Pediatric testicular torsion management practices: A survey of Canadian urologists.

INTRODUCTION: Pediatric testicular torsion (TT) is a urologic emergency that may result in testicular loss if left untreated. Testicular salvage is dependent on prompt intervention, and thus delays in diagnosis and management may threaten testicular viability. Knowledge of real-world Canadian practice patterns for pediatric TT will allow optimization of practices based on resource availability and geographic limitations to improve care. METHODS: An electronic survey on pediatric TT management was distributed to Canadian urologists. Descriptive statistics were performed on respondent demographic factors, hospital policies and barriers to care, surgical approaches, and transfer practices. Respondent practice patterns were analyzed based on geographic location and training. RESULTS: Thirty-four urologists responded, with the majority of respondents operating a community practice. Ultrasonography (US) was frequently used to support TT diagnosis. Despite this, poor US access was often cited as a barrier to care, with particular impact on rural urologists. Neonatal patients and <10 years old were commonly transferred to a pediatric hospital for definitive management due to surgeon discomfort and hospital policies. Reported transport methods commonly included use of the patient's own vehicle or ambulance based on availability and timing. CONCLUSIONS: Neonatal patients and patients under 10 years old are most commonly reported to be transferred to pediatric hospitals for TT management. Patients located in rural locations and at centers with limited US access may be at risk for delayed diagnosis and treatment. Pathways for prompt management of suspected TT may better serve these younger pediatric patients.

Radiation exposure associated with computed tomography for pediatric urolithiasis evaluation: A scoping review of the literature.

INTRODUCTION: Computed tomography (CT) imaging is used for assessment of pediatric urolithiasis in cases where ultrasound is inconclusive. The utility of CT imaging must be considered alongside the potential risks of radiation exposure in this patient population due to the increased risk of cancer development. The purpose of this review is to investigate the radiation exposure associated with standard-dose and low-dose computed tomography (CT) imaging for the assessment of pediatric urolithiasis. METHODS: A scoping literature review over a 23 year period between 2000 and 2023 was conducted of all English-language studies reporting on the use of non-contrast CT imaging for assessment of pediatric urolithiasis. Patients that were specified as pediatric with age ≤20 years at time of intervention and undergoing standard-dose or low/ultra-low-dose CT were included. Low-dose and ultra-low-dose CT were defined as a radiation dose ≤3.0 mSv and ≤1.9 mSv, respectively. RESULTS: A total of 8121 articles were identified and after screening, 6 articles representing 309 patients were included in this scoping review. Of the articles reviewed, standard non-contrast CT radiation doses for pediatric urolithiasis evaluation ranged from 2.9 to 5.5 mSv and low-dose CT radiation dose was reported to be 1.0-2.72 mSv. Only 2 studies directly evaluated low-dose CT imaging compared to standard-dose CT imaging for pediatric urolithiasis assessment. Radiation reduction approaches did not negatively impact urolithiasis detection or characterization in 2 studies reviewed. CONCLUSIONS: CT radiation doses for suspected or known pediatric urolithiasis are underreported and vary greatly with underutilization of low-dose/ultra-dose protocols for pediatric urolithiasis especially in comparison to the adult population. Results from this scoping review support that low-dose CTprotocols for pediatric stone disease are feasible to reduce radiation exposure.

The Toronto nomogram: A Bayesian meta-regression derived prenatal ultrasound index to predict lower urinary tract obstruction and prune belly syndrome.

