Predictive Models for the Management of Vesicoureteral Reflux from the View of Statisticians
DOI:
https://doi.org/10.6000/1929-6029.2013.02.02.07Keywords:
Modeling, Vesicoureteral reflux (VUR), Regression, Artificial neural networks (ANN), Decision supportAbstract
The management of vesicoureteral reflux (VUR) is one of the most challenging issues not only for pediatric urologists but also for pediatric nephrologists and all other related subspecialties. Urinary tract infections (UTI), pyelonephritis and renal scarring which may lead to deterioration in renal function are the common complications in a child presenting with VUR. Due to the patient heterogeneity and varying management options, patient selection for each treatment modality remains as a controversial issue. The different bio-statistical models have been used in order to disclose the factors affecting success of different management modalities and represent the incidence of possible complications. Bio-statistical models are useful to define variables which may help predict the outcome of disease during the different managements. Artificial neural networks (ANN) and regression models are popular methods employed to predict the outcome of urological abnormalities. Statistical models and ANNs provide an estimation of the probability of outcome that is of utmost importance in clinical decision. This study addresses both bio-statistical methods and ANNs employed to predict the outcome of VUR management and their clinical applications. To reach the best fit model that predicts the VUR outcome in a child, widespread knowledge regarding available bio-statistical methods is needed.
References
Peters CA, Skoog SJ, Arant BS Jr., Copp HL, Elder JS, Hudson RG, et al. Summary of the AUA Guideline on Management of Primary Vesicoureteral Reflux in Children. J Urol. 2010; 184(3): 1134-44. http://www.ncbi.nlm.nih.gov/ pubmed/20650499. http://dx.doi.org/10.1016/j.juro.2010.05.065 DOI: https://doi.org/10.1016/j.juro.2010.05.065
Cooper CS. Diagnosis and management of vesicoureteral reflux in children. Nat Rev Urol 2009; 6(9): 481-9. http://www.ncbi.nlm.nih.gov/pubmed/19668250. DOI: https://doi.org/10.1038/nrurol.2009.150
Vittinghoff E, Glidden DV, Shiboski SC, McCulloch CE. Regression methods in biostatistics: linear, logistic, survival, and repeated measures models: Springer 2011. DOI: https://doi.org/10.1007/978-1-4614-1353-0
Vach W, Roßner R, Schumacher M. Neural networks and logistic regression. Comput Statist Data Anal 1996; 21: 683. http://dx.doi.org/10.1016/0167-9473(95)00033-X DOI: https://doi.org/10.1016/0167-9473(95)00033-X
Wang L, Fu K. Artificial neural networks: Wiley Online Library 2009. DOI: https://doi.org/10.1002/9780470050118.ecse021
Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 1996; 49(11): 1225-31. http://dx.doi.org/10.1016/S0895-4356(96)00002-9 DOI: https://doi.org/10.1016/S0895-4356(96)00002-9
Remzi M, Djavan B. Artificial neural networks in Urology 2004. Eur Urol Suppl 2004; 3(3): 33-8. http://dx.doi.org/10.1016/j.eursup.2004.02.016 DOI: https://doi.org/10.1016/j.eursup.2004.02.016
Kirkwood BR. Essentials of medical statistics: Blackwell Scientific Publications 1988.
Harrell Jr FE. rms: Regression Modeling Strategies. R package version 2009; 2: 1-0.
Harrell FE. Regression modeling strategies: with applications to linear models, logistic regression, and survival analysis: Springer 2001. DOI: https://doi.org/10.1007/978-1-4757-3462-1
Hosmer DW, Lemeshow S, May S. Applied survival analysis: regression modeling of time to event data: Wiley-Interscience 2011.
Efron B. Logistic regression, survival analysis, and the Kaplan-Meier curve. J Amn Statist Assoc 1988; 83(402): 414-25. http://dx.doi.org/10.1080/01621459.1988.10478612 DOI: https://doi.org/10.1080/01621459.1988.10478612
Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 2002; 35(5): 352-9. http://dx.doi.org/10.1016/S1532-0464(03)00034-0 DOI: https://doi.org/10.1016/S1532-0464(03)00034-0
Carter DB, Signorino CS. Back to the future: Modeling time dependence in binary data. Political Anal 2010; 18(3): 271-92. http://dx.doi.org/10.1093/pan/mpq013 DOI: https://doi.org/10.1093/pan/mpq013
Pradhan B, Lee S. Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environ Model Software 2010; 25(6): 747-59. http://dx.doi.org/10.1016/j.envsoft.2009.10.016 DOI: https://doi.org/10.1016/j.envsoft.2009.10.016
Kleinbaum DG, Klein M. Maximum likelihood techniques: An overview. Logistic regression 2010; pp. 103-27. DOI: https://doi.org/10.1007/978-1-4419-1742-3_4
Hosmer DW, Taber S, Lemeshow S. The importance of assessing the fit of logistic regression models: a case study. Am J Public Health 1991; 81(12): 1630-5. http://dx.doi.org/10.2105/AJPH.81.12.1630 DOI: https://doi.org/10.2105/AJPH.81.12.1630
Muthén B, Asparouhov T. Beyond multilevel regression modeling: Multilevel analysis in a general latent variable framework. Handbook of Advanced Multilevel Analysis 2011; 15-40.
Hilbe J. Logistic regression models: CRC Press 2009. DOI: https://doi.org/10.1201/9781420075779
Janssen KJ, Siccama I, Vergouwe Y, Koffijberg H, Debray TP, Keijzer M, et al. Development and validation of clinical prediction models: marginal differences between logistic regression, penalized maximum likelihood estimation, and genetic programming. J Clin Epidemiol 2012; 65(4): 404-12. http://www.ncbi.nlm.nih.gov/pubmed/22214734. http://dx.doi.org/10.1016/j.jclinepi.2011.08.011 DOI: https://doi.org/10.1016/j.jclinepi.2011.08.011
Steyerberg EW, Borsboom GJ, van Houwelingen HC, Eijkemans MJ, Habbema JDF. Validation and updating of predictive logistic regression models: a study on sample size and shrinkage. Statist Med 2004; 23(16): 2567-86. http://dx.doi.org/10.1002/sim.1844 DOI: https://doi.org/10.1002/sim.1844
Cox DR. Regression models and life-tables. J Royal Statist Soc Ser B (Methodological) 1972; 187-220. DOI: https://doi.org/10.1111/j.2517-6161.1972.tb00899.x
Fisher LD, Lin D. Time-dependent covariates in the Cox proportional-hazards regression model. Ann Rev Public Health 1999; 20(1): 145-57. http://dx.doi.org/10.1146/annurev.publhealth.20.1.145 DOI: https://doi.org/10.1146/annurev.publhealth.20.1.145
Schemper M, Wakounig S, Heinze G. The estimation of average hazard ratios by weighted Cox regression. Statist Med 2009; 28(19): 2473-89. http://dx.doi.org/10.1002/sim.3623 DOI: https://doi.org/10.1002/sim.3623
Vu DQ, Asuncion AU, Hunter DR, Smyth P. Continuous-time regression models for longitudinal networks. Advances in Neural Information Processing Systems MIT Press 2011.
