Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
World Journal of Urology
Published in: World Journal of Urology 9/2019

01-09-2019 | Original Article

Predicting posterior urethral obstruction in boys with lower urinary tract symptoms using deep artificial neural network

Authors: S. Abdovic, M. Cuk, N. Cekada, M. Milosevic, A. Geljic, S. Fusic, M. Bastic, Z. Bahtijarevic

Published in: World Journal of Urology | Issue 9/2019

Login to get access

Abstract

Purpose

To assess the prediction model for late-presenting posterior urethral valve (PUV) in boys with lower urinary tract symptoms (LUTS) using artificial neural network (ANN).

Materials and methods

408 boys aged 3–17 years (median 7.2 years) with LUTS were examined and had bladder diary, ultrasound, uroflowmetry, urine, and urine culture. Cystoscopy was recommended when peak flow rate (Qmax) was persistently ≤ 5th percentile in patients who were unresponsive to urotherapy and pharmacological treatment (oxybutynin). With four-layered backpropagating deep ANN, the probability of finding PUV was estimated using noninvasive, quantitative parameters (age, Qmax, time to Qmax, voided volume, flow time, voiding time, average flow rate).

Results

There were 97 patients with low Qmax and 74 were unresponsive. In 41, cystoscopy was performed and PUV was diagnosed in 37 (9.1%). In multivariate analysis, significant variables in favor of PUV were urgency (OR = 3.96, 95% CI = 1.30–12.03, p = 0.015), increased voiding frequency (OR = 3.81, 95% CI = 1.03–14.11, p = 0.045), and weak stream/intermittency (OR = 8.30, 95% CI = 2.49–27.63, p = 0.001). The ANN dataset included 87 uroflows of children with PUV and 114 uroflows classified as normal. The best performance was with two hidden layers with four neurons each. The best test accuracy was 92.7% and AUROC was 98.0%. With cutoff value of 0.8, sensitivity was 100.0%, specificity 89.7%, positive predictive value 80.0%, and negative predictive value 100.0%.

