Related Experiment Video
Updated: Jul 14, 2026
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
Predicting renal damage in children with IgA vasculitis by machine learning
Mengen Pan1, Ming Li2, Na Li1
1Zhejiang University School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
Insights
Machine learning accurately predicts kidney damage in children with IgA Vasculitis (IgAV). The developed model identifies key risk factors for IgA Vasculitis with Nephritis (IgAVN), aiding early diagnosis and treatment.
Area of Science:
- Pediatric Nephrology
- Medical Informatics
- Immunology
Background:
- Children with IgA Vasculitis (IgAV) face risks of renal complications impacting long-term health.
- Early identification of kidney damage is crucial for managing IgAV outcomes.
Purpose of the Study:
- To develop a machine learning model for predicting renal damage in pediatric IgAV patients.
- To identify significant risk factors associated with IgA Vasculitis with Nephritis (IgAVN).
Main Methods:
- Collected data on 50 clinical indicators from 217 pediatric IgAV inpatients.
- Evaluated six machine learning algorithms, selecting Random Forest for optimal predictive performance.
- Developed and validated a simplified model using feature importance, tested on an additional 46-patient cohort.
Main Results:
- The Random Forest model achieved high performance metrics (accuracy 0.91, AUC 0.94).
- Key predictors included anti-streptolysin O, corticosteroid/antihistamine therapy, eosinophil count, and IgE levels.
- A simplified model showed 84.2% accuracy in external validation, with a publicly available web tool developed.
Conclusions:
- The Random Forest-based model effectively predicts renal damage in pediatric IgAV.
- This predictive tool supports early clinical diagnosis and informed decision-making for IgAVN.
Background:
Children with IgA Vasculitis (IgAV) may develop renal complications, which can impact their long-term prognosis. This study aimed to build a machine learning model to predict renal damage in children with IgAV and analyze risk factors for IgA Vasculitis with Nephritis (IgAVN).
Methods:
50 clinical indicators were collected from 217 inpatients at our hospital. Six machine learning algorithms-Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbor, Support Vector Machine, Decision Trees, and Random Forest-were utilized to select the model with the highest predictive performance. A simplified model was developed through feature importance ranking and validated by an additional cohort with 46 patients.
Results:
The random forest model had the highest accuracy, precision, recall, F1 score, and area under the curve, with values of 0.91, 0.98, 0.70, 0.79 and 0.94, respectively. The top 11 features according to the importance ranking were anti-streptolysin O, corticosteroids therapy, antihistamine therapy, absolute eosinophil count, immunoglobulin E, anticoagulant therapy, C-reactive protein, prothrombin time, age at onset, D-dimer, recurrence of rash ≥ 3 times. A simplified model using these features demonstrated optimal performance with an accuracy of 84.2%, a sensitivity of 89.4%, and a specificity of 82.5% in external validation. Finally, we provided a web tool based on the simplified model, whose code was published on https://github.com/mulanruo/IgAVN_Prediction .
Conclusion:
The model based on the random forest algorithm demonstrates good performance in predicting renal damage in children with IgAV, providing a basis for early clinical diagnosis and decision-making.
Related Concept Videos
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
01:22Acute Kidney Injury I: Introduction
01:29Acute Kidney Injury III: Clinical Manifestations
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention