A machine learning algorithm predicting risk of dilating VUR among infants with hydronephrosis using UTD classification

BACKGROUNDS

Urinary Tract Dilation (UTD) classification has been designed to be a more objective grading system to evaluate antenatal and post-natal UTD. Due to unclear association between UTD classifications to specific anomalies such as vesico-ureteral reflux (VUR), management recommendations tend to be subjective.

OBJECTIVE

We sought to develop a model to reliably predict VUR from early post-natal ultrasound.

STUDY DESIGN

Radiology records from single institution were reviewed to identify infants aged 0-90 days undergoing early ultrasound for antenatal UTD. Medical records were reviewed to confirm diagnosis of VUR. Primary outcome defined as dilating (≥Gr3) VUR. Exclusion criteria include major congenital urologic anomalies (bilateral renal agenesis, horseshoe kidney, cross fused ectopia, exstrophy) as well as patients without VCUG. Data were split into training/testing sets by 4:1 ratio. Machine learning (ML) algorithm hyperparameters were tuned by the validation set.

RESULTS

In total, 280 patients (540 renal units) were included in the study (73 % male). Median (IQR) age at ultrasound was 27 (18-38) days. 66 renal units were found to have ≥ grade 3 VUR. The final model included gender, ureteral dilation, parenchymal appearance, parenchymal thickness, central calyceal dilation. The model predicted VUR with AUC at 0.81(0.73-0.88) on out-of-sample testing data. Model is shown in the figure.

DISCUSSION

We developed a ML model that can predict dilating VUR among patients with hydronephrosis in early ultrasound. The study is limited by the retrospective and single institutional nature of data source. This is one of the first studies demonstrating high performance for future diagnosis prediction in early hydronephrosis cohort.

CONCLUSIONS

By predicting dilating VUR, our predictive model using machine learning algorithm provides promising performance to facilitate individualized management of children with prenatal hydronephrosis, and identify those most likely to benefit from VCUG. This would allow more selective use of this test, increasing the yield while also minimizing overutilization.

Intradetrusor botox injection and augmentation cystoplasty trends among spina bifida patients at US freestanding children's hospitals

INTRODUCTION

Intra-detrusor botulinum toxin (Botox) injection is a minimally invasive alternative to augmentation cystoplasty in patients with refractory neurogenic bladder. Botox was first used for neurogenic bladder children two decades ago. However, there are no existing guidelines on indications or use among patients with spina bifida. Furthermore, there are little data regarding its use relative to bladder augmentation and patient volume on a national scale.

OBJECTIVE

We sought to investigate the contemporary trends of intra-detrusor Botox injection and augment cystoplasty in free-standing children's hospitals.

STUDY DESIGN

We queried the Pediatric Health Information System database to identify spina bifida patients from 2016 to 2019 who underwent intra-detrusor Botox injection and augment cystoplasty based on CPT and ICD-10 codes. Total spina bifida population under care in the free-standing children's hospitals was estimated by all inpatient and ambulatory surgery encounters as denominators to calculate frequency by time for both intra-detrusor Botox injections and augmentation cystoplasty.

RESULTS

In total, we included 1924 intra-detrusor Botox injections and 842 augmentation cystoplasties. 1413 (51.1%) patients were female. Median age at surgery was 10.0 (interquartile range 6.98-13.5) years. There was a significant increase in intra-detrusor Botox injection frequency (p < 0.001). While there was an overall decreasing, but not significant, trend for augmentation cystoplasty, there was a significant increase in this procedure during the summer months compared to the rest of the year (p < 0.001, Figure 1). Sensitivity analysis using only first intra-detrusor Botox injection per patient demonstrated similarly significant increasing trend.

DISCUSSION

Use of intra-detrusor Botox injection for the management of neurogenic bladder has significantly increased among patients with spina bifida while augmentation cystoplasty has slightly decreased, but not significantly.

CONCLUSIONS

Over time, practice patterns for the treatments of neurogenic bladder among spina bifida children have favored minimally invasive Botox injections while augmentation cystoplasty use has not significantly changed.

Artificial Intelligence in Pediatric Urology

Application of artificial intelligence (AI) is one of the hottest topics in medicine. Unlike traditional methods that rely heavily on statistical assumptions, machine learning algorithms can identify highly complex patterns from data, allowing robust predictions. There is an abundance of evidence of exponentially increasing pediatric urologic publications using AI methodology in recent years. While these studies show great promise for better understanding of disease and patient care, we should be realistic about the challenges arising from the nature of pediatric urologic conditions and practice, in order to continue to produce high-impact research.

Association between lower limb spasticity and cryptorchidism in males with cerebral palsy

AIM

To explore the association between presence and severity of lower limb spasticity (LLS) and risk of orchidopexy for cryptorchidism among people with cerebral palsy (CP) and to further define the cremasteric muscle spasticity theory.

METHOD

We queried the Pediatric Health Information System database for male patients with CP, stratified patients into those with/without LLS, and compared groups for orchidopexy occurrence. Comparative statistics were performed using χ2 and Mann-Whitney U tests for categorical and continuous variables respectively. The association between orchidopexy and spasticity type was investigated using logistic regression.