Karnehed N, Rasmussen F, Hemmingsson T, Tynelius P. Obesity and attained education: cohort study of more than 700,000 Swedish men. Obesity 2012; 14(8): 1421-8. http://dx.doi.org/10.1038/oby.2006.161 DOI: https://doi.org/10.1038/oby.2006.161
Jankowska EA, Rozentryt P, Witkowska A, Nowak J, Hartmann O, Ponikowska B, et al. Iron deficiency: an ominous sign in patients with systolic chronic heart failure. Eur Heart J 2010; 31(15): 1872-80. http://dx.doi.org/10.1093/eurheartj/ehq158 DOI: https://doi.org/10.1093/eurheartj/ehq158
Zheng W, McLerran DF, Rolland B, Zhang X, Inoue M, Matsuo K, et al. Association between body-mass index and risk of death in more than 1 million Asians. New Engl J Med 2011; 364(8): 719-29. http://dx.doi.org/10.1056/NEJMoa1010679 DOI: https://doi.org/10.1056/NEJMoa1010679
Altman DG, Andersen PK. Bootstrap investigation of the stability of a Cox regression model. Statist Med 2006; 8(7): 771-83. http://dx.doi.org/10.1002/sim.4780080702 DOI: https://doi.org/10.1002/sim.4780080702
Sauerbrei W, Schumacher M. A bootstrap resampling procedure for model building: Application to the cox regression model. Statist Med 1992; 11(16): 2093-109. http://dx.doi.org/10.1002/sim.4780111607 DOI: https://doi.org/10.1002/sim.4780111607
Kajbafzadeh AM, Tourchi A, Aryan Z. Factors that impact the outcome of endoscopic correction of vesicoureteral reflux: a multivariate analysis. Int Urol Nephrol 2013; 45(1): 1-9. http://www.ncbi.nlm.nih.gov/pubmed/23161378. http://dx.doi.org/10.1007/s11255-012-0327-5 DOI: https://doi.org/10.1007/s11255-012-0327-5
Austin JC, Cooper CS. Vesicoureteral reflux: who benefits from correction. Urol Clin North Am 2010; 37(2): 243-52. http://www.ncbi.nlm.nih.gov/pubmed/20569802. http://dx.doi.org/10.1016/j.ucl.2010.03.012 DOI: https://doi.org/10.1016/j.ucl.2010.03.012
Kaplan GW. Words of wisdom: re: observation of patients with vesicoureteral reflux off antibiotic prophylaxis: physician bias on patient selection and risk factors for recurrent febrile urinary tract infection. Eur Urol 2013; 63(2): 403. http://www.ncbi.nlm.nih.gov/pubmed/23272735. http://dx.doi.org/10.1016/j.eururo.2012.11.020 DOI: https://doi.org/10.1016/j.eururo.2012.11.020
Drzewiecki BA, Thomas JC, Pope JCt, Adams MC, Brock JW 3rd, Tanaka ST. Observation of patients with vesicoureteral reflux off antibiotic prophylaxis: physician bias on patient selection and risk factors for recurrent febrile urinary tract infection. J Urol 2012; 188(4 Suppl): 1480-4. http://www.ncbi. nlm.nih.gov/pubmed/22906676. http://dx.doi.org/10.1016/j.juro.2012.02.033 DOI: https://doi.org/10.1016/j.juro.2012.02.033
Tekgul S, Riedmiller H, Hoebeke P, Kocvara R, Nijman RJ, Radmayr C, et al. EAU Guidelines on Vesicoureteral Reflux in Children. Eur Urol 2012. http://www.ncbi.nlm.nih.gov/ pubmed/22698573. DOI: https://doi.org/10.1016/j.eururo.2012.05.059
Knudson MJ, Austin JC, Wald M, Makhlouf AA, Niederberger CS, Cooper CS. Computational model for predicting the chance of early resolution in children with vesicoureteral reflux. J Urol 2007; 178(4 Pt 2): 1824-7. http://www.ncbi.nlm. nih.gov/pubmed/17707424. http://dx.doi.org/10.1016/j.juro.2007.05.093 DOI: https://doi.org/10.1016/j.juro.2007.05.093
