Full
Outline
To investigate the predictive value of machine learning methods for non-alcoholic fatty liver disease(NAFLD) in non-obese populations and to analyze the risk factors for NAFLD within this group.
Data on 43 variables,including body composition, medical history, and laboratory test results, were retrospectively collected and screened from 1 517 non-obese subjects at the Physical Examination Center of Xiyuan Hospital, China Academy of Chinese Medical Sciences,between January 2021 and December 2024. The outcome indicator was the diagnosis of NAFLD by abdominal ultrasonography,based on which subjects were stratified into NAFLD and non-NAFLD groups. Predictors were screened using univariate analysis, lasso regression, and multivariable logistic regression analysis. Seven machine learning methods including logistic regression, decision tree, random forest, extreme gradient boosting (XGBoost), light hradient boosting machine(LightGBM),support vector machine(SVM), and artificial neural network(ANN), were employed to develop and validate prediction models for NAFLD in non-obese individuals. The shapley additive explanations (SHAP) method was used to interpret variable contributions.
Among the 1 517 included subjects, 215 (14.2%) were diagnosed with NAFLD. Ten independent predictors were identified. The area under the curve (AUC) values for the seven prediction models on the validation set ranged from 0.876 to 0.924. The model based on XGBoost demonstrated the best discriminative ability (AUC=0.924, 95% CI: 0.895-0.949). The SHAP value-based variable importance ranking identified phase angle, the ZJU index, and UHR as the top three significant predictors.
The XGBoost model, constructed using routine physical examination data, exhibits high predictive performance for NAFLD incidence in non-obese populations. Its interpretable features facilitate the clinical prioritization of high-risk individuals.
17
8
| 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
