Suppr
超能文献

基于机器学习的PG-SGA≥4肿瘤患者的快速识别：一项前瞻性研究。

Rapid identification of tumor patients with PG-SGA ≥ 4 based on machine learning: a prospective study.

作者信息

Qian Gui, Jiaxin Huang, Minghua Cong, Beijia Liu, Yinfeng Li, Guiyu Huang, Mingxue Yang, Xiaoli Tang, Hongyan Yan

机构信息

School of Medicine, University of Electronic Science and Technology of China, Chengdu, China.

Department of Comprehensive Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

出版信息

BMC Cancer. 2025 May 20;25(1):902. doi: 10.1186/s12885-025-14222-9.

DOI:10.1186/s12885-025-14222-9

PMID:40394504

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12093709/

Abstract

BACKGROUND

Malnutrition is common in cancer patients and worsens treatment and prognosis. The Patient-Generated Subjective Global Assessment (PG-SGA) is the best tool to evaluate malnutrition, but it is complicated has limited its routine clinical use.

METHODS

We reviewed 798 records from 416 cancer patients treated at our hospital from July 2022 to March 2024. We used machine learning methods like XGBoost and Random Forest to find important factors linked to PG-SGA scores of 4 or higher. We confirmed the most important factors with logistic regression analysis.

RESULTS

Among all models, XGBoost and Random Forest models perform the best, with the area under the curve (AUC) reaching of 0.75 and 0.77. Multivariate logistic regression analysis identified body mass index (BMI) (OR = 0.82, 95%CI 0.66-0.99; P = 0.045), handgrip strength (HGS) (OR = 0.89, 95%CI 0.82-0.96; P = 0.004), fat-free mass index (FFMI) (OR = 1.36, 95%CI 1.01-1.88; P = 0.045), and bedridden status (OR = 3.16, 95%CI 1.17-9.14; P = 0.026) as key predictors for PG-SGA scores of ≥ 4.

CONCLUSION

BMI, HGS, FFMI, and bedridden status were identified as practical indicators to efficiently screen patients likely to have PG-SGA scores ≥ 4.

摘要

背景

营养不良在癌症患者中很常见，会使治疗和预后恶化。患者主观整体评定法（PG-SGA）是评估营养不良的最佳工具，但因其操作复杂限制了其在临床常规使用。

方法

我们回顾了2022年7月至2024年3月在我院接受治疗的416例癌症患者的798份记录。我们使用XGBoost和随机森林等机器学习方法来找出与PG-SGA评分≥4相关的重要因素。我们通过逻辑回归分析确认了最重要的因素。

结果

在所有模型中，XGBoost和随机森林模型表现最佳，曲线下面积（AUC）分别达到0.75和0.77。多变量逻辑回归分析确定体重指数（BMI）（比值比[OR]=0.82，95%置信区间[CI]0.66-0.99；P=0.045）、握力（HGS）（OR=0.89，95%CI0.82-0.96；P=0.004）、去脂体重指数（FFMI）（OR=1.36，95%CI1.01-1.88；P=0.045）和卧床状态（OR=3.16，95%CI1.17-9.14；P=0.026）是PG-SGA评分≥4的关键预测因素。