External validation and reliability assessment of posterior urethral morphology on initial voiding cystourethrogram as a predictor for infants with posterior urethral valves.

INTRODUCTION: The morphology of the bladder and posterior urethra on initial voiding cystourethrogram (VCUG) in posterior urethral valve (PUV) has been proposed as a meaningful early metric for short- and long-term kidney outcomes. Here, we seek to externally validate the proposed association and assess the reliability of PUV morphology characteristics. MATERIALS AND METHODS: We reviewed our institutional database for patients managed for PUV between 2000 and 2022 and included those treated with primary ablation with at least 1 year of follow-up for kidney function. Each VCUG was evaluated by three independent raters for the height-width ratio of the bladder (HW-B), height-width ratio of the posterior urethra (HW-PU), and posterior-anterior urethral ratio (PA-UR), and trabeculation (none, fine, or coarse). We assessed the reliability in these with intra-class coefficient and Fleiss kappa for continuous and categorical data, respectively. We performed univariate analysis with nadir creatinine and five-year follow-up glomerular filtration rate (GFR). RESULTS: In total, 98 patients met inclusion criteria. The median age at diagnosis and ablation was 10 and 21 days, respectively. Patients with nadir creatinine <0.8 mg/dL had higher follow-up GFR (101 vs. 20 ml/min/1.73 m2, p = 0.04), and lower risk of CKD (odds ratio 14.7, p = 0.002). The median value for HW-B was 1.4, median HW-PU was 2.1, and median PA-U was 4.7, There was significant inter-class agreement between all three measures of 0.80, 0.51, and 0.70 (p < 0.001). The inter-rater agreement for bladder trabeculation was fair (Fleiss K = 0.40, p < 0.001). There was no statistically significant correlation between HW-B, HW-PU, PU-A with nadir creatinine (p = 0.07, 0.33, 0.91) or 5-year GFR (0.27, 0.45, 0.62), respectively. DISCUSSION: There is significant interest in determining prognostic factors and metrics in PUV. The morphological characteristics on VCUG are reliable and is available information for all boys diagnosed with PUV, resulting in an attractive metric. While we do not demonstrate correlation with kidney outcomes, VCUG features warrant further attention as prognostic factors in PUV. CONCLUSIONS: PUV morphology on initial VCUG is a reliable metric of lower urinary tract deformity but is not associated with 5-year kidney outcomes.

Development, multi-institutional external validation, and algorithmic audit of an artificial intelligence-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA) for patients undergoing radical prostatectomy: a retrospective cohort study.

BACKGROUND: Accurate prediction of side-specific extraprostatic extension (ssEPE) is essential for performing nerve-sparing surgery to mitigate treatment-related side-effects such as impotence and incontinence in patients with localised prostate cancer. Artificial intelligence (AI) might provide robust and personalised ssEPE predictions to better inform nerve-sparing strategy during radical prostatectomy. We aimed to develop, externally validate, and perform an algorithmic audit of an AI-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA). METHODS: Each prostatic lobe was treated as an individual case such that each patient contributed two cases to the overall cohort. SEPERA was trained on 1022 cases from a community hospital network (Trillium Health Partners; Mississauga, ON, Canada) between 2010 and 2020. Subsequently, SEPERA was externally validated on 3914 cases across three academic centres: Princess Margaret Cancer Centre (Toronto, ON, Canada) from 2008 to 2020; L'Institut Mutualiste Montsouris (Paris, France) from 2010 to 2020; and Jules Bordet Institute (Brussels, Belgium) from 2015 to 2020. Model performance was characterised by area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), calibration, and net benefit. SEPERA was compared against contemporary nomograms (ie, Sayyid nomogram, Soeterik nomogram [non-MRI and MRI]), as well as a separate logistic regression model using the same variables included in SEPERA. An algorithmic audit was performed to assess model bias and identify common patient characteristics among predictive errors. FINDINGS: Overall, 2468 patients comprising 4936 cases (ie, prostatic lobes) were included in this study. SEPERA was well calibrated and had the best performance across all validation cohorts (pooled AUROC of 0·77 [95% CI 0·75-0·78] and pooled AUPRC of 0·61 [0·58-0·63]). In patients with pathological ssEPE despite benign ipsilateral biopsies, SEPERA correctly predicted ssEPE in 72 (68%) of 106 cases compared with the other models (47 [44%] in the logistic regression model, none in the Sayyid model, 13 [12%] in the Soeterik non-MRI model, and five [5%] in the Soeterik MRI model). SEPERA had higher net benefit than the other models to predict ssEPE, enabling more patients to safely undergo nerve-sparing. In the algorithmic audit, no evidence of model bias was observed, with no significant difference in AUROC when stratified by race, biopsy year, age, biopsy type (systematic only vs systematic and MRI-targeted biopsy), biopsy location (academic vs community), and D'Amico risk group. According to the audit, the most common errors were false positives, particularly for older patients with high-risk disease. No aggressive tumours (ie, grade >2 or high-risk disease) were found among false negatives. INTERPRETATION: We demonstrated the accuracy, safety, and generalisability of using SEPERA to personalise nerve-sparing approaches during radical prostatectomy. FUNDING: None.

