• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于机器学习的老年患者住院并发症预测——以 GLIM、SGA 和 ESPEN 2015 营养不良诊断为因素。

Machine Learning-Based Prediction of In-Hospital Complications in Elderly Patients Using GLIM-, SGA-, and ESPEN 2015-Diagnosed Malnutrition as a Factor.

机构信息

Department of Clinical nutrition, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing 100730, China.

The Key Laboratory of Geriatrics, National Center of Gerontology, National Health Commission, Beijing Hospital, Beijing Institute of Geriatrics, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing 100730, China.

出版信息

Nutrients. 2022 Jul 24;14(15):3035. doi: 10.3390/nu14153035.

DOI:10.3390/nu14153035
PMID:35893889
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9331502/
Abstract

BACKGROUND

Malnutrition is prevalent in elderly inpatients and is associated with various adverse outcomes during their hospital stay, but the diagnosis of malnutrition still lacks widely applicable criteria. This study aimed to investigate the association of malnutrition diagnosed with the SGA, ESPEN 2015, and GLIM criteria, respectively, with in-hospital complications in elderly patients.

METHOD

Hospitalized patients over 65 years old who had been assessed with the SGA guideline for malnutrition at admission were retrospectively recruited from a large observational cohort study conducted in 34 level-A tertiary hospitals in 18 cities in China from June to September 2014. Malnutrition was then retrospectively diagnosed using the GLIM and ESPEN 2015 criteria, respectively, for comparison with the results of the SGA scale. The risk factors for malnutrition were analyzed using logistic regression, and the value of the three diagnostic criteria in predicting the in-hospital complications was subsequently explored using multivariate regression and the random forest machine learning algorithm.

RESULTS

A total of 2526 subjects who met the inclusion and exclusion criteria of the study were selected from the 7122 patients in the dataset, with an average age of 74.63 ± 7.12 years, 59.2% male, and 94.2% married. According to the GLIM, SGA, and ESPEN 2015 criteria, the detection rates of malnutrition were 37.8% (956 subjects), 32.8% (829 subjects), and 17.0% (429 subjects), respectively. The diagnostic consistency between the GLIM and the SGA criteria is better than that between the ESPEN 2015 and the SGA criteria (Kappa statistics, 0.890 vs. 0.590). Logistic regression showed that the risk of developing complications in the GLIM-defined malnutrition patients is 2.414 times higher than that of normal patients, higher than those of the ESPEN 2015 and SGA criteria (1.786 and 1.745 times, respectively). The random forest classifications show that the GLIM criteria have a higher ability to predict complications in these elderly patients than the SGA and ESPEN 2015 criteria with a mean decrease in accuracy of 12.929, 10.251, and 5.819, respectively, and a mean decrease in Gini of 2.055, 1.817, and 1.614, respectively.

CONCLUSION

The prevalence of malnutrition diagnosed with the GLIM criteria is higher than that of the SGA and the ESPEN 2015 criteria. The GLIM criteria are better than the SGA and the ESPEN 2015 criteria for predicting in-hospital complications in elderly patients.

摘要

背景

营养不良在老年住院患者中很常见,并且与住院期间的各种不良后果有关,但营养不良的诊断仍然缺乏广泛适用的标准。本研究旨在探讨分别使用 SGA、ESPEN 2015 和 GLIM 标准诊断的营养不良与老年患者住院并发症的关系。

方法

从 2014 年 6 月至 9 月在中国 18 个城市的 34 家甲级三级医院进行的一项大型观察性队列研究中,回顾性招募了入院时根据 SGA 营养不良指南评估的年龄在 65 岁以上的住院患者。分别使用 GLIM 和 ESPEN 2015 标准回顾性诊断营养不良,以与 SGA 量表的结果进行比较。使用逻辑回归分析营养不良的危险因素,并使用多元回归和随机森林机器学习算法探讨三种诊断标准预测住院并发症的价值。