Lebowitz RL, Olbing H, Parkkulainen KV, Smellie JM, Tamminen-Mobius TE. International system of radiographic grading of vesicoureteric reflux. International Reflux Study in Children. Pediatr Radiol 1985; 15(2): 105-9. http://www.ncbi. nlm.nih.gov/pubmed/3975102. http://dx.doi.org/10.1007/BF02388714 DOI: https://doi.org/10.1007/BF02388714
Shiraishi K, Matsuyama H, Nepple KG, Wald M, Niederberger CS, Austin CJ, et al. Validation of a prognostic calculator for prediction of early vesicoureteral reflux resolution in children. J Urol 2009; 182(2): 687-90; discussion 90-1. http://www.ncbi.nlm.nih.gov/pubmed/ 19539324. http://dx.doi.org/10.1016/j.juro.2009.04.036 DOI: https://doi.org/10.1016/j.juro.2009.04.036
Camacho V, Estorch M, Fraga G, Mena E, Fuertes J, Hernandez MA, et al. DMSA study performed during febrile urinary tract infection: a predictor of patient outcome? Eur J Nucl Med Mol Imaging 2004; 31(6): 862-6. http://www.ncbi. nlm.nih.gov/pubmed/14758509. http://dx.doi.org/10.1007/s00259-003-1410-z DOI: https://doi.org/10.1007/s00259-003-1410-z
Nepple KG, Knudson MJ, Austin JC, Wald M, Makhlouf AA, Niederberger CS, et al. Adding renal scan data improves the accuracy of a computational model to predict vesicoureteral reflux resolution. J Urol 2008; 180(4 Suppl): 1648-
; discussion 52. http://www.ncbi.nlm.nih.gov/pubmed/ 18715584. http://dx.doi.org/10.1016/j.juro.2008.03.109 DOI: https://doi.org/10.1016/j.juro.2008.03.109
Zerati Filho M, Calado AA, Barroso U Jr., Amaro JL. Spontaneous resolution rates of vesicoureteral reflux in Brazilian children: a 30-year experience. Int Braz J Urol 2007; 33(2): 204-12; discussion 13-5. http://www.ncbi.nlm. nih.gov/pubmed/17488541. http://dx.doi.org/10.1590/S1677-55382007000200012 DOI: https://doi.org/10.1590/S1677-55382007000200012
Huang FY, Tsai TC. Resolution of vesicoureteral reflux during medical management in children. Pediatr Nephrol 1995; 9(6): 715-7. http://www.ncbi.nlm.nih.gov/pubmed/ 8747111. http://dx.doi.org/10.1007/BF00868720 DOI: https://doi.org/10.1007/BF00868720
Estrada CR Jr., Passerotti CC, Graham DA, Peters CA, Bauer SB, Diamond DA, et al. Nomograms for predicting annual resolution rate of primary vesicoureteral reflux: results from 2,462 children. J Urol 2009; 182(4): 1535-41. http://www.ncbi.nlm.nih.gov/pubmed/19683762. http://dx.doi.org/10.1016/j.juro.2009.06.053 DOI: https://doi.org/10.1016/j.juro.2009.06.053
Elmore JM, Scherz HC, Kirsch AJ. Dextranomer/hyaluronic acid for vesicoureteral reflux: success rates after initial treatment failure. J Urol 2006; 175(2): 712-5. http://www.ncbi. nlm.nih.gov/pubmed/16407036. http://dx.doi.org/10.1016/S0022-5347(05)00187-4 DOI: https://doi.org/10.1016/S0022-5347(05)00187-4
Routh JC, Reinberg Y, Ashley RA, Inman BA, Wolpert JJ, Vandersteen DR, et al. Multivariate comparison of the efficacy of intraureteral versus subtrigonal techniques of dextranomer/hyaluronic acid injection. J Urol 2007; 178(4 Pt 2): 1702-5; discussion 5-6. http://www.ncbi.nlm.nih.gov/ pubmed/17707019. DOI: https://doi.org/10.1016/j.juro.2007.03.174
Lorenzo AJ, Pippi Salle JL, Barroso U, Cook A, Grober E, Wallis MC, et al. What are the most powerful determinants of endoscopic vesicoureteral reflux correction? Multivariate analysis of a single institution experience during 6 years. J Urol 2006; 176(4 Pt 2): 1851-5. http://www.ncbi.nlm.nih.gov/ pubmed/16945671. http://dx.doi.org/10.1016/S0022-5347(06)00599-4 DOI: https://doi.org/10.1016/S0022-5347(06)00599-4
Dave S, Lorenzo AJ, Khoury AE, Braga LH, Skeldon SJ, Suoub M, et al. Learning from the learning curve: factors associated with successful endoscopic correction of vesicoureteral reflux using dextranomer/hyaluronic acid copolymer. J Urol 2008; 180(4 Suppl): 1594-9; discussion 9-600. http://www.ncbi.nlm.nih.gov/pubmed/18710756. http://dx.doi.org/10.1016/j.juro.2008.03.084 DOI: https://doi.org/10.1016/j.juro.2008.03.084
Yucel S, Gupta A, Snodgrass W. Multivariate analysis of factors predicting success with dextranomer/hyaluronic acid injection for vesicoureteral reflux. J Urol 2007; 177(4): 1505-9. http://www.ncbi.nlm.nih.gov/pubmed/17382765. http://dx.doi.org/10.1016/j.juro.2006.11.077 DOI: https://doi.org/10.1016/j.juro.2006.11.077
Kajbafzadeh A-M, Aryan Z, Tourchi A, Alizadeh H. Long-term Ultrasound Appearance of Concomitant Autologous Blood and Dextranomer/Hyaluronic Acid Copolymer Implants: Is It Associated With Successful Correction of Vesicoureteral Reflux? Urology 2013; 81(2): 407-13. http://linkinghub. elsevier.com/retrieve/pii/S0090429512012253?showall=true. http://dx.doi.org/10.1016/j.urology.2012.10.006 DOI: https://doi.org/10.1016/j.urology.2012.10.006
Lavelle MT, Conlin MJ, Skoog SJ. Subureteral injection of Deflux for correction of reflux: analysis of factors predicting success. Urology 2005; 65(3): 564-7. http://www.ncbi.nlm. nih.gov/pubmed/15780377. http://dx.doi.org/10.1016/j.urology.2004.09.068 DOI: https://doi.org/10.1016/j.urology.2004.09.068
Routh JC, Inman BA, Reinberg Y. Dextranomer/hyaluronic acid for pediatric vesicoureteral reflux: systematic review. Pediatrics 2010; 125(5): 1010-9. http://www.ncbi.nlm.nih.gov/ pubmed/20368325. http://dx.doi.org/10.1542/peds.2009-2225 DOI: https://doi.org/10.1542/peds.2009-2225
Routh JC, Kramer SA, Inman BA, Ashley RA, Wolpert JJ, Vandersteen DR, et al. Utility of dextranomer/hyaluronic acid injection in setting of bladder and ureteral anomalies. Urology 2008; 71(3): 435-8. http://www.ncbi.nlm.nih.gov/pubmed/ 18342182. http://dx.doi.org/10.1016/j.urology.2007.10.043 DOI: https://doi.org/10.1016/j.urology.2007.10.043
Yucel S, Ucar M, Guntekin E, Kukul E, Melikoglu M, Baykara M. The effect of location of the ureteric orifice on the efficacy of endoscopic injection to correct vesico-ureteric reflux. BJU Int 2005; 95(9): 1314-8. http://www.ncbi.nlm.nih.gov/pubmed/ 15892824. http://dx.doi.org/10.1111/j.1464-410X.2005.05525.x DOI: https://doi.org/10.1111/j.1464-410X.2005.05525.x
Kajbafzadeh AM, Tourchi A. Usefulness of concomitant autologous blood and dextranomer/hyaluronic Acid copolymer injection to correct vesicoureteral reflux. J Urol 2012; 188(3): 948-52. http://www.ncbi.nlm.nih.gov/pubmed/ 22819104. http://dx.doi.org/10.1016/j.juro.2012.04.119 DOI: https://doi.org/10.1016/j.juro.2012.04.119
Stroup DF, Berlin JA, Morton SC, Olkin I, Williamson GD, Rennie D, et al. Meta-analysis of observational studies in epidemiology. JAMA: J Am Med Assoc 2000; 283(15): 2008-12. http://dx.doi.org/10.1001/jama.283.15.2008 DOI: https://doi.org/10.1001/jama.283.15.2008
