External Validation of an Artificial Neural Network and Two Nomograms for Prostate Cancer Detection. (5th July 2012)

• Record Type: Journal Article
• Authors: Ecke, Thorsten H.; Hallmann, Steffen; Koch, Stefan; Ruttloff, Jürgen; Cammann, Henning; Gerullis, Holger; Miller, Kurt; Stephan, Carsten
• Other Names: Chang P.-L. Academic Editor.; Ku J. H. Academic Editor.; Okamura T. Academic Editor.
• Is Part Of: ISRN urology. Volume 2012(2012)
• Publication Date: 2012-07-05
• Subjects: Urology -- Periodicals; Urologic Diseases; Urology; Periodical; Periodicals; Fulltext; Internet Resources; Periodicals; Electronic journals; 616.6
• DOI: 10.5402/2012/643181
• Languages: English
• ISSNs: 2090-5807

Abstract

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 = 0.009 ) compared with %fPSA while the other model did not differ from %fPSA (P = 0.15 and P = 0.41 ). 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.