Vesicoureteral Reflux and Urinary Tract Infection
| Article DOI | https://doi.org/10.1016/j.jpurol.2021.10.009 |
| Objective | To predict high-grade VUR from quantitative features annotated from VCUGs |
| AI Approach | Random forest |
| Data Source(s) | Web scraping (41 renal units), institutional series (44 renal units) |
| Model Input | Ureter tortuosity, UPJ width, UVJ width, and maximum ureter width on VCUG |
| Model Outcome | High-grade VUR (Grade 4, 5) |
| Model Metrics | AUROC = 0.83, accuracy = 90% |
| Model Usability | https://akhondker.shinyapps.io/qVUR/ |
AIPEDURO 
Leave a comment