Need for surgery in UPJO
| Article DOI | https://doi.org/10.1007/s11845-025-03895-7 |
| Objective | To predict the need for surgery in patients with hydronephrosis resulting from UPJO |
| AI Approach | XGBClassifier, logistic regression, random forest, LGM classifier with Re, extra trees, AVG blender |
| Data Source(s) | Single center institutional series (323 patients) |
| Model Input | Presence of obstruction on DTPA/MAG3 scintigraphy, kidney size on urinary USG, AP diameter of the renal pelvis and renal parenchymal loss |
| Model Outcome | Need for surgery |
| Model Metrics | AUC 0.98, accuracy 95% |
| Model Usability | Dataset available upon request to authors. |
AI = Artificial intelligence, UPJO = Ureteropelvic junction obstruction
AIPEDURO 
Leave a comment