AI-PEDURO - Artificial intelligence in pediatric urology: Protocol for a living scoping review and online repository.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) methods are increasingly being applied in pediatric urology across a growing number of settings, with more extensive databases and wider interest for use in clinical practice. More than 30 ML models have been published in the pediatric urology literature, but many lack items required by contemporary reporting frameworks to be high quality. For example, most studies lack multi-institution validation, validation over time, and validation within the clinical environment, resulting in a large discrepancy between the number of models developed versus the number of models deployed in a clinical setting, a phenomenon known as the AI chasm. Furthermore, pediatric urology is a unique subspecialty of urology with low frequency conditions and complex phenotypes where clinical management can rely on a lower quality of evidence. OBJECTIVE: To establish the AI in PEDiatric UROlogy (AI-PEDURO) collaborative, which will carry out a living scoping review and create an online repository (www.aipeduro.com) for models in the field and facilitate an evidence synthesis of AI models in pediatric urology. METHODS AND ANALYSIS: The scoping review will follow PRISMA-ScR guidelines. We will include ML models identified through standardized search methods of four databases, hand-search papers, and user-submitted models. Retrieved records will be included if they involve ML algorithms for prediction, classification, or risk stratification for pediatric urology conditions. The results will be tabulated and assessed for trends within the literature. Based on data availability, models will be divided into clinical disease sections (e.g. hydronephrosis, hypospadias, vesicoureteral reflux). A risk assessment will be performed using the APPRAISE-AI tool. The retrieved model cards (brief summary model characteristics in table form) will be uploaded to the online repository for open access to clinicians, patients, and data scientists, and will be linked to the Digital Object Identifier (DOI) for each article. DISCUSSION AND CONCLUSION: We hope this living scoping review and online repository will offer a valuable reference for pediatric urologists to assess disease-specific ML models' scope, validity, and credibility to encourage opportunities for collaboration, external validation, clinical testing, and responsible deployment. In addition, the repository may aid in identifying areas in need of further research.

The Hydronephrosis Severity Index guides paediatric antenatal hydronephrosis management based on artificial intelligence applied to ultrasound images alone.

Antenatal hydronephrosis (HN) impacts up to 5% of pregnancies and requires close, frequent follow-up monitoring to determine who may benefit from surgical intervention. To create an automated HN Severity Index (HSI) that helps guide clinical decision-making directly from renal ultrasound images. We applied a deep learning model to paediatric renal ultrasound images to predict the need for surgical intervention based on the HSI. The model was developed and studied at four large quaternary free-standing paediatric hospitals in North America. We evaluated the degree to which HSI corresponded with surgical intervention at each hospital using area under the receiver-operator curve, area under the precision-recall curve, sensitivity, and specificity. HSI predicted subsequent surgical intervention with > 90% AUROC, > 90% sensitivity, and > 70% specificity in a test set of 202 patients from the same institution. At three external institutions, HSI corresponded with AUROCs ≥ 90%, sensitivities ≥ 80%, and specificities > 50%. It is possible to automatically and reliably assess HN severity directly from a single ultrasound. The HSI stratifies low- and high-risk HN patients thus helping to triage low-risk patients while maintaining very high sensitivity to surgical cases. HN severity can be predicted from a single patient ultrasound using a novel image-based artificial intelligence system.

Bortezomib for antibody-mediated rejection of kidney transplant in youth: Associations with donor-specific antibody.

BACKGROUND: Antibody-mediated rejection is one of the most significant risk factors for allograft dysfunction and failure in children and adolescents with kidney transplants, yet optimal treatment remains unidentified. To date, there are mixed findings regarding the use of Bortezomib, a plasma cell apoptosis inducer, as an adjunct therapy in the treatment of antibody-mediated rejection. METHODS: In a retrospective single center study, we reviewed the efficacy and tolerability of bortezomib as adjunct therapy for treatment-refractory antibody-mediated rejection. RESULTS: Six patients with a median age of 14.6 years (range 6.9-20.1 years) received bortezomib at a mean of 71 months (range 15-83 months) post-kidney transplant. Four patients experienced decline in estimated glomerular filtration rate (eGFR) from 4% to 42%. One patient started bortezomib while on hemodialysis and did not recover graft function, and another patient progressed to hemodialysis 6 months after receiving bortezomib. Although DSA did not completely resolve, there was a statistically significant decline in DSA MFI pre and 12-months post-BZ (p = .012, paired t-test) for the subjects who were not on dialysis at the time of bortezomib. Chronic Allograft Damage Index (CADI) score of ≥3 was seen in all six subjects at their biopsy prior to therapy. No adverse effects were reported. CONCLUSIONS: Bortezomib was well tolerated and resulted in improvements in MFI of DSA among four pediatric subjects without allograft failure, although no effects were observed on eGFR trajectory. Further studies are needed to clarify whether earlier intervention with bortezomib could prevent renal failure progression.

Imaging fibrosis in pediatric kidney transplantation: A pilot study.

BACKGROUND: Noninvasive alternatives to biopsy for assessment of interstitial fibrosis and tubular atrophy (IFTA), the major determinant of kidney transplant failure, remain profoundly limited. Elastography is a noninvasive technique that propagates shear waves across tissues to measure their stiffness. We aimed to test utility of elastography for early detection of IFTA in pediatric kidney allografts. METHODS: We compared ultrasound (USE) and MR elastography (MRE) stiffness measurements, performed on pediatric transplant recipients referred for clinically indicated biopsies, and healthy controls. RESULTS: Ten transplant recipients (median age 16 years) and eight controls (median age 16.5 years) were enrolled. Three transplant recipients had "stable" allografts and seven had Banff Grade 1 IFTA. Median time from transplantation to biopsy was 12 months. Mean estimated glomerular filtration rate was 61.5 mL/min/1.73m2 by creatinine-cystatin-C CKiD equation at time of biopsy. Mean stiffness, calculated through one-way ANOVA, was higher for IFTA allografts (23.4 kPa USE/5.6 kPa MRE) than stable allografts (13.7 kPa USE/4.4 kPa MRE) and controls (9.1 kPa USE/3.6 kPa MRE). Pearson's coefficient between USE and MRE stiffness values was strong (r = .97). AUC for fibrosis prediction in transplanted kidneys was high for both modalities (0.91 USE and 0.89 MRE), although statistically nonsignificant (p > .05). Stiffness cut-off values for USE and MRE were 13.8 kPa and 4.6 kPa, respectively. Both values yielded a sensitivity of 100% but USE specificity (72%) was slightly higher than MRE (67%). CONCLUSION: Elastography shows potential for detection of low-grade IFTA in allografts although a larger sample is imperative for clinical validation.

Primary ablation versus urinary diversion in posterior urethral valve: Systematic review and meta-analysis.

PURPOSE: To determine differences in long-term kidney and bladder outcomes in boys with posterior urethral valves (PUV) managed by a primary valve ablation or primary urinary diversion. MATERIALS AND METHODS: A systematic search was performed in March 2021. Comparative studies were evaluated according to Cochrane collaboration recommendations. Assessed measures included kidney outcomes (chronic kidney disease, end-stage renal disease, kidney function) and bladder outcomes. Odds ratios (OR) and mean difference (MD) with 95% confidence interval (CI) were extrapolated from available data for quantitative synthesis. Random-effects meta-analysis and meta-regression were performed according to study design, and potential covariates were assessed with subgroup analysis. The systematic review was prospectively registered on PROSPERO (CRD42021243967). RESULTS: Thirty unique studies describing 1547 boys with PUV were included in this synthesis. Overall effect estimates demonstrate that patients undergoing primary diversion have significantly increased odds of developing renal insufficiency [OR 0.60, 95% CI 0.44, 0.80; p < 0.001]. However, when adjusting for baseline kidney function between intervention groups, there was no significant difference in long term kidney outcomes [p = 0.09, 0.35], or the development of bladder dysfunction or requiring clean-intermittent catheterization with primary ablation rather than diversion [OR 0.89, 95% CI 0.49, 1.59; p = 0.68]. CONCLUSIONS: Current low-quality evidence suggests that medium-term kidney outcomes in children are similar between primary ablation and primary diversion after adjusting for baseline kidney function, while bladder outcomes are highly heterogenous. Further research with covariate control is warranted to investigate sources of heterogeneity. LEVEL OF EVIDENCE: Level III.

Risk of Acute Kidney Injury Following Contrast-enhanced CT in a Cohort of 10 407 Children and Adolescents.

