Renal scarring in VUR, VUR + UTI.
| Article DOI | https://doi.org/10.1007/s11845-023-03275-z |
| Objective | To predict renal scarring in pediatric population with VUR |
| AI Approach | Logistic Regression, Discriminant Analysis, Bayesian Logistic Regression, Naïve Bayes, Decision Tree |
| Data Source(s) | Single institutional series (94 patients) |
| Model Input | Kidney injury molecule-1 (KIM-1), Neutrophil gelatinase–associated lipocalin (NGAL), Urinary creatinine, Ratios of NGAL and KIM-1 to urinary creatinine |
| Model Outcome | Presence of renal scarring: |
| Model Metrics | Logistic Regression: AUC 0.83 Discriminant Analysis: AUC 0.83 Bayesian Logistic Regression: AUC 0.83 Naïve Bayes: AUC 0.81 Decision Tree (C5.0): AUC 0.83 |
| Model Usability | NA |
AI = Artificial intelligence
AIPEDURO 
Leave a comment