Development and Assessment of Assisted Diagnosis Models Using Machine Learning for Identifying Elderly Patients With Malnutrition: Cohort Study

Overview

Journal J Med Internet Res

Publisher JMIR Publications

Specialty Medical Informatics

Date 2023 Mar 14

PMID 36917167

Authors

Xue Wang

Fengchun Yang

Mingwei Zhu

Hongyuan Cui

Junmin Wei

Jiao Li

Wei Chen

Affiliations

Soon will be listed here.

Abstract

Background: Older patients are at an increased risk of malnutrition due to many factors related to poor clinical outcomes.

Objective: This study aims to develop an assisted diagnosis model using machine learning (ML) for identifying older patients with malnutrition and providing the focus of individualized treatment.

Methods: We reanalyzed a multicenter, observational cohort study including 2660 older patients. Baseline malnutrition was defined using the global leadership initiative on malnutrition (GLIM) criteria, and the study population was randomly divided into a derivation group (2128/2660, 80%) and a validation group (532/2660, 20%). We applied 5 ML algorithms and further explored the relationship between features and the risk of malnutrition by using the Shapley additive explanations visualization method.

Results: The proposed ML models were capable to identify older patients with malnutrition. In the external validation cohort, the top 3 models by the area under the receiver operating characteristic curve were light gradient boosting machine (92.1%), extreme gradient boosting (91.9%), and the random forest model (91.5%). Additionally, the analysis of the importance of features revealed that BMI, weight loss, and calf circumference were the strongest predictors to affect GLIM. A BMI of below 21 kg/m2 was associated with a higher risk of GLIM in older people.

Conclusions: We developed ML models for assisting diagnosis of malnutrition based on the GLIM criteria. The cutoff values of laboratory tests generated by Shapley additive explanations could provide references for the identification of malnutrition.

Trial Registration: Chinese Clinical Trial Registry ChiCTR-EPC-14005253; https://www.chictr.org.cn/showproj.aspx?proj=9542.

Citing Articles

An interpretable machine learning model based on computed tomography radiomics for predicting programmed death ligand 1 expression status in gastric cancer.

Dai L, Yin J, Xin X, Yao C, Tang Y, Xia X Cancer Imaging. 2025; 25(1):31.

PMID: 40075494 PMC: 11905525. DOI: 10.1186/s40644-025-00855-3.

Identification of key factors for malnutrition diagnosis in chronic gastrointestinal diseases using machine learning underscores the importance of GLIM criteria as well as additional parameters.

Rischmuller K, Caton V, Wolfien M, Ehlers L, van Welzen M, Brauer D Front Nutr. 2024; 11:1479501.

PMID: 39726873 PMC: 11670747. DOI: 10.3389/fnut.2024.1479501.

Predictive modeling of lean body mass, appendicular lean mass, and appendicular skeletal muscle mass using machine learning techniques: A comprehensive analysis utilizing NHANES data and the Look AHEAD study.

Olshvang D, Harris C, Chellappa R, Santhanam P PLoS One. 2024; 19(9):e0309830.

PMID: 39240958 PMC: 11379308. DOI: 10.1371/journal.pone.0309830.

Investigating Frailty, Polypharmacy, Malnutrition, Chronic Conditions, and Quality of Life in Older Adults: Large Population-Based Study.

Liu Y, Huang L, Hu F, Zhang X JMIR Public Health Surveill. 2024; 10:e50617.

PMID: 39145920 PMC: 11512125. DOI: 10.2196/50617.

Artificial Intelligence in Malnutrition: A Systematic Literature Review.

Janssen S, Bouzembrak Y, Tekinerdogan B Adv Nutr. 2024; 15(9):100264.

PMID: 38971229 PMC: 11403436. DOI: 10.1016/j.advnut.2024.100264.

References

Warmuth M, Liao J, Ratsch G, Mathieson M, Putta S, Lemmen C . Active learning with support vector machines in the drug discovery process. J Chem Inf Comput Sci. 2003; 43(2):667-73. DOI: 10.1021/ci025620t. View

De van der Schueren M, Keller H, Cederholm T, Barazzoni R, Compher C, Correia M . Global Leadership Initiative on Malnutrition (GLIM): Guidance on validation of the operational criteria for the diagnosis of protein-energy malnutrition in adults. Clin Nutr. 2020; 39(9):2872-2880. DOI: 10.1016/j.clnu.2019.12.022. View

Zhu M, Wei J, Chen W, Yang X, Cui H, Zhu S . Nutritional Risk and Nutritional Status at Admission and Discharge among Chinese Hospitalized Patients: A Prospective, Nationwide, Multicenter Study. J Am Coll Nutr. 2017; 36(5):357-363. DOI: 10.1080/07315724.2017.1304293. View