结果

从数据集中的 7122 名患者中,共选择了符合研究纳入和排除标准的 2526 名患者,平均年龄为 74.63±7.12 岁,59.2%为男性,94.2%已婚。根据 GLIM、SGA 和 ESPEN 2015 标准,营养不良的检出率分别为 37.8%(956 例)、32.8%(829 例)和 17.0%(429 例)。GLIM 与 SGA 标准之间的诊断一致性优于 ESPEN 2015 与 SGA 标准之间的诊断一致性(Kappa 统计,0.890 与 0.590)。逻辑回归显示,GLIM 定义的营养不良患者发生并发症的风险是正常患者的 2.414 倍,高于 ESPEN 2015 和 SGA 标准(分别为 1.786 和 1.745 倍)。随机森林分类显示,GLIM 标准在预测这些老年患者的并发症方面具有比 SGA 和 ESPEN 2015 标准更高的能力,准确性分别平均降低了 12.929、10.251 和 5.819,基尼系数分别平均降低了 2.055、1.817 和 1.614。

结论

GLIM 标准诊断的营养不良患病率高于 SGA 和 ESPEN 2015 标准。GLIM 标准在预测老年患者住院并发症方面优于 SGA 和 ESPEN 2015 标准。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/541782d56265/nutrients-14-03035-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/427d518a2254/nutrients-14-03035-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/954022e8f55e/nutrients-14-03035-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/541782d56265/nutrients-14-03035-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/427d518a2254/nutrients-14-03035-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/954022e8f55e/nutrients-14-03035-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6615/9331502/541782d56265/nutrients-14-03035-g003.jpg

相似文献

1
Machine Learning-Based Prediction of In-Hospital Complications in Elderly Patients Using GLIM-, SGA-, and ESPEN 2015-Diagnosed Malnutrition as a Factor.基于机器学习的老年患者住院并发症预测——以 GLIM、SGA 和 ESPEN 2015 营养不良诊断为因素。
Nutrients. 2022 Jul 24;14(15):3035. doi: 10.3390/nu14153035.
2
Machine Learning-Based Prediction of Complications and Prolonged Hospitalization with the GLIM Criteria Combinations Containing Calf Circumference in Elderly Asian Patients.基于机器学习的基于 GLIM 标准组合(包含小腿围)的老年亚洲患者并发症和住院时间延长的预测。
Nutrients. 2023 Sep 26;15(19):4146. doi: 10.3390/nu15194146.
3
Association of Malnutrition, as Defined by the PG-SGA, ESPEN 2015, and GLIM Criteria, With Complications in Esophageal Cancer Patients After Esophagectomy.根据PG-SGA、ESPEN 2015及GLIM标准定义的营养不良与食管癌患者食管切除术后并发症的相关性
Front Nutr. 2021 Apr 26;8:632546. doi: 10.3389/fnut.2021.632546. eCollection 2021.
4
Validation of the GLIM criteria for diagnosis of malnutrition and quality of life in patients with inflammatory bowel disease: A multicenter, prospective, observational study.GLIM 标准诊断炎症性肠病患者营养不良及生活质量的验证:一项多中心、前瞻性、观察性研究。
Clin Nutr. 2022 Jun;41(6):1297-1306. doi: 10.1016/j.clnu.2022.04.016. Epub 2022 Apr 21.
5
GLIM vs ESPEN criteria for the diagnosis of early malnutrition in oncological outpatients.GLIM 与 ESPEN 标准对肿瘤门诊早期营养不良的诊断价值比较。
Clin Nutr. 2021 Jun;40(6):3741-3747. doi: 10.1016/j.clnu.2021.04.025. Epub 2021 Apr 22.
6
Accuracy of three tools for malnutrition diagnosis in hospitalised patients: Comparison to subjective global assessment.三种用于住院患者营养不良诊断的工具的准确性:与主观全面评估的比较。
J Hum Nutr Diet. 2021 Dec;34(6):935-944. doi: 10.1111/jhn.12907. Epub 2021 Jun 23.
7
Malnutrition diagnosed by the Global Leadership Initiative on Malnutrition criteria as a predictor of gait ability in patients with hip fracture.全球营养不良倡议标准诊断的营养不良是髋部骨折患者步态能力的预测指标。
Injury. 2022 Oct;53(10):3394-3400. doi: 10.1016/j.injury.2022.08.004. Epub 2022 Aug 3.
8
AND-ASPEN and ESPEN consensus, and GLIM criteria for malnutrition identification in AECOPD patients: a longitudinal study comparing concurrent and predictive validity.AND-ASPEN 和 ESPEN 共识以及 GLIM 标准在 AECOPD 患者营养不良识别中的应用:一项比较同期和预测效度的纵向研究。
Eur J Clin Nutr. 2022 May;76(5):685-692. doi: 10.1038/s41430-021-01025-x. Epub 2021 Oct 26.
9
Comparison of the GLIM, ESPEN and ICD-10 Criteria to Diagnose Malnutrition and Predict 30-Day Outcomes: An Observational Study in an Oncology Population.GLIM、ESPEN 和 ICD-10 标准诊断营养不良和预测 30 天结局的比较:肿瘤人群中的一项观察性研究。
Nutrients. 2021 Jul 28;13(8):2602. doi: 10.3390/nu13082602.
10
Prevalence of malnutrition comparing the GLIM criteria, ESPEN definition and MST malnutrition risk in geriatric rehabilitation patients: RESORT.老年康复患者中 GLIM 标准、ESPEN 定义和 MST 营养风险评估比较的营养不良患病率:RESORT 研究。
Clin Nutr. 2020 Nov;39(11):3504-3511. doi: 10.1016/j.clnu.2020.03.015. Epub 2020 Mar 23.

