Construction and validation of a risk prediction model for hyperuricemia in children and adolescents
XIAO Ningting
LI Li
GUO Xuemei
CHEN Lili
Abstract：Objective:To investigate the risk factors for the development of hyperuricemia in children and adolescents and to construct a risk prediction model.Methods:The clinical data of 9 857 cases of children and adolescents aged 6～17 years attending the Affiliated Hospital of Chuanbei Medical College from January 2017 to December 2021 were retrospectively analyzed,and 8 689 cases from January 2017 to December 2020 constituted the modeling group,and 1 168 cases from January to December 2021 constituted the validation group for internal validation.Referring to the definition of hyperuricemia,they were divided into hyperuricemia group and non-hyperuricemia group.Univariate analysis and Logistic regression were applied to analyze the influencing factors of hyperuricemia in children and adolescents,and prediction models were developed.The area under the subject operating characteristic(ROC)curve(AUC)and C-index were used to assess the predictive ability of the model,and Bootstrap repeated sampling method(1 000 times of sampling)was used for internal validation of the model.Results:The results of multifactorial analysis showed that age,gender,body mass index,creatinine,urea nitrogen,estimated glomerular filtration rate,triglycerides,high-density lipoprotein as influencing factors of hyperuricemia in children and adolescents.The area under the ROC curve AUC of the model was 0.876,the sensitivity was 0.809,the specificity was 0.796,the Youden index was 0.611,and the C-index was 0.877.the area under the ROC curve AUC of external validation was 0.838,and the overall correctness of the model was 77.8%.Conclusion:The risk prediction model for hyperuricemia in children and adolescents has good predictive efficacy and implementability,and provides a reference for clinical staff to assess the risk of hyperuricemia in children and adolescents.
Keywords：childrenadolescentshyperuricemiarisk factorsprediction model
Publication Date：2024-06-10
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 1908-1913 )