Kaye JD, Srinivasan AK, Delaney C, Cerwinka WH, Elmore JM, Scherz HC, et al. Clinical and radiographic results of endoscopic injection for vesicoureteral reflux: Defining measures of success. J Pediatr Urol 2012; 8(3): 297-303. http://www.ncbi.nlm.nih.gov/pubmed/21543259. http://dx.doi.org/10.1016/j.jpurol.2011.02.006 DOI: https://doi.org/10.1016/j.jpurol.2011.02.006
Hunziker M, Mohanan N, D'Asta F, Puri P. Incidence of febrile urinary tract infections in children after successful endoscopic treatment of vesicoureteral reflux: a long-term follow-up. J Pediatr 2012; 160(6): 1015-20. http://www.ncbi.nlm.nih.gov/pubmed/22284917. http://dx.doi.org/10.1016/j.jpeds.2011.12.033 DOI: https://doi.org/10.1016/j.jpeds.2011.12.033
Yegnanarayana B. Artificial neural networks: PHI Learning Pvt. Ltd. 2004.
Fyfe C. Artificial Neural Networks. Do Smart Adaptive Systems Exist? 2005; 57-79. DOI: https://doi.org/10.1007/3-540-32374-0_4
Zurada JM. Introduction to artificial neural systems: West St. Paul, Minn 1992.
Yao X. Evolving artificial neural networks. Proc IEEE 1999; 87(9): 1423-47. http://dx.doi.org/10.1109/5.784219 DOI: https://doi.org/10.1109/5.784219
Hagan MT, Menhaj MB. Training feedforward networks with the Marquardt algorithm. Neural Networks, IEEE Transactions on. 1994; 5(6): 989-93. http://dx.doi.org/10.1109/72.329697 DOI: https://doi.org/10.1109/72.329697
Hashem S, Schmeiser B, Yih Y, Eds. Optimal linear combinations of neural networks: an overview. Neural Networks, 1994 IEEE World Congress on Computational Intelligence, 1994 IEEE International Conference on 1994: IEEE.
Hassoun MH. Fundamentals of artificial neural networks: MIT Press 1995. DOI: https://doi.org/10.1109/JPROC.1996.503146
White H. Artificial neural networks: approximation and learning theory: Blackwell Publishers, Inc. 1992.
Zhang G, Eddy Patuwo B, Y Hu M. Forecasting with artificial neural networks: The state of the art. Int J Forecasting 1998; 14(1): 35-62. http://dx.doi.org/10.1016/S0169-2070(97)00044-7 DOI: https://doi.org/10.1016/S0169-2070(97)00044-7
Serrano-Durba A, Serrano AJ, Magdalena JR, Martin JD, Soria E, Dominguez C, et al. The use of neural networks for predicting the result of endoscopic treatment for vesico-ureteric reflux. BJU Int 2004; 94(1): 120-2. http://www. ncbi.nlm.nih.gov/pubmed/15217444. http://dx.doi.org/10.1111/j.1464-410X.2004.04912.x DOI: https://doi.org/10.1111/j.1464-410X.2004.04912.x
Seckiner I, Seckiner SU, Erturhan S, Erbagci A, Solakhan M, Yagci F. The use of artificial neural networks in decision support in vesicoureteral reflux treatment. Urol Int 2008; 80(3): 283-6. http://www.ncbi.nlm.nih.gov/pubmed/18480632. http://dx.doi.org/10.1159/000127342 DOI: https://doi.org/10.1159/000127342
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2013 Zahra Aryan, Abdol-Mohammad Kajbafzadeh
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Policy for Journals/Articles with Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
Policy for Journals / Manuscript with Paid Access
Authors who publish with this journal agree to the following terms:
- Publisher retain copyright .
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .
