Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux

Matthew J. Knudson, James (Christopher) Austin, Moshe Wald, Antoine A. Makhlouf, Craig S. Niederberger, Christopher S. Cooper

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Purpose: Minimally invasive treatment options and concern regarding long-term antibiotics have increased emphasis on predicting the chance of early vesicoureteral reflux resolution. Computational models, such as artificial neural networks, have been used to assist decision making in the clinical setting using complex numeric constructs to solve multivariable problems. We investigated various computational models to enhance the prediction of vesicoureteral reflux resolution. Materials and Methods: We reviewed the records of 205 children with vesicoureteral reflux, including 163 females and 42 males. In addition to reflux grade, several clinical variables were recorded from the diagnostic visit. Outcome was noted as resolved or unresolved at 1 and 2 years after diagnosis. Two separate data sets were prepared for the 1 and 2-year outcomes, sharing the same input features. The data sets were randomized into a modeling set of 155 and a cross-validation set of 50. The model was constructed with several constructs using neUROn++, a set of C++ programs that we developed, to best fit the data. Results: A linear support vector machine was found to have the highest accuracy with a test set ROC curve area of 0.819 and 0.86 for the 1 and 2-year models, respectively. The model was deployed in JavaScript® for ready availability on the Internet, allowing all input variables to be entered and calculating the odds of 1 and 2-year resolution. Conclusions: This computational model allowed the use of multiple variables to improve the individualized prediction of early reflux resolution. This is a potentially useful clinical tool regarding treatment decisions for vesicoureteral reflux.

Original languageEnglish (US)
Pages (from-to)1824-1827
Number of pages4
JournalJournal of Urology
Volume178
Issue number4 SUPPLEMENT
DOIs
StatePublished - Oct 2007
Externally publishedYes

Fingerprint

Vesico-Ureteral Reflux
ROC Curve
Internet
Anti-Bacterial Agents
Neurons
Therapeutics
Datasets

Keywords

  • bladder
  • computational biology
  • computer simulation
  • ureter
  • vesico-ureteral reflux

ASJC Scopus subject areas

  • Urology

Cite this

Knudson, M. J., Austin, J. C., Wald, M., Makhlouf, A. A., Niederberger, C. S., & Cooper, C. S. (2007). Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux. Journal of Urology, 178(4 SUPPLEMENT), 1824-1827. https://doi.org/10.1016/j.juro.2007.05.093

Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux. / Knudson, Matthew J.; Austin, James (Christopher); Wald, Moshe; Makhlouf, Antoine A.; Niederberger, Craig S.; Cooper, Christopher S.

In: Journal of Urology, Vol. 178, No. 4 SUPPLEMENT, 10.2007, p. 1824-1827.

Research output: Contribution to journalArticle

Knudson, MJ, Austin, JC, Wald, M, Makhlouf, AA, Niederberger, CS & Cooper, CS 2007, 'Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux', Journal of Urology, vol. 178, no. 4 SUPPLEMENT, pp. 1824-1827. https://doi.org/10.1016/j.juro.2007.05.093
Knudson, Matthew J. ; Austin, James (Christopher) ; Wald, Moshe ; Makhlouf, Antoine A. ; Niederberger, Craig S. ; Cooper, Christopher S. / Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux. In: Journal of Urology. 2007 ; Vol. 178, No. 4 SUPPLEMENT. pp. 1824-1827.
@article{7089ccd2a37244fbae784244b301c30d,
title = "Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux",
abstract = "Purpose: Minimally invasive treatment options and concern regarding long-term antibiotics have increased emphasis on predicting the chance of early vesicoureteral reflux resolution. Computational models, such as artificial neural networks, have been used to assist decision making in the clinical setting using complex numeric constructs to solve multivariable problems. We investigated various computational models to enhance the prediction of vesicoureteral reflux resolution. Materials and Methods: We reviewed the records of 205 children with vesicoureteral reflux, including 163 females and 42 males. In addition to reflux grade, several clinical variables were recorded from the diagnostic visit. Outcome was noted as resolved or unresolved at 1 and 2 years after diagnosis. Two separate data sets were prepared for the 1 and 2-year outcomes, sharing the same input features. The data sets were randomized into a modeling set of 155 and a cross-validation set of 50. The model was constructed with several constructs using neUROn++, a set of C++ programs that we developed, to best fit the data. Results: A linear support vector machine was found to have the highest accuracy with a test set ROC curve area of 0.819 and 0.86 for the 1 and 2-year models, respectively. The model was deployed in JavaScript{\circledR} for ready availability on the Internet, allowing all input variables to be entered and calculating the odds of 1 and 2-year resolution. Conclusions: This computational model allowed the use of multiple variables to improve the individualized prediction of early reflux resolution. This is a potentially useful clinical tool regarding treatment decisions for vesicoureteral reflux.",
keywords = "bladder, computational biology, computer simulation, ureter, vesico-ureteral reflux",
author = "Knudson, {Matthew J.} and Austin, {James (Christopher)} and Moshe Wald and Makhlouf, {Antoine A.} and Niederberger, {Craig S.} and Cooper, {Christopher S.}",
year = "2007",
month = "10",
doi = "10.1016/j.juro.2007.05.093",
language = "English (US)",
volume = "178",
pages = "1824--1827",
journal = "Journal of Urology",
issn = "0022-5347",
publisher = "Elsevier Inc.",
number = "4 SUPPLEMENT",