INTRODUCTION: A nomogram for predicting the diagnosis of lower urinary tract obstruction (LUTO) based on an antenatal ultrasound index generated from a Bayesian Meta-regression analysis has been in development and noted with superior diagnostic accuracy compared to the keyhole sign (KHS). We aim to assess the accuracy of the nomogram in expanded diagnostic utilization to predict LUTO. METHODOLOGY: The validation of the nomogram for expanded diagnostic utilization was based on data from a prospective institutional antenatal clinic database between January 2020 and June 2022. Diagnostic accuracy indices were determined for confirmed postnatal diagnosis of LUTO or prune belly syndrome (PBS). Receiver operating characteristics (ROC) curves were generated to compare the area under the curve (AUC) of the nomogram versus KHS. RESULTS: Based on 84 male fetuses with antenatal ultrasound of moderate-severe hydronephrosis (PUV n = 15, PBS n = 4), the KHS had 26.3% (95%CI 9.1-51.2) sensitivity and 100% (95%CI 94.4%-100%) specificity, with 14 false-negatives. The nomogram showed a 84.2 (95%CI 60.4%-96.6%) sensitivity and 95.4 (95%CI 87.1%-99%) specificity with three false-positives. The nomogram also had a superior AUC compared to KHS (0.98 vs. 0.63). CONCLUSION: The nomogram can be used as a valuable tool to trigger further postnatal screening and provide individualized risk assessments to families during prenatal counseling.

A quantitative analysis of voiding cystourethrogram features confirms the association between high-grade vesicoureteral reflux with male sex, younger age, and hydronephrosis.

INTRODUCTION: Vesicoureteral reflux (VUR) is commonly diagnosed in the workup of urinary tract infections or hydronephrosis in children. Traditionally, VUR severity is graded subjectively based on voiding cystourethrogram (VCUG) imaging. Herein, we characterized the association between age, sex, and indication for VCUG, by employing standardized quantitative features. METHODS: We included renal units with a high certainty in VUR grade (>80% consensus) from the qVUR model validation study at our institution between 2013 and 2019. We abstracted the following variables: age, sex, laterality, indication for VCUG, and qVUR parameters (tortuosity, ureter widths on VCUG). High-grade VUR was defined as grade 4 or 5 The association between each variable and VUR grade was assessed. RESULTS: A total of 443 patients (523 renal units) were included, consisting of a 48:52 male/female ratio. The median age at VCUG was 13 months. Younger age at VCUG (<6 months) was associated with greater odds of severe VUR (odds ratio [OR] 2.0), and there was a weak correlation between age and VUR grade (ρ=-0.17). Male sex was associated with increased odds of high-grade VUR (OR 2.7). VCUGs indicated for hydronephrosis were associated with high-grade VUR (OR 4.1) compared to those indicated for UTI only. Ureter tortuosity and width were significantly associated with each clinical variable and VUR severity. CONCLUSIONS: Male sex, younger age (<6 months), and history of hydronephrosis are associated with both high-grade VUR and standardized quantitative measures, including greater ureter tortuosity and increased ureteral width. This lends support to quantitative assessment to improve reliability in VUR grading.

Diagnosis, Classification, and Contemporary Management of Undescended Testicles.

This article provides a comprehensive review regarding undescended testicles and other related conditions. We have included background information summarizing variable clinical presentations, epidemiology, and the implications of undescended testis (UDT) on fertility and malignancy risk. This article has an emphasis on the approach to diagnosis and surgical management for the UDT. The purpose of this review is to provide readers with useful clinical tools for assessing and treating patients with cryptorchidism.

Implementation of a standardized clinical pathway in a dedicated posterior urethral valves clinic: short-term outcomes.

BACKGROUND: To determine if the implementation of a posterior urethral valves (PUV) clinic and standardized management pathway improves the short-term kidney outcomes of infants with PUV. METHODS: From 2016-2022, 50 consecutive patients were divided into groups after the implementation of the clinic (APUV, n = 29) and before (BPUV, n = 21) during a comparable timeframe. Assessed data included age at initial visit, timing and type of surgery, frequency of follow-up visits, medications, nadir creatinine, and development of CKD/kidney failure. Data are shown as median with interquartile range (IQR) and odds ratios (OR) with 95% confidence interval (CI). RESULTS: APUV had higher rates of prenatal diagnoses (12/29 vs. 1/21; p = 0.0037), earlier initial surgical intervention (8 days; IQR 0, 105 vs. 33 days; IQR 4, 603; p < 0.0001), and higher rates of primary diversions (10/29 vs. 0/21; p = 0.0028). Standardized management led to earlier initiation of alpha blockers (326 days; IQR 6, 860 vs. 991; IQR 149, 1634; p = 0.0019) and anticholinergics (57 days; IQR 3, 860 vs. 1283 days; IQR 477, 1718; p < 0.0001). Nadir creatinine was reached at earlier ages in APUV (105 days; IQR 2, 303 vs. 164 days; IQR 21, 447; p = 0.0192 BPUV). One patient progressed to CKD5 in APUV compared to CKD3, CKD5 and one transplant in BPUV. CONCLUSION: Implementing the PUV clinic with standardized treatment expedited postnatal management and resulted in a higher number of cases detected prenatally, a shift in primary treatment, younger ages at initial treatment, reduced time to nadir creatinine, and timely initiation of supportive medications. A higher resolution version of the Graphical abstract is available as Supplementary information.

