Portal de Periódicos da CAPES

Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning Approaches

2022; Lippincott Williams & Wilkins; Volume: 208; Issue: 6 Linguagem: Inglês

10.1097/ju.0000000000002987

1527-3792

Adree Khondker, Jethro C.C. Kwong, Priyank Yadav, Justin Y.H. Chan, Anuradha Singh, Marta Skreta, Lauren Erdman, Daniel T. Keefe, Katherine Fischer, Gregory E. Tasian, Jessica H. Hannick, Frank Papanikolaou, Benjamin J. Cooper, Christopher S. Cooper, Mandy Rickard, Armando J. Lorenzo,

Urinary Tract Infections Management

No AccessJournal of UrologyPediatric Urology1 Dec 2022Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning ApproachesThis article is commented on by the following:Editorial Comment Adree Khondker, Jethro C. C. Kwong, Priyank Yadav, Justin Y. H. Chan, Anuradha Singh, Marta Skreta, Lauren Erdman, Daniel T. Keefe, Katherine Fischer, Gregory Tasian, Jessica H. Hannick, Frank Papanikolaou, Benjamin J. Cooper, Christopher S. Cooper, Mandy Rickard, and Armando J. Lorenzo Adree KhondkerAdree Khondker https://orcid.org/0000-0003-3246-4662 Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Co-first authors. More articles by this author , Jethro C. C. KwongJethro C. C. Kwong Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada Co-first authors. More articles by this author , Priyank YadavPriyank Yadav Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author , Justin Y. H. ChanJustin Y. H. Chan Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada More articles by this author , Anuradha SinghAnuradha Singh Department of Diagnostic Imaging, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author , Marta SkretaMarta Skreta Department of Computer Science, University of Toronto, Toronto, Ontario, Canada Vector Institute, Toronto, Ontario, Canada More articles by this author , Lauren ErdmanLauren Erdman Department of Computer Science, University of Toronto, Toronto, Ontario, Canada Vector Institute, Toronto, Ontario, Canada More articles by this author , Daniel T. KeefeDaniel T. Keefe Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada Department of Surgery, IWK Hospital, Halifax, Nova Scotia, Canada More articles by this author , Katherine FischerKatherine Fischer Division of Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania More articles by this author , Gregory TasianGregory Tasian Division of Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania More articles by this author , Jessica H. HannickJessica H. Hannick Division of Pediatric Urology, UH Rainbow Babies and Children's Hospital, Cleveland, Ohio More articles by this author , Frank PapanikolaouFrank Papanikolaou Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Trillium Health Partners, Mississauga, Ontario, Canada More articles by this author , Benjamin J. CooperBenjamin J. Cooper Department of Urology, University of Iowa Hospitals and Clinics, Iowa City, Iowa More articles by this author , Christopher S. CooperChristopher S. Cooper Department of Urology, University of Iowa Hospitals and Clinics, Iowa City, Iowa More articles by this author , Mandy RickardMandy Rickard Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author , and Armando J. LorenzoArmando J. Lorenzo †Correspondence: Hospital for Sick Children, 555 University Ave., Toronto, Ontario M5G 1X8, Canada(telephone: 416-813i6580; email: E-mail Address: [email protected] Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002987AboutFull TextPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract 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. References 1. . International system of radiographic grading of vesicoureteric reflux. International Reflux Study in Children. Pediatr Radiol. 1985; 15(2):105-109. Google Scholar 2. . Summary of the AUA guideline on management of primary vesicoureteral reflux in children. J Urol. 2010; 184(3):1134-1144. Link, Google Scholar 3. Interventions for primary vesicoureteric reflux. Cochrane Database Syst Rev. 2019; 2(2):CD001532. Google Scholar 4. . EAU guidelines on vesicoureteral reflux in children. Eur Urol. 2012; 62(3):534-542. Google Scholar 5. RIVUR Trial Investigators, Hoberman A, Greenfield SP, et al. Antimicrobial prophylaxis for children with vesicoureteral reflux. N Engl J Med. 2014; 370(25):2367-2376. Google Scholar 6. . Reliability assessment of international grading system for vesicoureteral reflux. J Urol. 2012; 188(4 suppl):1490-1492. Google Scholar 7. . Reliability of grading of vesicoureteral reflux and other findings on voiding cystourethrography. J Pediatr Urol. 2017; 13(2):192-198. Google Scholar 8. . Reliability of voiding cystourethrogram for the grading of vesicoureteral reflux. J Pediatr Urol. 2014; 10(1):107-111. Google Scholar 9. . Inter-rater reliability of distal ureteral diameter ratio compared to grade of VUR. J Pediatr Urol. 2017; 13(2):207.e1-207.e5. Google Scholar 10. . Non-animal stabilized hyaluronic acid/dextranomer gel (NASHA/dx, deflux) for endoscopic treatment of vesicoureteral reflux: what have we learned over the last 20 Years?Urology. 2021; 157:15-28. Google Scholar 11. . Validation of the ureteral diameter ratio for predicting early spontaneous resolution of primary vesicoureteral reflux. J Pediatr Urol. 2017; 13(4):383.e1-383.e6. Google Scholar 12. . A quantitative grading system of vesicoureteral reflux by contrastenhanced voiding urosonography. Med Ultrason. 2020; 22(3):287-292. Google Scholar 13. . Mild fetal renal pelvis dilatation—much ado about nothing?Clin J Am Soc Nephrol. 2009; 4(1):168-177. Google Scholar 14. . A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: methods and proof of concept. J Pediatr Urol. 2022; 18(1):78.e1-78.e7. Google Scholar 15. . Current status of artificial intelligence applications in urology and their potential to influence clinical practice. BJU Int. 2019;https://bjui-journals.onlinelibrary.wiley.com/doi/full/10.1111/bju.14852. Google Scholar 16. . A reanalysis of the RIVUR trial using a risk classification system. J Urol. 2018; 199(6):1608-1614. Link, Google Scholar 17. . Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves. Pediatr Nephrol. 2022; 37(5):1067-1074. Google Scholar 18. . Standardized reporting of machine learning applications in urology: the STREAM-URO framework. Eur Urol Focus. 2021; 7(4):672-682. Google Scholar 19. R Core Team: R: a language and environment for statistical computing. 2013. Accessed January 1, 2022. https://cran.microsoft.com/snapshot/2014-09-08/web/packages/dplR/vignettes/xdate-dplR.pdf. Google Scholar 20. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011; 12:2825-2830. Google Scholar 21. . Random forests. Mach Learn. 2001; 45:5-32. Google Scholar 22. . Random decision forests. In: ICDAR '95: Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1). IEEE 1995; pp 278-282. Google Scholar 23. . Understanding random forest. How the algorithm works and why it is so effective. Towar Data Sci. 2019. Accessed June 1, 2022. https://towardsdatascience.com/understanding-random-forest-58381e0602d2?gi=79cade6ac40e. Google Scholar 24. . Hyperparameter tuning the random forest in Python. Towar Data Sci. 2018. Accessed June 1, 2022. https://towardsdatascience.com/hyperparameter-tuning-the-random-forest-in-python-using-scikit-learn-28d2aa77dd74. Google Scholar 25. . IBM SPSS Statistics 26 Step by Step: A Simple Guide and Reference. Routledge; 2019. Google Scholar 26. , McLorie G, Geary . The natural history of neonatal vesicoureteral reflux associated with antenatal hydronephrosis. J Urol. 2000; 164(3 Pt 2):1057-1060. Abstract, Google Scholar Submitted May 29, 2022; accepted September 15, 2022; published October 10, 2022. Support: This research was supported by the Hospital for Sick Children and the Urology Care Foundation. A.K. is the recipient of an AUA Summer Medical Student Fellowship (Herbert Brendler, MD Research Fund; ID: 839859). K.F. is the recipent of a 2021 Urology Care Foundation Research Scholar Award Program and the Societies for Pediatric Urology Sushil Lacy, MD Award. The funders had no role in study design, data collection and analysis, decision to publish, or manuscript preparation. Conflict of Interest: The Authors have no conflicts of interest to disclose. Ethics Statement: Ethical approval was received from the Hospital for Sick Children research ethics board (IRB No. 1000068080). © 2022 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetailsCited byWan J (2022) This Month in Pediatric UrologyJournal of Urology, VOL. 208, NO. 6, (1175-1175), Online publication date: 1-Dec-2022.Related articlesJournal of Urology1 Dec 2022Editorial Comment Volume 208Issue 6December 2022Page: 1314-1322Supplementary Materials PEER REVIEW REPORTS Advertisement Copyright & Permissions© 2022 by American Urological Association Education and Research, Inc.Keywordsmachine learningvesico-ureteral refluxurographyreproducibility of resultsMetricsAuthor Information Adree Khondker Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Co-first authors. More articles by this author Jethro C. C. Kwong Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada Co-first authors. More articles by this author Priyank Yadav Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author Justin Y. H. Chan Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada More articles by this author Anuradha Singh Department of Diagnostic Imaging, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author Marta Skreta Department of Computer Science, University of Toronto, Toronto, Ontario, Canada Vector Institute, Toronto, Ontario, Canada More articles by this author Lauren Erdman Department of Computer Science, University of Toronto, Toronto, Ontario, Canada Vector Institute, Toronto, Ontario, Canada More articles by this author Daniel T. Keefe Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada Department of Surgery, IWK Hospital, Halifax, Nova Scotia, Canada More articles by this author Katherine Fischer Division of Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania More articles by this author Gregory Tasian Division of Urology, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania More articles by this author Jessica H. Hannick Division of Pediatric Urology, UH Rainbow Babies and Children's Hospital, Cleveland, Ohio More articles by this author Frank Papanikolaou Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Trillium Health Partners, Mississauga, Ontario, Canada More articles by this author Benjamin J. Cooper Department of Urology, University of Iowa Hospitals and Clinics, Iowa City, Iowa More articles by this author Christopher S. Cooper Department of Urology, University of Iowa Hospitals and Clinics, Iowa City, Iowa More articles by this author Mandy Rickard Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada More articles by this author Armando J. Lorenzo Division of Urology, The Hospital for Sick Children, Toronto, Ontario, Canada Division of Urology, Department of Surgery, University of Toronto, Toronto, Ontario, Canada †Correspondence: Hospital for Sick Children, 555 University Ave., Toronto, Ontario M5G 1X8, Canada(telephone: 416-813i6580; email: E-mail Address: [email protected] More articles by this author Expand All Submitted May 29, 2022; accepted September 15, 2022; published October 10, 2022. Support: This research was supported by the Hospital for Sick Children and the Urology Care Foundation. A.K. is the recipient of an AUA Summer Medical Student Fellowship (Herbert Brendler, MD Research Fund; ID: 839859). K.F. is the recipent of a 2021 Urology Care Foundation Research Scholar Award Program and the Societies for Pediatric Urology Sushil Lacy, MD Award. The funders had no role in study design, data collection and analysis, decision to publish, or manuscript preparation. Conflict of Interest: The Authors have no conflicts of interest to disclose. Ethics Statement: Ethical approval was received from the Hospital for Sick Children research ethics board (IRB No. 1000068080). Advertisement PDF downloadLoading ...