Full
Outline
To investigate the influencing factors of frailty among rural elderly people,and to construct,verify and compare frailty risk prediction models based on multiple machine learning algorithms,so as to provide a scientific basis for the early identification and precise prevention of frailty.
From July to September 2023,using a multi-stage stratified cluster random sampling strategy,a total of 1 366 elderly people from 13 rural areas were selected as the research subjects.They were randomly divided into the training set(n=957) and the internal validation set(n=409) at a ratio of 7∶3.In July 2024,a total of 491 rural elderly people were selected as the external validation set.In this study,whether frailty occurs was used as the dependent variable.Variable selection was completed through single-factor analysis and LASSO regression.Then five machine learning methods including random forest(RF),extreme gradient boosting algorithm(XGBoost),artificial neural network(ANN),support vector machine(SVM),and Logistic regression(LR) were used to construct the prediction model.The core evaluation indicators were sensitivity,specificity,area under the receiver operating characteristic curve,and classification accuracy rate.The clinical practicality of the model was evaluated by the decision curve analysis.The performance of each frailty risk prediction model was comprehensively evaluated to determine the optimal model.
The incidence rate of frailty among rural elderly people was 27.4%.LASSO regression ultimately included sleep quality,depression status,anxiety status,fall risk and physical condition as key predictors.After internal and external verification and comprehensive evaluation by multiple indicators,the XGBoost model performed the best.
The incidence of frailty among rural elderly people is relatively high.There are numerous influencing factors.The frailty risk prediction model based on XGBoost algorithm has the best performance.It could provide a scientific and effective tool for frailty risk screening and precise intervention.It has high clinical application value.
49
21
| 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