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.

Electronic medical record-related burnout in healthcare providers: a scoping review of outcomes and interventions.

OBJECTIVE: Healthcare provider (HCP) burnout is on the rise with electronic medical record (EMR) use being cited as a factor, particularly with the rise of the COVID-19 pandemic. Burnout in HCPs is associated with negative patient outcomes, and, therefore, it is crucial to understand and address each factor that affects HCP burnout. This study aims to (a) assess the relationship between EMR use and burnout and (b) explore interventions to reduce EMR-related burnout. METHODS: We searched MEDLINE (Ovid), CINAHL and SCOPUS on 29 July 2021. We selected all studies in English from any publication year and country that discussed burnout in HCPs (physicians, nurse practitioners and registered nurses) related to EMR use. Studies must have reported a quantitative relationship to be included. Studies that implemented an intervention to address this burnout were also included. All titles and abstracts were screened by two reviewers, and all full-text articles were reviewed by two reviewers. Any conflicts were addressed with a third reviewer and resolved through discussion. Quality of evidence of all included articles was assessed using the Quality Rating Scheme for Studies and Other Evidence. FINDINGS: The search identified 563 citations with 416 citations remaining after duplicate removal. A review of abstracts led to 59 studies available for full-text assessment, resulting in 25 studies included in the scoping review. Commonly identified associations between EMR-related burnout in HCPs included: message and alert load, time spent on EMRs, organisational support, EMR functionality and usability and general use of EMRs. Two articles employed team-based interventions to improve burnout symptoms without significant improvement in burnout scores. CONCLUSIONS AND RELEVANCE: Current literature supports an association between EMR use and provider burnout. Very limited evidence exists for burnout-reducing interventions that address factors such as time spent on EMRs, organisational support or EMR design.

Concurrent Multicystic Dysplastic Kidney, Posterior Urethral Valves, and Obstructive Ureterocele in a Male Pediatric Patient: A Case Report.

Congenital anomalies of the kidney and urinary tract (CAKUT) are diagnosed in approximately 3-6 per 1000 live births and represent a spectrum of urologic conditions impacting the kidneys, ureter, bladder, and urethra.1 Although both are considered under the classification of CAKUT, there is no known unifying pathophysiologic mechanism for ureteroceles and posterior urethral valves with only 1 case report noted in the literature. Herein we report the only documented case of a patient with CAKUT related to posterior urethral valves, ureterocele, and multicystic dysplastic kidney.

Attaining competency and proficiency in open pyeloplasty: a learning curve configuration using cumulative sum analysis.

INTRODUCTION: The learning curves for minimally invasive pyeloplasty techniques have been described in the past. However, the learning curve in achieving competency in open pyeloplasty has not been described. Hence, we aim to evaluate a single surgeon series of open pyeloplasty technique using the cumulative sum (CUSUM) methodology. METHODS: We retrospectively reviewed all open pyeloplasties performed by a single surgeon (AJL) between January 2008 and March 2020. Collected variables included: sex, age at surgery, operative time, hospital stay, pre-operative ultrasound, pre-operative nuclear scans, pre-operative anteroposterior diameter, associated anomalies, laterality (left or right), type of stent, pre-operative split renal function, and duration of follow-up. A CUSUM analysis was used: the highest peak, plateau and downward trends for complications (defined as Clavien-Dindo classification ≥ 3b) were identified on the plot and set as the transition points between five phases (learning, competency, proficiency, case-mix, and mastery). RESULTS: Based on the CUSUM analysis, the index surgeon reached the competency phase after performing their 13th open pyeloplasty and became proficient after the 70th case. In the case-mix phase (104th-126th cases), where the surgeon may be performing more complex cases while increasing trainee involvement, there was a slight increase in complication rates. After the 126th case, the surgeon entered the mastery phase, where there was consistent decreasing trend in complications. CONCLUSIONS: Surgeons performing open pyeloplasty in children following completion of their surgical training will continue to learn through their early cases until achieving competency. Technical competency may be reached after the 13th case. In this report, we looked at the number of cases to become proficient in open pyeloplasty procedure in children. A surgeon may achieve technical proficiency in the procedure after their 13th case.