引用本文的文献

1
A predictive model based on the GLIM diagnosis for malnutrition in older adult heart failure patients.一种基于GLIM诊断的老年心力衰竭患者营养不良预测模型。
Front Nutr. 2025 May 30;12:1551483. doi: 10.3389/fnut.2025.1551483. eCollection 2025.
2
Nomogram based on a novel nutritional immune-inflammatory status score to predict postoperative outcomes in esophageal squamous cell carcinoma.基于一种新型营养免疫炎症状态评分的列线图预测食管鳞状细胞癌术后结局
World J Gastroenterol. 2025 Jan 28;31(4):101749. doi: 10.3748/wjg.v31.i4.101749.
3
Prevalence of malnutrition among adult inpatients in China: a nationwide cross-sectional study.

本文引用的文献

1
Accuracy of the GLIM criteria for diagnosing malnutrition: A systematic review and meta-analysis.GLIM 标准诊断营养不良的准确性:系统评价和荟萃分析。
Clin Nutr. 2022 Jun;41(6):1208-1217. doi: 10.1016/j.clnu.2022.04.005. Epub 2022 Apr 11.
2
Guidance for assessment of the muscle mass phenotypic criterion for the Global Leadership Initiative on Malnutrition (GLIM) diagnosis of malnutrition.用于评估全球营养不足倡议(GLIM)营养不良诊断中肌肉量表型标准的指导意见。
Clin Nutr. 2022 Jun;41(6):1425-1433. doi: 10.1016/j.clnu.2022.02.001. Epub 2022 Apr 19.
3
Utilization and validation of the Global Leadership Initiative on Malnutrition (GLIM): A scoping review.
中国成年住院患者的营养不良患病率:一项全国性横断面研究。
Sci China Life Sci. 2025 May;68(5):1487-1497. doi: 10.1007/s11427-023-2619-7. Epub 2025 Jan 21.
4
Artificial Intelligence in Malnutrition: A Systematic Literature Review.人工智能在营养不良中的应用:系统文献综述。
Adv Nutr. 2024 Sep;15(9):100264. doi: 10.1016/j.advnut.2024.100264. Epub 2024 Jul 4.
5
Drug Burden Index Is a Modifiable Predictor of 30-Day Hospitalization in Community-Dwelling Older Adults With Complex Care Needs: Machine Learning Analysis of InterRAI Data.药物负担指数是具有复杂护理需求的社区居住老年人 30 天住院的可修正预测指标:InterRAI 数据分析的机器学习
J Gerontol A Biol Sci Med Sci. 2024 Aug 1;79(8). doi: 10.1093/gerona/glae130.
6
Predictors of micronutrient deficiency among children aged 6-23 months in Ethiopia: a machine learning approach.埃塞俄比亚6至23个月儿童微量营养素缺乏的预测因素:一种机器学习方法
Front Nutr. 2024 Jan 5;10:1277048. doi: 10.3389/fnut.2023.1277048. eCollection 2023.
7
Machine Learning-Based Prediction of Complications and Prolonged Hospitalization with the GLIM Criteria Combinations Containing Calf Circumference in Elderly Asian Patients.基于机器学习的基于 GLIM 标准组合(包含小腿围)的老年亚洲患者并发症和住院时间延长的预测。
Nutrients. 2023 Sep 26;15(19):4146. doi: 10.3390/nu15194146.
8
Application of machine learning approaches in predicting clinical outcomes in older adults - a systematic review and meta-analysis.机器学习方法在预测老年人临床结局中的应用 - 系统评价和荟萃分析。
