Stone free status after ureteroscopy
| Article DOI | https://dx.doi.org/10.1089/end.2024.0120 |
| Objective | To predict postoperative ureteroscopy outcomes in children (stone-free status and complications) from preoperative characteristics |
| AI Approach | LR, SVM, DT, RF, Extra Trees (boosted), Naive Bayes, KNN, Bagging; Ensemble (Bagging + Extra Trees + LDA), Multitask ANN |
| Data Source(s) | Single institutional series (146 patients) |
| Model Input | Age, gender, pre-op urine culture, anatomical variants, stone location, multiple stones, total stone size, pre-op urinary drainage (stent/nephrostomy) |
| Model Outcome | Stone-free status Complications |
| Model Metrics | Prediction of stone-free status, ensemble: Training set accuracy 90%, F1 0.67-0.91 Prediction of complications, ensemble: Training set accuracy 93-100%, F1 0.74-1.00. |
| Model Usability | Code not provided; dataset not publicly available. |
AI = Artificial intelligence, SVM = Support bector machines, RF = Random forest, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment