基于GLIM评分的帕金森病患者营养不良风险预测模型构建OACSTPCD

Objective To study a model for predicting the risk of malnutrition in patients with Parkinson's disease(PD),and to provide a basis for early nutritional intervention.Methods A total of 229 patients with PD admitted to the Department of Neurology of the Second Affiliated Hospital of Zhengzhou University from January 2020 to December 2022 were enrolled.Clinical data of patients were collected and patients were screened for nutritional risk using Global Leadership Initiative on Malnutrition.A malnutrition screening model for patients with PD was constructed by machine learning.Results The number of patients with Hoehn-Yahr(H-Y)grade 3-4 in the malnutrition group was higher than that in the normal nutrition group,and the course of the disease in the malnutrition group was longer than that in the normal nutrition group,and the differences were statistically significant(all P<0.05).The Lasso regression model and multivariate Logistic regression analysis showed that H-Y grade,course of illness(Course),body mass index(BMI),C-reactive protein(CRP)and albumin(ALB)were risk factors for malnutrition in PD patients.The nomogram model had a C-index of 0.837(95%CI:0.787-0.887)and an area under the receiver operating characteristic(AUC)curve was 0.837,indicating good predictive value.Decision curve analysis showed that when the probability value was 2%-79.0%,the patient had the highest clinical net benefit rate using this model.Conclusion The nomogram provides a practical method for effective screening of malnutrition in Parkinson's patients,and provides a basis for early nutritional intervention.