Abnormal urinalysis on day 7 in patients with IgA vasculitis (Henoch-Schönlein purpura)

Recurrence of Henoch Schoenlein Purpura Nephritis in Children: A Retrospective Study

The aim of the study was to identify predictive patient characteristics for Henoch Schoenlein Purpura (HSPN) relapse in childhood HSPN. One hundred and thirty-five Chinese children with HSPN were enrolled in this study, mean age 10.25 ± 3.39 years. The pathology of HSPN was according to the International Study of Kidney Disease in Children criteria.(ISKDC); ISKDC II(mesangial proliferation (MP)) AND ISKDC III (MP with <50 % crescents).Recurrence of HSPN was observed in 66.3 % patients; male to female ratio (2:1)Statistically significant correlation existed between biopsy grade(p < 0.001), gender(p < 0.001),age ranges(p = 0.002) and treatment regimen (p < 0.001)in the frequency of recurrent HSPN episodes. We identified some significant predictors for HSPN relapse such as the severity of HSPN, adjunctive therapies administered to these patients,and close attention should be paid in patients between the ages 7 and 12 years old. In addition, the use of mycophenolate mofetil as an adjunctive therapy in the treatment of HSPN may reduce the frequency of HSPN relapse episodes in children.

Prediction of renal damage in children with IgA vasculitis based on machine learning

This article is objected to explore the value of machine learning algorithm in predicting the risk of renal damage in children with IgA vasculitis by constructing a predictive model and analyzing the related risk factors of IgA vasculitis Nephritis in children. Case data of 288 hospitalized children with IgA vasculitis from November 2018 to October 2021 were collected. The data included 42 indicators such as demographic characteristics, clinical symptoms and laboratory tests, etc. Univariate feature selection was used for feature extraction, and logistic regression, support vector machine (SVM), decision tree and random forest (RF) algorithms were used separately for classification prediction. Lastly, the performance of four algorithms is compared using accuracy rate, recall rate and AUC. The accuracy rate, recall rate and AUC of the established RF model were 0.83, 0.86 and 0.91 respectively, which were higher than 0.74, 0.80 and 0.89 of the logistic regression model; higher than 0.70, 0.80 and 0.89 of SVM model; higher than 0.74, 0.80 and 0.81 of the decision tree model. The top 10 important features provided by RF model are: Persistent purpura ≥4 weeks, Cr, Clinic time, ALB, WBC, TC, Relapse, TG, Recurrent purpura and EB-DNA. The model based on RF algorithm has better performance in the prediction of children with IgA vasculitis renal damage, indicated by better classification accuracy, better classification effect and better generalization performance.