Conclusions

With ANN, we accurately predicted 92.7% of late-presenting PUV using uroflow. Considering the high frequency of PUV in boys with LUTS, especially in cases of urgency, increased voiding frequency, and weak stream or intermittency, accurate prediction could lead to timely treatment.
Literature
1.
Bomalaski MD, Anema JG, Coplen DE et al (1999) Delayed presentation of posterior urethral valves: a not so benign condition. J Urol 162:2130–2132CrossRefPubMed
2.
Nakamura S, Kawai S, Kubo T et al (2011) Transurethral incision of congenital obstructive lesions in the posterior urethra in boys and its effect on urinary incontinence and urodynamic study. BJU Int 107:1304–1311CrossRefPubMed
3.
Schober JM, Dulabon LM, Woodhouse CR (2004) Outcome of valve ablation in late-presenting posterior urethral valves. BJU Int 94:616–619CrossRefPubMed
4.
de Jong TPVM, Kuijper CF, Chrzan R et al (2013) Efficacy and safety of urethral de-obstruction in boys with overactive bladder complaints. J Pediatr Urol 9:1072–1076CrossRefPubMed
5.
van Gool JD, de Jong TPVM, Winkler-Seinstra P et al (2014) Multi-center randomized controlled trial of cognitive treatment, placebo, oxybutynin, bladder training, and pelvic floor training in children with functional urinary incontinence. Neurourol Urodyn 33:482–487CrossRefPubMed
6.
de Jong TPVM, Radmayr C, Dik P et al (2008) Posterior urethral valves: search for a diagnostic reference standard. Urology 72:1022–1025CrossRefPubMed
7.
Jönson Ring I, Nevéus T, Markström A et al (2017) Nocturnal enuresis impaired children’s quality of life and friendships. Acta Paediatr 106:806–811CrossRefPubMed
8.
Bontempi G, Ben Taieb S, Le Borgne Y-A (2013) Machine learning strategies for time series forecasting. In: Aufaure M-A, Zimányi E (eds) Business intelligence: second European Summer School, eBISS 2012, Brussels, Belgium, July 15–21, 2012, Tutorial Lectures. Springer, Berlin, pp 62–77CrossRef
9.
Austin PF, Bauer SB, Bower W et al (2016) The standardization of terminology of lower urinary tract function in children and adolescents: update report from the standardization committee of the International Children’s Continence Society. Neurourol Urodyn 35:471–481CrossRefPubMed
10.
Szabo L, Fegyverneki S (1995) Maximum and average urine flow rates in normal children-the Miskolc nomograms. BJU Int 76:16–20CrossRef
11.
Cass AS, Stephens FD (1974) Posterior urethral valves: diagnosis and management. J Urol 112:519–525CrossRefPubMed
12.
Kihara T, Nakai H, Mori K-I et al (2008) Variety of congenital urethral lesions in boys with lower urinary tract symptoms and the results of endoscopic treatment. Int J Urol 15:235–240CrossRefPubMed
13.
14.
15.
16.
17.
Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
18.
Lee A, Lee HJ, Lim KB et al (2016) Can intravesical prostatic protrusion predict bladder outlet obstruction even in men with good flow? Asian J Urol 3:39–43CrossRefPubMed
19.
Vijverberg MAW, Klijn AJ, Rabenort A et al (2011) A comparative analysis of pediatric uroflowmetry curves. Neurourol Urodyn 30:1576–1579CrossRefPubMed
20.
de Kort LMO, Uiterwaal CSPM, Beek EJA et al (2004) Reliability of voiding cystourethrography to detect urethral obstruction in boys. Urology 63:967–971 (discussion 971–972) CrossRefPubMed
21.
Smeulders N, Makin E, Desai D et al (2011) The predictive value of a repeat micturating cystourethrogram for remnant leaflets after primary endoscopic ablation of posterior urethral valves. J Pediatr Urol 7:203–208CrossRefPubMed
22.
Matoka DJ, Marks AJ, Stoltz RS, Maizels M (2013) Utilization of computer enhanced visual learning (CEVL) method improves endoscopic diagnosis of posterior urethral valves (PUV). J Pediatr Urol 9:498–502CrossRefPubMed
23.
Sonke GS, Heskes T, Verbeek AL et al (2000) Prediction of bladder outlet obstruction in men with lower urinary tract symptoms using artificial neural networks. J Urol 163:300–305CrossRefPubMed
24.
Wadie BS, Badawi AM, Abdelwahed M, Elemabay SM (2006) Application of artificial neural network in prediction of bladder outlet obstruction: a model based on objective, noninvasive parameters. Urology 68:1211–1214CrossRefPubMed
25.
Franco I, Shei-Dei Yang S, Chang S-J et al (2016) A quantitative approach to the interpretation of uroflowmetry in children. Neurourol Urodyn 35:836–846CrossRefPubMed
26.
27.
Nakamura S, Hyuga T, Kawai S et al (2016) The endoscopic morphological features of congenital posterior urethral obstructions in boys with refractory daytime urinary incontinence and nocturnal enuresis. Eur J Pediatr Surg 26:368–375PubMed
28.
Franco I, Franco J, Lee YS et al (2016) Can a quantitative means be used to predict flow patterns: agreement between visual inspection vs. flow index derived flow patterns. J Pediatr Urol 12:218.e1–218.e8CrossRef
Metadata
Title
Predicting posterior urethral obstruction in boys with lower urinary tract symptoms using deep artificial neural network
Authors
S. Abdovic
M. Cuk
N. Cekada
M. Milosevic
A. Geljic
S. Fusic
M. Bastic
Z. Bahtijarevic
Publication date
01-09-2019
Publisher
Springer Berlin Heidelberg
Published in
World Journal of Urology / Issue 9/2019
Print ISSN: 0724-4983
Electronic ISSN: 1433-8726
DOI
https://doi.org/10.1007/s00345-018-2588-9

Other articles of this Issue 9/2019

World Journal of Urology 9/2019 Go to the issue

Original Article

Laparoscopic and robotic-assisted repair of retrocaval ureter in children: a multi-institutional comparative study with open repair

Letter to Editor

Furthering the external validity of Aquablation and implications for real-world patients

Letter to Editor

Towards the future of upper tract urothelial carcinoma surveillance: lessons learnt from bladder cancer urinary biomarkers

Topic Paper

The current role and future directions of circulating tumor cells and circulating tumor DNA in urothelial carcinoma of the bladder

Original Article

Trifecta outcome of ureteral reconstruction in iatrogenic injury and non-iatrogenic ureteral lesions: a 10-year experience at a tertiary referral center

Original Article

Novel nomograms to predict recurrence and progression in primary non-muscle-invasive bladder cancer: validation of predictive efficacy in comparison with European Organization of Research and Treatment of Cancer scoring system