HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Submit an electronic Letter to the Editor about this paper Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Citation Map Services Email this article to a friend Similar articles in this journal Similar articles in ISI Web of Science Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via ISI Web of Science (10) Citing Articles via Google Scholar Google Scholar Articles by Veltri, R. W. Articles by Partin, A. W. Search for Related Content PubMed PubMed Citation Articles by Veltri, R. W. Articles by Partin, A. W. Related Collections General Clinical Chemistry Oak Ridge Conference Proteomics and Protein Markers

Comparison of Logistic Regression and Neural Net Modeling for Prediction of Prostate Cancer Pathologic Stage

¹ Johns Hopkins Hospital, Department of Urology, 600 North Wolfe St., Baltimore, MD 21287.

² 8032 Covered Bridge Drive, Quakertown, PA 18951.

³ UroCor, Inc., Division of Dianon Systems, Oklahoma City, OK 73104.

^aAuthor for correspondence. Fax 410-614-3695; e-mail rveltri1{at}jhmi.edu.

Abstract

Background: Prostate cancer (PCa) pathologic staging remains a challenge for the physician using individual pretreatment variables. We have previously reported that UroScore^TM, a logistic regression (LR)-derived algorithm, can correctly predict organ-confined (OC) disease state with >90% accuracy. This study compares statistical and neural network (NN) approaches to predict PCa stage.

Methods: A subset (756 of 817) of radical prostatectomy patients was assessed: 434 with OC disease, 173 with capsular penetration (NOC-CP), and 149 with metastases (NOC-AD) in the training sample. Additionally, an OC + NOC-CP (n = 607) vs NOC-AD (n = 149) two-outcome model was prepared. Validation sets included 120 or 397 cases not used for modeling. Input variables included clinical and several quantitative biopsy pathology variables. The classification accuracies achieved with a NN with an error back-propagation architecture were compared with those of LR statistical modeling.

Results: We demonstrated >95% detection of OC PCa in three-outcome models, using both computational approaches. For training patient samples that were equally distributed for the three-outcome models, NNs gave a significantly higher overall classification accuracy than the LR approach (40% vs 96%, respectively). In the two-outcome models using either unequal or equal case distribution, the NNs had only a marginal advantage in classification accuracy over LR.

Conclusions: The strength of a mathematics-based disease-outcome model depends on the quality of the input variables, quantity of cases, case sample input distribution, and computational methods of data processing of inputs and outputs. We identified specific advantages for NNs, especially in the prediction of multiple-outcome models, related to the ability to pre- and postprocess inputs and outputs.

The following articles in journals at HighWire Press have cited this article:

				D. Saxena, P. W. Caufield, Y. Li, S. Brown, J. Song, and R. Norman Genetic Classification of Severe Early Childhood Caries by Use of Subtracted DNA Fragments from Streptococcus mutans J. Clin. Microbiol., September 1, 2008; 46(9): 2868 - 2873. [Abstract] [Full Text] [PDF]

				H. J. Lee, K. G. Kim, S. E. Lee, S.-S. Byun, S. I. Hwang, S. I. Jung, S. K. Hong, and S. H. Kim Role of transrectal ultrasonography in the prediction of prostate cancer: artificial neural network analysis. J. Ultrasound Med., July 1, 2006; 25(7): 815 - 821. [Abstract] [Full Text] [PDF]