Predicting obstruction risk using common ultrasonography parameters in paediatric hydronephrosis with machine learning.

OBJECTIVE: To sensitively predict the risk of renal obstruction on diuretic renography using routine reported ultrasonography (US) findings, coupled with machine learning approaches, and determine safe criteria for deferral of diuretic renography. PATIENTS AND METHODS: Patients from two institutions with isolated hydronephrosis who underwent a diuretic renogram within 3 months following renal US were included. Age, sex, and routinely reported US findings (laterality, kidney length, anteroposterior diameter, Society for Fetal Urology [SFU] grade) were abstracted. The drainage half-times were collected from renography and stratified as low risk (<20 min, primary outcome), intermediate risk (20-60 min), and high risk of obstruction (>60 min). A random Forest model was trained to classify obstruction risk, here named the 'Artificial intelligence Evaluation of Renogram Obstruction' (AERO). Model performance was determined by measuring area under the receiver-operating-characteristic curve (AUROC) and decision curve analysis. RESULTS: A total of 304 patients met the inclusion criteria, with a median (interquartile range) age of diuretic renogram at 4 (2-7) months. Of all patients, 48 (16%) were low risk, 102 (33%) were intermediate risk, 156 (51%) were high risk of obstruction based on diuretic renogram. The AERO achieved a binary AUROC of 0.84, multi-class AUROC of 0.74 that was superior to the SFU grade, and external validation (n = 64) binary AUROC of 0.76. The most important features for prediction included age, anteroposterior diameter, and SFU grade. We deployed our application in an easy-to-use application (https://sickkidsurology.shinyapps.io/AERO/). At a threshold probability of 30%, the AERO would allow 66 more patients per 1000 to safely avoid a renogram without missing significant obstruction compared to a strategy in which a renogram is routinely performed for SFU Grade ≥3. CONCLUSIONS: Coupled with machine learning, routine US findings can improve the criteria to determine in which children with isolated hydronephrosis a diuretic renogram can be safely avoided. Further optimisation and validation are required prior to implementation into clinical practice.

Posterior urethral valves in patients with trisomy 21: Similar renal outcomes and rates of volitional voiding.

INTRODUCTION: Posterior urethral valves (PUV) occur in patients with Down Syndrome (DS) at a rate of 3-4%; far higher than the general population. Our understanding of the relationship between PUVs and DS is in its infancy, with the majority of the literature consisting of case reports. In this study, we present the largest known series of DS patients with PUVs. AIM: We hypothesized that patients with DS and PUVs would have worse functional bladder outcomes and renal outcomes when compared to PUV patients without DS. STUDY DESIGN: We queried our prospectively managed multi-institutional database of PUV patients from 1990 to 2021. We identified patients with a concomitant diagnosis of DS and PUV. In addition, we performed a systematic review of the literature describing the presentation of children with PUV and DS. Patient demographics, renal outcomes, voiding habits, surgical interventions, and radiologic images were aggregated and analyzed. RESULTS: Out of the 537 patients in our PUV database, we identified 18 patients with a concomitant diagnosis of PUV and DS, as well as 14 patients with a concomitant diagnosis of PUV and DS from the literature. DS and non-DS patients had a similar age at presentation, 31.5 days (2-731) and 17 (4-846), and length of follow up 6.32 years (2-11.2) and 6.98 (1-13). Both groups had similar nadir creatinines DS 0.43 (0.4-0.8), non-DS 0.31 (0.2-0.5) and similar rates of renal failure (DS 11.1% and non-DS 14.5%). With respect to bladder outcomes, a similar percentage of patients were volitionally voiding at last follow up (DS 72.2% and non-DS 72.3%). Our literature review corroborated these findings. CONCLUSIONS: Patients with DS and PUV have similar renal outcomes to other PUV patients in terms of renal function, progression to renal failure, and probability of volitional voiding with continence. Given the increased rate of PUVs in the DS population, physicians should have a high index of suspicion for PUV when patients with DS present with voiding dysfunction.

Assessing the Utility of Tamsulosin in Delaying Progression to Clean Intermittent Catheterization and End-stage Renal Disease in Patients With Posterior Urethral Valves: Are We Postponing the Inevitable?

OBJECTIVE: To assess whether tamsulosin may aid emptying of the lower urinary tract in posterior urethral valves patients, mitigating the likelihood of progressing to clean intermittent catheterization (CIC) or need for renal replacement therapy. METHODS: We reviewed a prospective institutional database containing posterior urethral valves patients treated between January 2000 and January 2022. After assessing baseline characteristics, Kaplan-Meier survival curves and log-rank tests were generated to assess differences in clinically significant outcomes (progression to CIC, dialysis, or kidney transplantation) between those prescribed tamsulosin and those who were not. RESULTS: A total of 179 patients were included. Fifty-nine patients received tamsulosin prior to initiation of CIC (group 1), and 120 did not (group 2). The baseline characteristics were similar between the two groups, except for anticholinergic use (tamsulosin group - 35/59 vs no tamsulosin - 32/120, P < .001). The median age at tamsulosin initiation was 26.0 months (IQR 15.5-48.6) and the median time from initiation of tamsulosin to progression to CIC was 52.6 months (IQR 10.1-69.3). Kaplan-Meier survival curves showed that patients on tamsulosin were less likely to progress to CIC (P = .021), however, there was no difference in progression to dialysis or kidney transplantation. A Cox-regression analysis controlling for baseline characteristics, including age, anticholinergic use, vesicoureteral reflux severity, and CKD stage at 1-year of life, showed a consistent effect of tamsulosin in delaying progression to CIC (HR 0.444 95%CI 0.218-0.902, P = .025). CONCLUSION: While tamsulosin may delay CIC, it does not appear to delay progression to end-stage renal disease. Additional studies exploring specific patient factors are required to determine the timing and subset who may benefit the most from tamsulosin.

Bladder Cancer Carcinogens: Opportunities for Risk Reduction.

Bladder cancer at an individual level is likely to be the consequence of repeated, long-term exposure to one or more known bladder carcinogens, some of which are endemic or unavoidable in daily life, in addition to host factors. This Mini-Review highlights exposures that are associated with higher risk of bladder cancer, summarizes the evidence for each association, and suggests strategies to decrease risk at both individual and population levels. PATIENT SUMMARY: Tobacco smoking, exposure to certain chemicals in your diet, environment, or workplace, urinary infections, and certain medications can increase your risk of bladder cancer.

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.

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.

Postoperative respiratory complications after adenotonsillectomy in children with obstructive sleep apnea.

OBJECTIVE: Children with obstructive sleep apnea are considered high risk for postoperative respiratory complications, but opinions differ regarding the polysomnography (PSG) criteria that suggest the need for postoperative admission. Our objective was to determine if otherwise healthy children age ≥3 years with an apnea-hypopnea index (AHI) < 24 on overnight PSG can be safely discharged on the same day of surgery. METHODS: Case series with chart review of children age <18 years with positive PSG (AHI > 2) who underwent adenotonsillectomy (T&A) between January 2013 and August 2019. Data collected included patient demographics, medical history, comorbidities, PSG results, operative details, length of stay, intraoperative and postoperative respiratory complications and management. Potential predictors of respiratory complications were evaluated using chi-square/Fisher's exact test and 2-tailed unpaired t tests with the Bonferroni adjustment for multiple comparison artifact. The percentages of healthy children age ≥3 years who were discharged on the day of surgery at various PSG cutoffs were calculated. RESULTS: Of the 560 children, mean (SD) age was 6.4 (3.7) years, 318 (56.8%) were male, 438 (78.2%) were African American, 243 (43.4%) were obese, 16 (2.9%) had Down Syndrome and 12 (2.1%) had sickle cell disease. Median (range) AHI was 12.3 (2-145). Fifteen children (2.7% [95% CI 1.3, 4.0]) had an intraoperative or postoperative respiratory complication. Minor complications including mild desaturation, stridor, croupy cough, and laryngospasm occurred in 9 patients and did not prolong the planned ambulatory or hospital stay. Of the 6 children with more severe complications including prolonged desaturation, tachypnea, atelectasis, intercostal retraction and obstructive apnea requiring continuous positive airway pressure, all were planned admissions based on age, severe sleep study indices (AHI ≥ 24 or oxygen saturation nadir < 80%) or underlying medical condition. Of the 165 children age ≥3 without medical comorbidities known to be predictive of postoperative complications with an AHI ≥10 but <24, 113 (68.5%) were discharged home on the same day of surgery without additional respiratory sequelae. CONCLUSIONS: This study demonstrates a low risk of respiratory complications after T&A. Otherwise healthy children age ≥3 years with AHI <24 may be considered for ambulatory discharge.