To predict breakthrough UTI, VUR + UTI.
| Article DOI | https://doi.org/10.1016/j.jpurol.2016.03.005 |
| Objective | To predict the probability of breakthrough fUTI in children with primary VUR. |
| AI Approach | 2-hidden node neural network |
| Data Source(s) | Single institutional series (384 patients) |
| Model Input | Age, gender, laterality, percentage PBC at VUR onset, VUR grade right/left, VUR onset right/left (filling or voiding), complete ureteral duplication, number of UTIs prior to VUR diagnosis (2 vs. <2), history of fUTI, and history of BBD. |
| Model Outcome | Breakthrough UTI |
| Model Metrics | AUC 0.76 |
| Model Usability | Web-based publicly available model is in production. |
AI = Artificial intelligence, UTI = Urinary tract infection, VUR = Vesicoureteral reflux, BBD = Bladder and bowel dysfunction
AIPEDURO 
Leave a comment