}

TY - JOUR

T1 - Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux

AU - Knudson, Matthew J.

AU - Austin, James (Christopher)

AU - Wald, Moshe

AU - Makhlouf, Antoine A.

AU - Niederberger, Craig S.

AU - Cooper, Christopher S.

PY - 2007/10

Y1 - 2007/10

N2 - Purpose: Minimally invasive treatment options and concern regarding long-term antibiotics have increased emphasis on predicting the chance of early vesicoureteral reflux resolution. Computational models, such as artificial neural networks, have been used to assist decision making in the clinical setting using complex numeric constructs to solve multivariable problems. We investigated various computational models to enhance the prediction of vesicoureteral reflux resolution. Materials and Methods: We reviewed the records of 205 children with vesicoureteral reflux, including 163 females and 42 males. In addition to reflux grade, several clinical variables were recorded from the diagnostic visit. Outcome was noted as resolved or unresolved at 1 and 2 years after diagnosis. Two separate data sets were prepared for the 1 and 2-year outcomes, sharing the same input features. The data sets were randomized into a modeling set of 155 and a cross-validation set of 50. The model was constructed with several constructs using neUROn++, a set of C++ programs that we developed, to best fit the data. Results: A linear support vector machine was found to have the highest accuracy with a test set ROC curve area of 0.819 and 0.86 for the 1 and 2-year models, respectively. The model was deployed in JavaScript® for ready availability on the Internet, allowing all input variables to be entered and calculating the odds of 1 and 2-year resolution. Conclusions: This computational model allowed the use of multiple variables to improve the individualized prediction of early reflux resolution. This is a potentially useful clinical tool regarding treatment decisions for vesicoureteral reflux.

AB - Purpose: Minimally invasive treatment options and concern regarding long-term antibiotics have increased emphasis on predicting the chance of early vesicoureteral reflux resolution. Computational models, such as artificial neural networks, have been used to assist decision making in the clinical setting using complex numeric constructs to solve multivariable problems. We investigated various computational models to enhance the prediction of vesicoureteral reflux resolution. Materials and Methods: We reviewed the records of 205 children with vesicoureteral reflux, including 163 females and 42 males. In addition to reflux grade, several clinical variables were recorded from the diagnostic visit. Outcome was noted as resolved or unresolved at 1 and 2 years after diagnosis. Two separate data sets were prepared for the 1 and 2-year outcomes, sharing the same input features. The data sets were randomized into a modeling set of 155 and a cross-validation set of 50. The model was constructed with several constructs using neUROn++, a set of C++ programs that we developed, to best fit the data. Results: A linear support vector machine was found to have the highest accuracy with a test set ROC curve area of 0.819 and 0.86 for the 1 and 2-year models, respectively. The model was deployed in JavaScript® for ready availability on the Internet, allowing all input variables to be entered and calculating the odds of 1 and 2-year resolution. Conclusions: This computational model allowed the use of multiple variables to improve the individualized prediction of early reflux resolution. This is a potentially useful clinical tool regarding treatment decisions for vesicoureteral reflux.

KW - bladder

KW - computational biology

KW - computer simulation

KW - ureter

KW - vesico-ureteral reflux

UR - http://www.scopus.com/inward/record.url?scp=34548392261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548392261&partnerID=8YFLogxK

U2 - 10.1016/j.juro.2007.05.093

DO - 10.1016/j.juro.2007.05.093

M3 - Article

C2 - 17707424

AN - SCOPUS:34548392261

VL - 178

SP - 1824

EP - 1827

JO - Journal of Urology

JF - Journal of Urology

SN - 0022-5347

IS - 4 SUPPLEMENT

ER -