About this Journal Submit a Manuscript Table of Contents
ISRN Urology
Volume 2012 (2012), Article ID 643181, 6 pages
http://dx.doi.org/10.5402/2012/643181
Research Article

External Validation of an Artificial Neural Network and Two Nomograms for Prostate Cancer Detection

1Department of Urology, HELIOS Hospital, 15526 Bad Saarow, Germany
2Institute of Pathology, HELIOS Hospital, Bad Saarow, Germany
3Institute of Medical Informatics, Charité—Universitätsmedizin Berlin, 10098 Berlin, Germany
4Department of Urology, Lukas Hospital Neuss, Germany
5Department of Urology, Charité—Universitätsmedizin Berlin, 10098 Berlin, Germany

Received 9 April 2012; Accepted 13 May 2012

Academic Editors: P.-L. Chang, J. H. Ku, and T. Okamura

Copyright © 2012 Thorsten H. Ecke et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Background. Multivariate models are used to increase prostate cancer (PCa) detection rate and to reduce unnecessary biopsies. An external validation of the artificial neural network (ANN) “ProstataClass” (ANN-Charité) was performed with daily routine data. Materials and Methods. The individual ANN predictions were generated with the use of the ANN application for PSA and free PSA assays, which rely on age, tPSA, %fPSA, prostate volume, and DRE (ANN-Charité). Diagnostic validity of tPSA, %fPSA, and the ANN was evaluated by ROC curve analysis and comparisons of observed versus predicted probabilities. Results. Overall, 101 (35.8%) PCa were detected. The areas under the ROC curve (AUCs) were 0.501 for tPSA, 0.669 for %fPSA, 0.694 for ANN-Charité, 0.713 for nomogram I, and 0.742 for nomogram II, showing a significant advantage for nomogram II ( 𝑃 = 0 . 0 0 9 ) compared with %fPSA while the other model did not differ from %fPSA ( 𝑃 = 0 . 1 5 and 𝑃 = 0 . 4 1 ). All models overestimated the predicted PCa probability. Conclusions. Beside ROC analysis, calibration is an important tool to determine the true value of using a model in clinical practice. The worth of multivariate models is limited when external validations were performed without knowledge of the circumstances of the model's development.