Construction and Validation of A Nomogram Prediction Model of Febrile Seizure in Children
10.11969/j.issn.1673-548X.2025.03.014
- VernacularTitle:儿童热性惊厥风险列线图预测模型的构建及验证
- Author:
Cheng WANG
1
;
Xingfu WEI
;
Meitao ZHAO
Author Information
1. 730050 兰州,甘肃省妇幼保健院(甘肃省中心医院);730000 兰州大学资源环境学院
- Publication Type:Journal Article
- Keywords:
Febrile seizure;
Children;
Prediction model;
Nomograms
- From:
Journal of Medical Research
2025;54(3):73-79
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the risk factors of febrile seizures(FS)in children,construct a visualization nomogram predic-tion model of FS and verify its effectiveness.Methods A retrospective analysis was conducted on the clinical data of 1320 children with fever admitted to the Gansu Provincial Maternity and Child-care Hospital(Gansu Provincial Central Hospital)from January 2019 to De-cember 2022.The samples were randomly divided into the training set and the validation set at a ratio of 7∶3.The clinical characteristics and laboratory examination of the two groups were compared.LASSO regression was used to select the risk factors for FS,and multivariate Logistic regression analysis was performed on the predictors,and construction a prediction mode,and the discrimination,calibration and clinical applicability of the model were evaluated.Results The results showed that age,low body weight,peak temperature,diurnal changes in onset,upper respiratory tract infection,serum sodium,serum calcium,white blood cell,procalcitonin were independent risk factors for FS in children.A predictive model was constructed and a nomogram was developed with these factors.The area under the re-ceiver operating characteristic(ROC)curve of the training set and the validation set were 0.870(95％CI:0.847-0.893)and 0.855(95％CI:0.817-0.894),respectively.The calibration plots and Hosmer-Lemeshow goodness-of-fit test showed its satisfactory cali-bration.The decision curve analysis(DCA)curve showed that the model provided a good net benefit with threshold probabilities when training set was＞5％,while in the validation set it was＞8％.Conclusion The risk prediction model based on LASSO-Logistic re-gression analysis can provide reference for early risk assessment of children with FS.