Ultrasonographical features of perinatal testicular torsion: an assessment of interobserver variability among radiologists and pediatric urologists.

PURPOSE: To retrospectively compare interpretations of Doppler ultrasound (US) in newborns with confirmed perinatal testicular torsion (PTT) by an experienced faculty (staff) pediatric radiologist (SPR), pediatric radiology fellow (PRF), pediatric urology fellow (PUF) and staff pediatric urologist (SPU). METHODS: US images of 27 consecutive males with PTT between May 2000 and July 2020 were retrieved. The testicles were classified as affected or non-affected by PTT. We performed a blinded comparison of interpretation by four assessors (SPR, PRF, PUF, SPU), with respect to the US features of PTT. Paired inter-rater agreement was calculated using Cohen's Kappa (κ) and overall agreement was assessed using Fleiss' kappa. RESULTS: Overall comparison using Fleiss' kappa found fair agreement for most features except testicular echogenicity and echogenic foci at interface for which there was poor agreement. Paired comparisons revealed better agreement between the SPR and PRF compared to the remaining two pairs, suggesting a need for the pediatric urologists (PUF and SPU) to acquaint themselves with testicular ultrasonography as this may have an impact on patient risk stratification and the quality of information given to parents. CONCLUSION: This study highlights the need for focused training program for pediatric urologists to attain similar agreement as the radiologists, suggesting a need for the pediatric urologists (PUF and SPU) to acquaint themselves with testicular ultrasonography as this may have an impact on patient risk stratification and the quality of information given to parents.

Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning Approaches.

PURPOSE: Vesicoureteral reflux grading from voiding cystourethrograms is highly subjective with low reliability. We aimed to demonstrate improved reliability for vesicoureteral reflux grading with simple and machine learning approaches using ureteral tortuosity and dilatation on voiding cystourethrograms. MATERIALS AND METHODS: Voiding cystourethrograms were collected from our institution for training and 5 external data sets for validation. Each voiding cystourethrogram was graded by 5-7 raters to determine a consensus vesicoureteral reflux grade label and inter- and intra-rater reliability was assessed. Each voiding cystourethrogram was assessed for 4 features: ureteral tortuosity, proximal, distal, and maximum ureteral dilatation. The labels were then assigned to the combination of the 4 features. A machine learning-based model, qVUR, was trained to predict vesicoureteral reflux grade from these features and model performance was assessed by AUROC (area under the receiver-operator-characteristic). RESULTS: A total of 1,492 kidneys and ureters were collected from voiding cystourethrograms resulting in a total of 8,230 independent gradings. The internal inter-rater reliability for vesicoureteral reflux grading was 0.44 with a median percent agreement of 0.71 and low intra-rater reliability. Higher values for each feature were associated with higher vesicoureteral reflux grade. qVUR performed with an accuracy of 0.62 (AUROC=0.84) with stable performance across all external data sets. The model improved vesicoureteral reflux grade reliability by 3.6-fold compared to traditional grading (P < .001). CONCLUSIONS: In a large pediatric population from multiple institutions, we show that machine learning-based assessment for vesicoureteral reflux improves reliability compared to current grading methods. qVUR is generalizable and robust with similar accuracy to clinicians but the added prognostic value of quantitative measures warrants further study.