RESULTS

In total, 44 561 males with CP were identified. Of these, 1.6% underwent orchidopexy (median age: 7 years 8 months [interquartile range: 4 years 6 months-11 years 4 months]). LLS presence was significantly associated with higher orchidopexy rate compared to spasticity absence (odds ratio [OR] = 1.33 [1.10-1.59], p = 0.003). Among 7134 patients with LLS, intervention was significantly associated with higher orchidopexy rate (injection procedures: OR = 2.47 [2.27-6.39], p = 0.034; surgical procedure: OR = 2.60 [1.22-6.76], p = 0.026). LLS groin proximity was significantly associated with higher orchidopexy rate (OR = 2.52 [1.42-4.96], p = 0.003).

INTERPRETATION

A strong association exists between LLS presence and severity and orchidopexy risk among people with CP. These findings support a cremasteric spasticity hypothesis as an important factor of cryptorchidism in CP. Providers should continue to examine for cryptorchidism in males with CP as they age.

WHAT THIS PAPER ADDS

Lower limb spasticity (LLS) is associated with higher orchidopexy rate in cerebral palsy. Orchidopexy rate was higher in more severe LLS. Orchidopexy rate was higher in more proximal LLS.

Novel phenotype characterization utilizing electrical impedance myography signatures in murine spinal cord injury neurogenic bladder models

Neurogenic bladder (NB) affects people of all ages. Electric impedance myography (EIM) assesses localized muscle abnormalities. Here, we sought to investigate whether unique detrusor EIM signatures are present in NB due to spinal cord injury (SCI). Twenty-eight, 8-10 weeks old, C57BL/6J female mice were studied. Twenty underwent spinal cord transection; 8 served as controls. Cohorts were euthanized at 4 and 6 weeks after spinal cord transection. Each bladder was measured in-situ with EIM with applied frequencies of 1 kHz to 10 MHz, and then processed for molecular and histologic study. SCI mice had greater bladder-to-body weight ratio (p < 0.0001), greater collagen deposition (p = 0.009), and greater smooth-muscle-myosin-heavy-chain isoform A/B ratio (p < 0.0001). Compared with the control group, the SCI group was associated with lower phase, reactance, and resistance values (p < 0.01). Significant correlations (p < 0.001) between bladder-to-body weight ratios and EIM measurements were observed across the entire frequency spectrum. A severely hypertrophied phenotype was characterized by even greater bladder-to-body weight ratios and more depressed EIM values. Our study demonstrated distinct EIM alterations in the detrusor muscle of mice with NB due to SCI. With further refinement, EIM may offer a potential point-of-care tool for the assessment of NB and its response to treatment.

High-performance pediatric surgical risk calculator: A novel algorithm based on machine learning and pediatric NSQIP data

BACKGROUNDS

New methods such as machine learning could provide accurate predictions with little statistical assumptions. We seek to develop prediction model of pediatric surgical complications based on pediatric National Surgical Quality Improvement Program(NSQIP).

METHODS

All 2012-2018 pediatric-NSQIP procedures were reviewed. Primary outcome was defined as 30-day post-operative morbidity/mortality. Morbidity was further classified as any, major and minor. Models were developed using 2012-2017 data. 2018 data was used as independent performance evaluation.

RESULTS

431,148 patients were included in the 2012-2017 training and 108,604 were included in the 2018 testing set. Our prediction models had high performance in mortality prediction at 0.94 AUC in testing set. Our models outperformed ACS-NSQIP Calculator in all categories for morbidity (0.90 AUC for major, 0.86 AUC for any, 0.69 AUC in minor complications).

CONCLUSIONS

We developed a high-performing pediatric surgical risk prediction model. This powerful tool could potentially be used to improve the surgical care quality.

Pattern recognition algorithm to identify detrusor overactivity on urodynamics

AIMS

Detrusor overactivity (DO) of the bladder is a finding on urodynamic studies (UDS) that often correlates with lower urinary tract symptoms and drives management. However, UDS interpretation remains nonstandardized. We sought to develop a mathematical model to reliably identify DO in UDS.

METHODS

We utilized UDS archive files for studies performed at our institution between 2013 and 2019. Raw tracings of vesical pressure, abdominal pressure, detrusor pressure, infused volume, and all annotations during UDS were obtained. Patients less than 1 year old, studies with calibration issues, or those with significant artifacts were excluded. In the training set, five representative DO patterns were identified. Candidate Pdet signal segments were matched to representative DO patterns. Manifold learning and dynamic time warping algorithms were used. Five-fold cross validation (CV) was used to evaluate the performance.

RESULTS

A total of 799 UDS studies were included. The median age was 9 years (range, 1-33). There were 1,742 DO events that did not overlap with annotated artifacts (cough, cry, valsalva, movements). The AUC of the training sets from the five-fold CV was 0.84 ± 0.01. The five-fold CV leads to an overall accuracy 81.35%, and sensitivity and specificity of detecting DO events are 76.92% and 81.41%, respectively, in the testing set.

CONCLUSIONS

Our predictive model using machine learning algorithms provides promising performance to facilitate automated identification of DO in UDS. This would allow for standardization and potentially more reliable UDS interpretation. Signal processing and machine learning interpretation of the other components of UDS are forthcoming.