Hydronephrosis from VUDS in spina bifida
| Article DOI | https://dx.doi.org/10.1097/JU.0000000000004547 |
| Objective | To predict incident hydronephrosis in patients with spina bifida using videourodynamics data |
| AI Approach | Random forrest |
| Data Source(s) | Single institutional series (554 patients) |
| Model Input | Four models using (1) prospectively collected clinical characteristics, (2) urodynamic pressure-volume recordings, (3) fluoroscopic imaging, and (4) risk prediction scores from pressure/volume and imaging models |
| Model Outcome | Probability of hydronephrosis, |
| Model Metrics | In VUDS reaching > 75% estimated bladder capacity: c-index of 0.73. Additional statistics on training/test datasets available. |
| Model Usability | None |
AI = Artificial intelligence, VUDS = Video urodynamics, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment