क्लिनिकल पीडियाट्रिक्स: ओपन एक्सेस
खुला एक्सेस

अमूर्त

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

Jinjuan Wang, Juanjuan Diao, Yueli Pan*

Henoch-Schönlein Purpura (HSP) is one of the most common systemic vasculitis in childhood. When HSP involves the kidney and causes different degrees of renal damage such as hematuria and proteinuria, it is called Henoch- Schonlein Purpura Nephritis (HSPN). HSPN is the most common secondary glomerular disease in children. Early and accurate diagnosis of HSPN is very important for patient prognosis and individualized treatment. Renal biopsy is the gold standard for the diagnosis of HSPN. However, due to its invasive nature, it is difficult for parents and children to accept it. As a result, some patients have extremely serious renal lesions at the time of diagnosis. Many researchers are committed to studying whether simple clinical data can be used to predict HSP renal damage, so as to help clinicians diagnose HSPN early and efficiently, in order to avoid the occurrence of HSPN or reduce its severity. At present, the research on machine learning in clinical disease prediction has been relatively common; we will review the application of machine learning in children's HSPN.