Leeches and Caudal Analgesia After Replantation for Glans Amputation During Neonatal Circumcision.

Neonatal circumcision is one of the most commonly performed surgical procedures in the world. As with all surgeries, it carries risks, including rare, but devastating complications, such as glans, and/or penile shaft amputation. Complete glans amputation with successful replantation has been previously reported. Herein we report a case of complete amputation at the penile midshaft in a 28-day-old neonate with a unique approach to postoperative care including the use of leech therapy, topical heparin, and caudal analgesia following successful microvascular replantation.

Pre-versus postnatal presentation of posterior urethral valves: a multi-institutional experience.

OBJECTIVE: To compare the outcomes of pre- vs postnatally diagnosed posterior urethral valves (PUV) at two large paediatric centres in North America to ascertain if the prenatal diagnosis of PUV is associated with better outcomes. PATIENTS AND METHODS: All boys with PUV were identified at two large paediatric institutions in North America between 2000 and 2020 (The Hospital for Sick Children [SickKids, SK] and Children's Hospital of Philadelphia [CHOP]). Baseline characteristics and outcome measures were compared between those diagnosed pre- vs postnatally. Main outcomes of interest included progression of chronic kidney disease (CKD), the need for renal replacement therapy (RRT), and bladder function compromise, as determined by need for clean intermittent catheterisation (CIC). Time-to-event analyses were completed when possible. RESULTS: During the study period, 152 boys with PUV were treated at the SK (39% prenatal) and 216 were treated at the CHOP (71% prenatal). At the SK, there was no difference between the pre- and postnatal groups in the proportion of boys who required RRT, progressed to CKD Stage ≥3, or who were managed with CIC when comparing the timing of diagnosis. The time to event for RRT and CIC was significantly younger for prenatally detected PUV. At the CHOP, significantly more prenatal boys required RRT; however, there was no significant difference in the age this outcome was reached. The proportion of boys managed with CIC was not different but the time to event was significantly earlier in the prenatal group. CONCLUSION: This study represents the largest multi-institutional series of boys with PUV and failed to identify any difference in the outcomes of pre- vs postnatal detection of PUV. A multidisciplinary approach with standardisation of the treatment pathways will help in understanding the true impact of prenatal/early detection on outcomes of PUV.

Omental Procedures During Peritoneal Dialysis Insertion: A Systematic Review and Meta-Analysis.

OBJECTIVES: Peritoneal dialysis (PD) is an option for ultrafiltration for patients with end-stage renal disease. Once placed, PD catheters may malfunction often due to omental wrapping. Omental procedures such as omentectomy and omentopexy may reduce this risk. This investigation aims to perform a systematic review and meta-analysis of the literature on the role of omental procedures on PD catheter insertions. METHODS: Following protocol registration on PROSPERO (CRD42020218950), a systematic review was performed in accordance with the Cochrane Collaboration. A literature search was performed in February 2021 across Medline, EMBASE, Scopus, and Cochrane Library. Records with patients who underwent PD catheter insertion with and without omental manipulation were included. The records underwent screening, full-text review, and data extraction. Study qualities were assessed using RoBINS-I and RoB2. Effect estimates were extracted as risk ratios and corresponding 95% confidence intervals (CI) were pooled using inverse variance method with random-effect model. RESULTS: Of 510 records identified, 15 studies were included in the meta-analysis (1 RCT, 2 prospective, 12 retrospective). With omental procedures, there was decreased the likelihood of failure requiring removal of PD catheter (RR 0.47, 95% CI 0.38, 0.58) and PD catheter obstruction (RR 0.23, 95% CI 0.14, 0.39); there was no difference in likelihood of catheter malposition or migration (RR 0.87, 95% CI 0.23, 3.29) or peritonitis (RR 0.74, 95% CI 0.40, 1.35). CONCLUSION: Based on the current low to moderate quality of evidence, omental manipulation at the time of PD catheter insertion confers benefits of decreased obstruction and failure requiring removal.

