Split renal function in hydronephrosis
| Article DOI | https://doi.org/10.1016/j.urology.2025.04.009 |
| Objective | To predict differential renal function <40% in unilateral hydronephrosis using urinary tract ultrasound |
| AI Approach | Random forest, logistic regression, SVM |
| Data Source(s) | Single institutional series (802 patients) |
| Model Input | Gender, side, age, renal pelvis anterior-posterior diameter (APD), upper calyx dilation, renal length ratio |
| Model Outcome | Decreased split renal function (<40%) |
| Model Metrics | SVM (best model): AUC 0.94, sensitivity 90%, specificity 81% |
| Model Usability | Dataset available upon request to authors. |
AI = Artificial intelligence, SVM = Support vector machine, AUC = Area under the receiver-operator characteristic
AIPEDURO 
Leave a comment