albumin level is an important indicator of nutritional risk of patients.Aiming at the prob-lems of the lack of albumin level prediction dataset,data redundancy and lack of interpretability of studies,a complete nutrition support dataset was constructed and an integrated learning framework was proposed for albumin level prediction in elderly patients.In this study,the XGBoost model opti-mized by Tree-structured Parzen Estimator(TPE)algorithm(TPE-XGBoost)was compared with other 4 baseline models to prove its performance,and the model interpretation algorithm SHapley Ad-ditive exPlanations(SHAP)was combined to select features and enhance the interpretability of the model from the global and local levels.The results showed that the TPE-XGBoost model was simple and effective,and the prediction accuracy reached 87.8%.In addition,the interpretable analysis of SHAP obtained 4 key factors and the threshold effects of 2 factors could be mutually verified with clinical studies.关键词
白蛋白水平预测/模型可解释性/XGBoost/模型解释算法/树结构的贝叶斯优化/集成学习Key words
albumin level prediction/model interpretability/XGBoost/SHAP/TPE/ensemble learning分类
医药卫生引用本文复制引用
督静雯,滕飞,林宁,李运明..基于集成学习白蛋白水平预测模型的可解释性研究[J].常州大学学报（自然科学版）,2026,38(3):82-92,11.基金项目
四川省干部保健科研课题资助项目(川干研2051-1303). （川干研2051-1303）