Vascular hitch for paediatric pelvi-ureteric junction obstruction with crossing vessels: institutional analysis and systematic review with meta-analysis.

OBJECTIVE: To compare the outcomes for laparoscopic vascular hitch (VH) and dismembered pyeloplasty in patients with pelvi-ureteric junction obstruction (PUJO) secondary to crossing vessels (CV). PATIENTS AND METHODS: Patients who underwent laparoscopic management of CV at our institution were identified between 2008 and 2020. Baseline characteristics and outcome measures were compared between those who underwent VH and those who underwent dismembered pyeloplasty. Those who underwent VH were selected intraoperatively by identifying CV in the absence of intrinsic obstruction by assessing resolution of hydronephrosis after cranially displacing the CV away from the PUJ, followed by intraoperative fluid bolus and diuretic test. In addition, a systematic search and meta-analysis were performed in June 2020 (International Prospective Register of Systematic Reviews [PROSPERO] ID CRD42020195833). RESULTS: A total of 20 patients underwent VH and 74 dismembered pyeloplasty. On multivariate analysis, VH was associated with: shorter operative time (P = 0.001; odds ratio [OR] 0.455, 95% confidence interval [CI] 0.294-0.705) and length of stay (P = 0.012; OR 0.383, 95% CI 0.183-0.803), lower use of stents (P < 0.001; OR 0.024, 95% CI 0.004-0.141) and opioid administration (P = 0.005; OR 0.157, 95% CI 0.044-0.567). From our literature search, 194 records were identified and 18 records were included (three comparative and 16 non-comparative). Meta-analysis of the comparative studies and our institutional data showed similar success rates (relative risk [RR] 1.77, 95% CI 0.33-9.52) and complication rates (RR 0.75, 95% CI 0.20-2.82). VH was associated with shorter operative time (standardised mean difference [SMD] -1.65, 95% CI -2.58 to -0.72 h) and hospital stay (SMD -1.41, 95% CI -2.36 to -0.47 days). The VH success rates ranged from 87.5% to 100% in the identified studies. Failure of VH was associated with unrecognised concomitant intrinsic obstruction in addition to CV. CONCLUSIONS: A VH, for well-selected patients with CV without concomitant intrinsic obstruction, offers a high success rate with shorter operative times.

Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves.

BACKGROUND: Early kidney and anatomic features may be predictive of future progression and need for additional procedures in patients with posterior urethral valve (PUV). The objective of this study was to use machine learning (ML) to predict clinically relevant outcomes in these patients. METHODS: Patients diagnosed with PUV with kidney function measurements at our institution between 2000 and 2020 were included. Pertinent clinical measures were abstracted, including estimated glomerular filtration rate (eGFR) at each visit, initial vesicoureteral reflux grade, and renal dysplasia at presentation. ML models were developed to predict clinically relevant outcomes: progression in CKD stage, initiation of kidney replacement therapy (KRT), and need for clean-intermittent catheterization (CIC). Model performance was assessed by concordance index (c-index) and the model was externally validated. RESULTS: A total of 103 patients were included with a median follow-up of 5.7 years. Of these patients, 26 (25%) had CKD progression, 18 (17%) required KRT, and 32 (31%) were prescribed CIC. Additionally, 22 patients were included for external validation. The ML model predicted CKD progression (c-index = 0.77; external C-index = 0.78), KRT (c-index = 0.95; external C-index = 0.89) and indicated CIC (c-index = 0.70; external C-index = 0.64), and all performed better than Cox proportional-hazards regression. The models have been packaged into a simple easy-to-use tool, available at https://share.streamlit.io/jcckwong/puvop/main/app.py CONCLUSION: ML-based approaches for predicting clinically relevant outcomes in PUV are feasible. Further validation is warranted, but this implementable model can act as a decision-making aid. A higher resolution version of the Graphical abstract is available as Supplementary information.

