Prediction of Renal Damage in Children with Henoch-Schönlein Purpura Based on Machine Learning

Background This article is objected to explore the value of machine learning algorithm in predicting the risk of renal damage in children with Henoch-Schönlein Purpura, and to construct a predictive model of Henoch-Schönlein Purpura Nephritis in children and analyze the related risk factors of Henoch-Schönlein Purpura Nephritis in children. Methods Case data of 288 hospitalized children with Henoch-Schönlein Purpura 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, decision tree and random forest algorithm were used respectively for classification prediction. Last, the performance of four algorithms are compared using accuracy rate and recall rate. Results The accuracy rate, recall rate and AUC of the established random forest 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 support vector machine model; higher than 0.74, 0.80 and 0.81 of the decision tree model. The top 10 important features provided by random forest model are Persistent purpura≥4weeks, Cr, Clinic time, ALB, WBC, TC, TG, Relapse, TG, Recurrent purpura and EB-DNA. Conclusion The model based on random forest algorithm has better performance in the prediction of children with allergic purpura renal damage, indicated by better classification accuracy, better classification effect and better generalization performance.

Intestinal dysbiosis featuring abundance of Streptococcus associates with Henoch-Schönlein purpura nephritis (IgA vasculitis with nephritis) in adult

Background The pathogenesis of Henoch-Schönlein purpura nephritis (HSPN) is closely associated with mucosal infection. But whether intestinal microbiota dysbiosis plays a role in it is not clear. Methods A total of 52 participants including 26 HSPN patients and 26 healthy controls were included. By using 16S ribosomal RNA gene sequencing, the intestinal microbiota composition between HSPN and healthy controls was compared. The diagnostic potency was evaluated by Receiver operating characteristic (ROC) with area under curves (AUC). Meanwhile, correlation analysis was also performed. Results The lower community richness and diversity of fecal microbiota was displayed in HSPN patients and the structure of gut microbiota was remarkedly different. A genus-level comparison indicated a significant increase in the proportions of g-Bacteroides, g-Escherichia–Shigella and g-Streptococcus, and a marked reduction of g-Prevotella_9 in HSPN patients, suggesting that the overrepresentation of potential pathogens and reduction of profitable strains were the main feature of the dysbiosis. The differential taxonomic abundance might make sense for distinguishing HSPN from healthy controls, with AUC of 0.86. The relative abundance of the differential bacteria was also concerned with clinical indices. Among them, Streptococcus spp. was positively associated with the severity of HSPN (P < 0.050). It was found that HSPN patients with higher level of Streptococcus spp. were more likely to suffering from hematuria and hypoalbuminemia (P < 0.050). Conclusions The dysbiosis of gut microbiota was obvious in HSPN patients, and the intestinal mucosal streptococcal infection was distinctive, which was closely related to its severity.

Chinese patent herbal medicine Huaiqihuang for Henoch-Schonlein purpura nephritis in children: a systematic review of randomized controlled trials

Background Henoch-Schönlein purpura nephritis (HSPN) is listed as the most common secondary glomerular diseases among children. Approximately 15 to 20% of children eventually could develop into chronic renal failure. Chinese patent herbal medicine Huaiqihuang (HQH) has been widely used in children with HSPN. This study aimed to evaluate the effectiveness and safety of HQH for HSPN in children, so as to provide evidence for clinical use. Methods Randomized controlled trials (RCTs) on HQH for HSPN in children were searched in eight Chinese and English databases from their inception to December 2020. We included children with HSPN received HQH combined with conventional medicine. Cochrane “Risk of bias” tool was used to assess methodological quality, and “Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach” to summarize the certainty of evidence for main findings. Effect estimates were presented as risk ratio (RR), mean difference (MD) or standardized mean difference (SMD) with 95% confidence interval (CI) in meta-analyses using RevMan 5.3. Data not suitable for statistical pooling were synthesized qualitatively. Results In total seven RCTs were identified. Compared with conventional medicine alone, HQH plus conventional medicine showed the better effect in improving clinical cure rate (RR 1.58; 95%CI 1.17 to 2.14; n = 6) and total effective rate (RR 1.34; 1.16 to 1.54; n = 6); reducing urine sediment erythrocyte count (MD -9.23; − 10.76 to − 7.69; n = 3) and urine β2 micro-globulin level (MD -0.09; − 0.12 to − 0.06; n = 2). No serious adverse event was recorded in all included trials. Conclusions Limited evidence showed HQH combined with conventional medicine had a beneficial effect for children with HSPN, and the side effects were mild. HQH may be a promising complementary therapy. However, long term follow-up, high quality and multicenter RCTs are required to confirm the findings.

Renal Outcomes of Childhood IgA Nephropathy and Henoch Schönlein Purpura Nephritis

Background: Henoch-Schönlein purpura nephritis (HSPN) is considered the systemic form of IgA nephropathy (IgAN). However, differing clinicopathological features and renal outcomes of children with IgAN and HSPN have been reported in some studies. Methods: This study retrospectively reviewed children with IgAN and HSPN younger than 18 years, between January 2004 and December 2015. The clinicopathological characteristics at diagnosis and the renal outcomes after at least 1 year of follow-up were compared between the two groups. Results: A total of 54 children, comprising 21 with IgAN and 33 with HSPN, were recruited. The children with HSPN were younger than the children with IgAN. Gross hematuria and nephritic syndrome at the initial presentation were more common in children with IgAN. Regarding the pathological findings, IgAN had greater chronicity than HSPN. After a median follow-up period from first presentation to renal outcomes measurement of 4.0 years (1.3-12.2) in children with IgAN and 4.2 years (1.1-11.4) in children with HSPN, the renal outcomes were better in the latter group. The incidence of chronic kidney disease (CKD) was 28.6% in children with IgAN and 6.1% in children with HSPN (p = 0.02). Complete recovery was observed more frequently in children with HSPN than in children with IgAN (57.1% in IgAN vs. 87.9% in HSPN, p = 0.01). Conclusions: Childhood IgAN has greater chronicity and worse renal outcomes than childhood HSPN, with a lower rate of complete recovery and a higher frequency of CKD. We recommend long-term follow-up for CKD in children with IgAN.