Full
Outline
To evaluate the predictive value of various TyG-obesity indices (TyG-BMI, TyG-WHR, TyG-LAP, TyG-BRI, TyG-CVAI, TyG-BAI) for hyperuricemia in community residents.
Using data from the 2020 cross-sectional survey of the Southwest China Natural Population Cohort, 960 participants were included. A base model was constructed using the random forest algorithm. The predictive performance of models incorporating different TyG-obesity indices was evaluated using the area under the ROC curve, accuracy, precision, recall, and the F1-score.
Among the TyG-obesity indices, the models incorporating TyG-LAP and TyG-CVAI showed the best predictive performance, both with an AUC of 0.716. The TyG-LAP model had slightly higher accuracy and F1-score(0.667 and 0.543), while the TyG-CVAI model achieved the highest recall (0.807). Feature importance analysis indicated that TyG-obesity indices were the important predictors in models incorporating demographic characteristics and behavioral and lifestyle factors.
TyG-obesity indices, particularly TyG-LAP and TyG-CVAI, demonstrate strong predictive ability for hyperuricemia in community residents and may serve as useful tools for community screening and identification of high-risk groups.
11
6
| 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
