Development of an artificial neural network for helping to diagnose diseases in urology

Antonio Soriano  Payá; Daniel Ruiz  Fernández; David Gil  Méndez; Carlos Alberto Montejo Hernández

1st International ICST Conference on Bio Inspired Models of Network, Information and Computing Systems

Research Article

Development of an artificial neural network for helping to diagnose diseases in urology

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1145/1315843.1315855,
    author={Antonio Soriano  Pay\^{a} and Daniel Ruiz  Fern\^{a}ndez and David Gil  M\^{e}ndez and Carlos Alberto Montejo Hern\^{a}ndez},
    title={Development of an artificial neural network for helping to diagnose diseases in urology},
    proceedings={1st International ICST Conference on Bio Inspired Models of Network, Information and Computing Systems},
    publisher={ACM},
    proceedings_a={BIONETICS},
    year={2006},
    month={12},
    keywords={Urology artificial neural network decision support systems.},
    doi={10.1145/1315843.1315855}
}

Antonio Soriano Payá
Daniel Ruiz Fernández
David Gil Méndez
Carlos Alberto Montejo Hernández
Year: 2006
Development of an artificial neural network for helping to diagnose diseases in urology
BIONETICS
ACM
DOI: 10.1145/1315843.1315855

Antonio Soriano Payá¹^,*, Daniel Ruiz Fernández¹^,*, David Gil Méndez¹^,*, Carlos Alberto Montejo Hernández¹^,*

1: Computing Technology and Data Processing, University of Alicante, Alicante, Spain

*Contact email: soriano@dtic.ua.es, druiz@dtic.ua.es, dgil@dtic.ua.es, cmontejo@dtic.ua.es

Abstract

In this article we propose the development of a tool for helping in the medical diagnosis using neural networks, in particular the multilayer perceptron. This new tool is meant to help the urologists in obtaining an automatic diagnosis for complex multi-variable systems, and to avoid painful and costly medical treatments. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The system is able to distinguish and classify dysfunctions as arreflexive, hyper-reflexive, and effort incontinence. Moreover, it is able to predict whether there is presence of dysfunction or not. The results of the experiments display a high percentage of certainty of about 85%.

Keywords: Urology artificial neural network decision support systems.

Published: 2006-12-13
Publisher: ACM

: http://dx.doi.org/10.1145/1315843.1315855