Background Previous studies have challenged the concept of contrast material-induced acute kidney injury (AKI) in adults; however, limited data exist for children and adolescents. Purpose To calculate the incidence and determine the risks of AKI in patients who received intravenous iodinated contrast media for CT. Materials and Methods This retrospective study was performed at a children's hospital from January 2008 to January 2018 and included patients aged 0-17 years in whom serum creatinine levels were measured within 48 hours before and after CT with or without contrast media. The incidence of AKI was measured according to the AKI Network guidelines. A subgroup analysis with propensity score matching of cases with control patients was performed. Differences before and after stratification based on estimated glomerular filtration rate (eGFR) were explored. Adjusted risk models were developed using log-binomial generalized estimating equations to estimate relative risk (RR). Results From a total of 54 000 CT scans, 19 377 scans from 10 407 patients (median age, 8.5 years; IQR, 3-14; 5869 boys, 4538 girls) were included in the analysis. Incidence rate of AKI for the entire sample was 1.5%; it was 1.4% (123 of 8844) in the group that underwent contrast-enhanced CT and 1.6% (171 of 10 533) in the group that did not (P = .18). In the contrast-enhanced CT group, AKI incidence was higher in the group with eGFR of at least 60 mL/min/1.73 m2 and in the group with eGFR lower than 60 mL/min/1.73 m2 (1.3% and 8.5%, respectively; P < .001) compared with the noncontrast group (0.1% and 2.7%, respectively; P < .001). Age was found to be a protective factor against AKI, with an RR of 0.96 (95% CI: 0.94, 0.99; P = .01), and contrast media increased risk in the subgroup analysis, with an RR of 2.19 (95% CI: 1.11, 4.35; P = .02). Conclusion The overall incidence of acute kidney injury after contrast-enhanced CT in children and adolescents was very low, and exposure to contrast media did not increase the risk consistently for acute kidney injury among different groups and analyses. © RSNA, 2022 See also the editorial by McDonald in this issue.

Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves.

BACKGROUND: We sought to use deep learning to extract anatomic features from postnatal kidney ultrasounds and evaluate their performance in predicting the risk and timing of chronic kidney disease (CKD) progression for boys with posterior urethral valves (PUV). We hypothesized that these features would predict CKD progression better than clinical characteristics such as nadir creatinine alone. METHODS: We performed a retrospective cohort study of boys with PUV treated at two pediatric health systems from 1990 to 2021. Features of kidneys were extracted from initial postnatal kidney ultrasound images using a deep learning model. Three time-to-event prediction models were built using random survival forests. The Imaging Model included deep learning imaging features, the Clinical Model included clinical data, and the Ensemble Model combined imaging features and clinical data. Separate models were built to include time-dependent clinical data that were available at 6 months, 1 year, 3 years, and 5 years. RESULTS: Two-hundred and twenty-five patients were included in the analysis. All models performed well with C-indices of 0.7 or greater. The Clinical Model outperformed the Imaging Model at all time points with nadir creatinine driving the performance of the Clinical Model. Combining the 6-month Imaging Model (C-index 0.7; 95% confidence interval [CI] 0.6, 0.79) with the 6-month Clinical Model (C-index 0.79; 95% CI 0.71, 0.86) resulted in a 6-month Ensemble Model that performed better (C-index 0.82; 95% CI 0.77, 0.88) than either model alone. CONCLUSIONS: Deep learning imaging features extracted from initial postnatal kidney ultrasounds may improve early prediction of CKD progression among children with PUV. A higher resolution version of the Graphical abstract is available as Supplementary information.

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.

Ultrasound-Based Renal Parenchymal Area and Kidney Function Decline in Infants With Congenital Anomalies of the Kidney and Urinary Tract.

Congenital anomalies of the kidney and urinary tract are the leading cause of chronic kidney disease in children. Noninvasive imaging biomarkers that predict chronic kidney disease progression in early infancy are needed. We performed a pilot study nested in the prospective Chronic Kidney Disease in Children cohort study to determine the association between renal parenchymal area (RPA) on first post-natal renal ultrasound and change in estimated glomerular filtration rate (eGFR) in children with congenital anomalies of the kidney and urinary tract. Among 14 participants, 78.6% were males, the median age at the time of the ultrasound was 3.4 months (interquartile range, 1.3-7.9 mo), and the median total RPA z-score at baseline was -1.01 (interquartile range, -2.39 to 0.52). After a median follow-up period of 7.4 years (interquartile range, 6.8-8.2 y), the eGFR decreased from a median of 49.4 mL/min per 1.73 m2 at baseline to 29.4 mL/min per 1.73 m2, an annual eGFR percentage decrease of -4.68%. Lower RPA z-scores were correlated weakly with a higher annual decrease in eGFR (Spearman correlation, 0.35; 95% confidence interval, -0.25 to 0.76). This pilot study shows the feasibility of obtaining RPA from a routine ultrasound and suggests that a lower baseline RPA may be associated with a greater decrease in eGFR over time. Further studies with larger patient cohorts are needed to confirm this association.