. Ageing and health--an agenda half completed. Lancet. 2015; 386(10003):1509. DOI: 10.1016/S0140-6736(15)00521-8. View

Zhang X, Tang M, Zhang Q, Zhang K, Guo Z, Xu H . The GLIM criteria as an effective tool for nutrition assessment and survival prediction in older adult cancer patients. Clin Nutr. 2020; 40(3):1224-1232. DOI: 10.1016/j.clnu.2020.08.004. View

Cederholm T, Jensen G, Correia M, Gonzalez M, Fukushima R, Higashiguchi T . GLIM criteria for the diagnosis of malnutrition - A consensus report from the global clinical nutrition community. Clin Nutr. 2018; 38(1):1-9. DOI: 10.1016/j.clnu.2018.08.002. View

Yin L, Song C, Cui J, Lin X, Li N, Fan Y . A fusion decision system to identify and grade malnutrition in cancer patients: Machine learning reveals feasible workflow from representative real-world data. Clin Nutr. 2021; 40(8):4958-4970. DOI: 10.1016/j.clnu.2021.06.028. View

Yin L, Lin X, Li N, Zhang M, He X, Liu J . Evaluation of the Global Leadership Initiative on Malnutrition Criteria Using Different Muscle Mass Indices for Diagnosing Malnutrition and Predicting Survival in Lung Cancer Patients. JPEN J Parenter Enteral Nutr. 2020; 45(3):607-617. DOI: 10.1002/jpen.1873. View

Skeie E, Tangvik R, Nymo L, Harthug S, Lassen K, Viste A . Weight loss and BMI criteria in GLIM's definition of malnutrition is associated with postoperative complications following abdominal resections - Results from a National Quality Registry. Clin Nutr. 2019; 39(5):1593-1599. DOI: 10.1016/j.clnu.2019.07.003. View

10.

Morley J . Anorexia of ageing: a key component in the pathogenesis of both sarcopenia and cachexia. J Cachexia Sarcopenia Muscle. 2017; 8(4):523-526. PMC: 5566640. DOI: 10.1002/jcsm.12192. View

11.

Liu H, Jiao J, Zhu C, Zhu M, Wen X, Jin J . Potential associated factors of functional disability in Chinese older inpatients: a multicenter cross-sectional study. BMC Geriatr. 2020; 20(1):319. PMC: 7650523. DOI: 10.1186/s12877-020-01738-x. View

12.

. How to cope with an ageing population. Lancet. 2013; 382(9900):1225. DOI: 10.1016/S0140-6736(13)62080-2. View

13.

Huang D, Yu D, Song H, Wang W, Luo X, Wu G . The relationship between the GLIM-defined malnutrition, body composition and functional parameters, and clinical outcomes in elderly patients undergoing radical gastrectomy for gastric cancer. Eur J Surg Oncol. 2021; 47(9):2323-2331. DOI: 10.1016/j.ejso.2021.02.032. View

14.

Allard J, Keller H, Gramlich L, Jeejeebhoy K, Laporte M, Duerksen D . GLIM criteria has fair sensitivity and specificity for diagnosing malnutrition when using SGA as comparator. Clin Nutr. 2020; 39(9):2771-2777. DOI: 10.1016/j.clnu.2019.12.004. View

15.

Agarwal E, Miller M, Yaxley A, Isenring E . Malnutrition in the elderly: a narrative review. Maturitas. 2013; 76(4):296-302. DOI: 10.1016/j.maturitas.2013.07.013. View

16.

Shi H, Yang D, Tang K, Hu C, Li L, Zhang L . Explainable machine learning model for predicting the occurrence of postoperative malnutrition in children with congenital heart disease. Clin Nutr. 2021; 41(1):202-210. DOI: 10.1016/j.clnu.2021.11.006. View

17.

Loh H, Ooi C, Seoni S, Barua P, Molinari F, Rajendra Acharya U . Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022). Comput Methods Programs Biomed. 2022; 226:107161. DOI: 10.1016/j.cmpb.2022.107161. View

18.

Fang E, Scheibye-Knudsen M, Jahn H, Li J, Ling L, Guo H . A research agenda for aging in China in the 21st century. Ageing Res Rev. 2015; 24(Pt B):197-205. PMC: 5179143. DOI: 10.1016/j.arr.2015.08.003. View

19.

Yin L, Lin X, Liu J, Li N, He X, Zhang M . Classification Tree-Based Machine Learning to Visualize and Validate a Decision Tool for Identifying Malnutrition in Cancer Patients. JPEN J Parenter Enteral Nutr. 2021; 45(8):1736-1748. DOI: 10.1002/jpen.2070. View

20.

Gunning D, Stefik M, Choi J, Miller T, Stumpf S, Yang G . XAI-Explainable artificial intelligence. Sci Robot. 2020; 4(37). DOI: 10.1126/scirobotics.aay7120. View