AUTHOR=Zhu Bin , Yang Li , Wu Mingfen , Wu Qiao , Liu Kejia , Li Yansheng , Guo Wei , Zhao Zhigang 

TITLE=Prediction of hyperuricemia in people taking low-dose aspirin using a machine learning algorithm: a cross-sectional study of the National Health and Nutrition Examination Survey

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 14 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2023.1276149

DOI=10.3389/fphar.2023.1276149

ISSN=1663-9812

ABSTRACT=Background: Hyperuricemia is one of a serious health problem not only related to gout but also cardiovascular diseases (CVD). Low-dose aspirin was reported to inhibit uric acid excretion, which leads to hyperuricemia. To decrease hyperuricemia-related CVD, this study is to identify the risk of hyperuricemia in people taking aspirin.
Method: The original data of this cross-sectional study were obtained from the National Health and Nutrition Examination Survey (NHANES) between 2011 and 2018. Participants filled in the questionnaire “preventive aspirin use” and with a positive answer were included in the analysis. Six machine learning (ML) algorithms were screened, and eXtreme gradient boosting (XGBoost) was employed to establish a model to predict the risk of hyperuricemia.
Results: A total of 805 participants were enrolled in the final analysis. Of them, 190 participants were found with hyperuricemia. The participants were divided into the training set and testing set at a ratio of 8:2. The area under the curve (AUC) for the training set was 0.864 and for the testing set was 0.811. The SHapley Additive explanation (SHAP) method was used to evaluate the performances of the modeling. Based on the SHAP results, the feature ranking interpretation showed that the estimated glomerular filtration rate, BMI, and waist were the three most important features for hyperuricemia in those taking aspirin. In addition, triglyceride, hypertension, total cholesterol, high density lipoprotein, low density lipoprotein, age, race, and smoking were also correlated with the development of hyperuricemia.
Conclusion： A predictive model established by XGBoost algorithms can potentially help clinicians to make early detection of hyperuricemia risk in people taking low-dose aspirin.