紫癜(腹足类)
过敏性紫癜
医学
计算机科学
人工智能
皮肤病科
免疫学
内科学
生物
血管炎
生态学
疾病
作者
Tingting Cao,Ying Zhu,Yiqian Zhu
摘要
Objective. The children with Henoch-Schönlein purpura (HSP) may suffer from renal insufficiency, which seriously affects the life and health of the children. This study aims to construct a prediction model of Henoch-Schönlein purpura nephritis (HSPN). Methods. A total of 240 children with HSP treated in dermatology and pediatrics in our hospital were selected. The general information, patients’ clinical symptoms, and laboratory examination indicators were collected for feature selection, and the XGBoost algorithm prediction model was built. Results. According to the input feature indexes, the top ten crucial feature indicators output by the XGBoost model were urine N-acetyl-β-D-aminoglucosidase, urinary retinol-binding protein, IgA, age, recurrence of purpura, purpura area, abdominal pain, 24-h urinary protein quantification, percentage of neutrophils, and serum albumin. The areas under the curves of the training set (0.895, 95% CI: 0.827-0.963) and test set (0.870, 95% CI: 0.799-0.941) models were similar. Conclusion. The prediction model based on XGBoost is used to predict HSP renal damage based on clinical data of children, which can reduce the harm caused by invasive examination for patients.
科研通智能强力驱动
Strongly Powered by AbleSci AI