A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: Methods and proof of concept.

INTRODUCTION: The objectivity of vesicoureteral reflux (VUR) grading has come into question for low inter-rater reliability. Using quantitative image features to aid in VUR grading may make it more consistent. OBJECTIVE: To develop a novel quantitative approach to the assignment of VUR from voiding cystourethrograms (VCUG) alone. STUDY DESIGN: An online dataset of VCUGs was abstracted and individual renal units were graded as low-grade (I-III) or high-grade (IV-V). We developed an image analysis and machine learning workflow to automatically calculate and normalize the ureteropelvic junction (UPJ) width, ureterovesical junction (UVJ) width, maximum ureter width, and tortuosity of the ureter based on three simple user annotations. A random forest classifier was trained to distinguish between low-vs high-grade VUR. An external validation cohort was generated from the institutional imaging repository. Discriminative capability was quantified using receiver-operating-characteristic and precision-recall curve analysis. We used Shapley Additive exPlanations to interpret the model's predictions. RESULTS: 41 renal units were abstracted from an online dataset, and 44 renal units were collected from the institutional imaging repository. Significant differences observed in UVJ width, UPJ width, maximum ureter width, and tortuosity between low- and high-grade VUR. A random-forest classifier performed favourably with an accuracy of 0.83, AUROC of 0.90 and AUPRC of 0.89 on leave-one-out cross-validation, and accuracy of 0.84, AUROC of 0.88 and AUPRC of 0.89 on external validation. Tortuosity had the highest feature importance, followed by maximum ureter width, UVJ width, and UPJ width. We deployed this tool as a web-application, qVUR (quantitative VUR), where users are able to upload any VCUG for automated grading using the model generated here (https://akhondker.shinyapps.io/qVUR/). DISCUSSION: This study provides the first step towards creating an automated and more objective standard for determining the significance of VUR features. Our findings suggest that tortuosity and ureter dilatation are predictors of high-grade VUR. Moreover, this proof-of-concept model was deployed in a simple-to-use web application. CONCLUSION: Grading of VUR using quantitative metrics is possible, even in non-standardized datasets of VCUG. Machine learning methods can be applied to objectively grade VUR in the future.

Personalized application of machine learning algorithms to identify pediatric patients at risk for recurrent ureteropelvic junction obstruction after dismembered pyeloplasty.

PURPOSE: To develop a model that predicts whether a child will develop a recurrent obstruction after pyeloplasty, determine their survival risk score, and expected time to re-intervention using machine learning (ML). METHODS: We reviewed patients undergoing pyeloplasty from 2008 to 2020 at our institution, including all children and adolescents younger than 18 years. We developed a two-stage machine learning model from 34 clinical fields, which included patient characteristics, ultrasound findings, and anatomical variation. We fit and trained with a logistic lasso model for binary cure model and subsequent survival model. Feature importance on the model was determined with post-selection inference. Performance metrics included area under the receiver-operating-characteristic (AUROC), concordance, and leave-one-out cross validation. RESULTS: A total of 543 patients were identified, with a median preoperative and postoperative anteroposterior diameter of 23 and 10 mm, respectively. 39 of 232 patients included in the survival model required re-intervention. The cure and survival models performed well with a leave-one-out cross validation AUROC and concordance of 0.86 and 0.78, respectively. Post-selective inference showed that larger anteroposterior diameter at the second post-op follow-up, and anatomical variation in the form of concurrent anomalies were significant model features predicting negative outcomes. The model can be used at https://sickkidsurology.shinyapps.io/PyeloplastyReOpRisk/ . CONCLUSION: Our ML-based model performed well in predicting the risk of and time to re-intervention after pyeloplasty. The implementation of this ML-based approach is novel in pediatric urology and will likely help achieve personalized risk stratification for patients undergoing pyeloplasty. Further real-world validation is warranted.