Potential benefits of functional magnetic resonance urography (fMRU) over MAG3 renal scan in children with obstructive uropathy.

INTRODUCTION: Functional renal imaging, most commonly with MAG3 nuclear medicine renal scan, is recommended in the evaluation of children with urinary tract dilation (UTD) suspected of obstructive uropathy. Alternatively, renal function can be evaluated with functional Magnetic Resonance Urography (fMRU), which has superior anatomic detail. However, there are not enough data comparing both methods' equivalency. In this study, we compare the functional and obstruction parameters of fMRU and MAG3 in a pediatric cohort presenting with obstructive uropathy. STUDY DESIGN: This is an IRB-approved retrospective review of all children undergoing fMRU at a single, free-standing children's hospital between May 2008 and September 2017. Patients who also underwent a MAG3 renal scan within 6 months and who had no interval surgical intervention were included in the study. Bladder catheterization was performed prior to both imaging studies. RESULTS: 735 children had 988 fMRU studies performed during the study period. 37 unique patients (13 girls and 24 boys) with median age of 6 months (range: 2 mo-19 y) were included in the final sample. Median time interval between studies was 70 days (range 6-179 days). The majority of participants (26/37, 70.3%) presented with UTD P3 and had diagnosis of uretero-pelvic junction obstruction (UPJO) in 21/37. Differential renal function (DRF) was used to group 10 fMRU and 9 MAG3 patients as normal; 9 fMRU and 11 MAG3 as mild; 11 fMRU and 6 MAG3 as moderate; and 7 fMRU and 6 MAG3 as severe; Wilcoxon signed-rank test (p = 0.5106). Results were similar for DRF among patients with and without duplex kidneys. In the analysis of obstruction, using reference standard T½ MAG3 ≥ 20 min, a greater or equal than 6 min renal transit time (RTT) from fMRU showed a specificity of 94%, a sensitivity of 62%, and an AUC of 0.827. DISCUSSION AND CONCLUSIONS: The differential renal function determined by MAG3 and fMRU in children was not statistically different, therefore we concluded that it was similar and potentially equivalent. Better correlation was shown in patients who had normal split kidney function. While the tests are clinically equivalent, the variability of DRF within each clinical category (i.e., normal, mild, moderate, severe) is not surprising, because MAG3 does not clearly differentiate the dilated collecting system from the functional parenchymal tissue, while fMRU does. Using MAG3 as the gold standard, fMRU was 94.74% specific and 5% more sensitive in detecting UPJO with a RTT of 6min vs. 8min.

Contrast-enhanced ultrasound of transplant organs - liver and kidney - in children.

Ultrasound (US) is the first-line imaging tool for evaluating liver and kidney transplants during and after the surgical procedures. In most patients after organ transplantation, gray-scale US coupled with color/power and spectral Doppler techniques is used to evaluate the transplant organs, assess the patency of vascular structures, and identify potential complications. In technically difficult or inconclusive cases, however, contrast-enhanced ultrasound (CEUS) can provide prompt and accurate diagnostic information that is essential for management decisions. CEUS is indicated to evaluate for vascular complications including vascular stenosis or thrombosis, active bleeding, pseudoaneurysms and arteriovenous fistulas. Parenchymal indications for CEUS include evaluation for perfusion defects and focal inflammatory and non-inflammatory lesions. When transplant rejection is suspected, CEUS can assist with prompt intervention by excluding potential underlying causes for organ dysfunction. Intracavitary CEUS applications can evaluate the biliary tract of a liver transplant (e.g., for biliary strictures, bile leak or intraductal stones) or the urinary tract of a renal transplant (e.g., for urinary obstruction, urine leak or vesicoureteral reflux) as well as the position and patency of hepatic, biliary and renal drains and catheters. The aim of this review is to present current experience regarding the use of CEUS to evaluate liver and renal transplants, focusing on the examination technique and interpretation of the main imaging findings, predominantly those related to vascular complications.

State-of-the-Art Renal Imaging in Children.

Imaging modalities for diagnosing kidney and urinary tract disorders in children have developed rapidly over the last decade largely because of advancement of modern technology. General pediatricians and neonatologists are often the front line in detecting renal anomalies. There is a lack of knowledge of the applicability, indications, and nephrotoxic risks of novel renal imaging modalities. Here we describe the clinical impact of congenital anomalies of the kidneys and urinary tract and describe pediatric-specific renal imaging techniques by providing a practical guideline for the diagnosis of kidney and urinary tract disorders.