BMC Geriatr. 2023 Sep 14;23(1):561. doi: 10.1186/s12877-023-04246-w.
9
Prevalence of malnutrition based on global leadership initiative in malnutrition criteria for completeness of diagnosis and future risk of malnutrition based on current malnutrition diagnosis: systematic review and meta-analysis.基于全球营养不良领导倡议标准的营养不良患病率用于诊断完整性以及基于当前营养不良诊断的未来营养不良风险:系统评价与荟萃分析
Front Nutr. 2023 Jul 4;10:1174945. doi: 10.3389/fnut.2023.1174945. eCollection 2023.
利用和验证全球营养不良领导倡议 (GLIM):范围综述。
Clin Nutr. 2022 Mar;41(3):687-697. doi: 10.1016/j.clnu.2022.01.018. Epub 2022 Feb 1.
4
Validation of GLIM malnutrition criteria in cancer patients undergoing major abdominal surgery: A large-scale prospective study.GLIM 营养不良标准在接受大腹部手术的癌症患者中的验证:一项大规模前瞻性研究。
Clin Nutr. 2022 Mar;41(3):599-609. doi: 10.1016/j.clnu.2022.01.010. Epub 2022 Jan 13.
5
Influence of Malnutrition According to the GLIM Criteria on the Clinical Outcomes of Hospitalized Patients With Cancer.根据GLIM标准的营养不良对癌症住院患者临床结局的影响。
Front Nutr. 2021 Dec 24;8:774636. doi: 10.3389/fnut.2021.774636. eCollection 2021.
6
Controlling Nutritional Status Score as a Predictive Marker of In-hospital Mortality in Older Adult Patients.控制营养状况评分作为老年患者院内死亡率的预测指标
Front Nutr. 2021 Sep 20;8:738045. doi: 10.3389/fnut.2021.738045. eCollection 2021.
7
Diagnostic Performance of SGA, PG-SGA and MUST for Malnutrition Assessment in Adult Cancer Patients: A Systematic Literature Review and Hierarchical Bayesian Meta-Analysis.SGA、PG-SGA 和 MUST 用于评估成年癌症患者营养不良的诊断性能:系统文献回顾和分层贝叶斯荟萃分析。
Nutr Cancer. 2022;74(3):903-915. doi: 10.1080/01635581.2021.1942080. Epub 2021 Jun 30.
8
Association of Malnutrition, as Defined by the PG-SGA, ESPEN 2015, and GLIM Criteria, With Complications in Esophageal Cancer Patients After Esophagectomy.根据PG-SGA、ESPEN 2015及GLIM标准定义的营养不良与食管癌患者食管切除术后并发症的相关性
Front Nutr. 2021 Apr 26;8:632546. doi: 10.3389/fnut.2021.632546. eCollection 2021.
9
Predictive Value of the GLIM Criteria in Chinese Community-Dwelling and Institutionalized Older Adults Aged 70 Years and Over.GLIM 标准在 70 岁及以上中国社区居住和机构居住的老年人中的预测价值。
J Nutr Health Aging. 2021;25(5):645-652. doi: 10.1007/s12603-021-1610-x.
10
Functional Frailty, Dietary Intake, and Risk of Malnutrition. Are Nutrients Involved in Muscle Synthesis the Key for Frailty Prevention?功能性虚弱、饮食摄入与营养不良风险。参与肌肉合成的营养素是预防虚弱的关键吗?
Nutrients. 2021 Apr 8;13(4):1231. doi: 10.3390/nu13041231.