Full
Outline
To develop and validate a risk prediction model for social frailty inelderly patients with type 2 diabetes mellitus.
A total of 455 elderly T2DM patients hospitalized in the endocrinology department of a Grade A tertiary hospital in Hebei Province between June 2024 and February 2025 were enrolled. Based on the HALFT scale, participants were categorized into asocial frailty group (n=169) and a non-social frailty group (n=286). They were randomly divided into a training set (n=318) and a test set (n=137) in a 7:3 ratio. Univariate analysis, Lasso regression, and multivariate regression were employed to identify influencing factors for social frailty. Risk prediction models were constructed using logistic regression, XGBoost, and Random Forest.The predictive performance of the models was evaluated, and the optimal model was selected.
Multivariate logistic regression analysis revealed that education level junior high school (OR=0.272, 95% CI: 0.101-0.730); high school (OR=0.275, 95% CI: 0.140-0.540); college (OR=0.064, 95% CI: 0.010-0.424); bachelor’s degree or above (OR=0.114, 95% CI: 0.021-0.618),e-health literacy (OR=0.954, 95% CI: 0.914-0.996), and social support (OR=0.897, 95% CI: 0.840-0.958) were protective factors against social frailty in elderly T2DM patients. In contrast, glycated hemoglobin (OR=1.315, 95% CI: 1.026-1.684), number of diabetic complications 2 complications (OR=2.813, 95% CI: 1.420-5.572); ≥3 complications (OR=6.196, 95% CI: 2.769-13.863), diabetic stress moderate (OR=3.022, 95% CI: 1.134-8.050); severe (OR=7.623, 95% CI: 2.543-22.854), and depressive (OR=2.940, 95% CI: 1.576-5.486) were identified as risk factors (P<0.05). In the test set, the area under the curve (AUC) for all models exceeded 0.800, with the Random Forest model demonst-rating the best performance (AUC=0.866).
The risk prediction mode-lfor social frailty in elderly patients with type 2 diabetes, developed based on the random forest model, exhibits good predictive abilityand can serve as a reference for the early identification of high-risk patients for social frailty in this population.
43
22
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