Liver, Spleen, and Kidney Size in Children as Measured by Ultrasound: A Systematic Review.

Ultrasound is commonly the first-line imaging modality for assessing the pediatric abdomen. An abnormal size of the liver, spleen, or kidneys may indicate disease, but the evaluation is challenging because the normal size changes with age. In addition, published normal value charts for children may vary by population and methods. In this systematic review, we summarized published data on the normal size of the pediatric liver, spleen, and kidneys as measured by ultrasound in which we found similar values across different populations, ages, and sexes.

Risk Factors for Recurrent Urinary Tract Infection and Renal Scarring.

OBJECTIVES: To identify risk factors for recurrent urinary tract infection (UTI) and renal scarring in children who have had 1 or 2 febrile or symptomatic UTIs and received no antimicrobial prophylaxis. METHODS: This 2-year, multisite prospective cohort study included 305 children aged 2 to 71 months with vesicoureteral reflux (VUR) receiving placebo in the RIVUR (Randomized Intervention for Vesicoureteral Reflux) study and 195 children with no VUR observed in the CUTIE (Careful Urinary Tract Infection Evaluation) study. Primary exposure was presence of VUR; secondary exposures included bladder and bowel dysfunction (BBD), age, and race. Outcomes were recurrent febrile or symptomatic urinary tract infection (F/SUTI) and renal scarring. RESULTS: Children with VUR had higher 2-year rates of recurrent F/SUTI (Kaplan-Meier estimate 25.4% compared with 17.3% for VUR and no VUR, respectively). Other factors associated with recurrent F/SUTI included presence of BBD at baseline (adjusted hazard ratio: 2.07 [95% confidence interval (CI): 1.09-3.93]) and presence of renal scarring on the baseline (99m)Tc-labeled dimercaptosuccinic acid scan (adjusted hazard ratio: 2.88 [95% CI: 1.22-6.80]). Children with BBD and any degree of VUR had the highest risk of recurrent F/SUTI (56%). At the end of the 2-year follow-up period, 8 (5.6%) children in the no VUR group and 24 (10.2%) in the VUR group had renal scars, but the difference was not statistically significant (adjusted odds ratio: 2.05 [95% CI: 0.86-4.87]). CONCLUSIONS: VUR and BBD are risk factors for recurrent UTI, especially when they appear in combination. Strategies for preventing recurrent UTI include antimicrobial prophylaxis and treatment of BBD.

Facial nerve palsy in a 3-year-old child with severe hypertension.

We report an interesting case of a child with new-onset malignant hypertension (HTN) associated with facial paralysis. A review of the medical literature on this association and discussion of diagnostic and management aspects are included.

Evaluation of differential renal function and renographic patterns in patients with dietl crisis.

PURPOSE: We analyzed preoperative and postoperative differential renal function and characterized the renographic findings in patients with ureteropelvic junction obstruction associated with Dietl crisis. MATERIALS AND METHODS: Patients with Dietl crisis who underwent pyeloplasty between January 2004 and December 2010 were classified by renographic presentation. Patients in group 1 were diagnosed with cortical retention, those in group 2 had an initial obstructed scan (T1/2 of 20 minutes or more and no cortical retention) and those in group 3 had an initial nondiagnostic scan (T1/2 of less than 20 minutes and no cortical retention). Renographic parameters were used to analyze each group. RESULTS: A total of 59 patients met criteria for study inclusion. The 13 patients in group 1 demonstrated the most significant recovery of function after pyeloplasty (mean differential renal function change 13.59%). The 38 patients in group 2 exhibited a mean differential renal function change of 43.06% (range 20% to 54.6%) and mean preoperative T1/2 of 64.31 minutes. Pyeloplasty was performed in all 8 patients in group 3 based on subsequent diagnostic scan (4 patients) or increased hydronephrosis on other imaging associated with further symptomatic episodes (4). Initial renographic patterns noted in group 3 included biphasic curves, diminished clearance after 15 minutes upright or symptoms despite nonobstructive drainage. CONCLUSIONS: Interpretation of diuretic renography requires the assimilation of multiple parameters since patients with Dietl crisis can exhibit variability in renographic patterns due to the intermittent nature of ureteropelvic junction obstruction. Cortical retention represents a specific and pathognomic finding of acute ureteropelvic junction obstruction. With appropriate evaluation of these parameters, obstruction can be reliably diagnosed and appropriate surgical candidates chosen.