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) Alert me when this article is cited Alert me if a correction is posted Citation Map Services Email this article to a friend Similar articles in this journal Similar articles in 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 Web of Science (47) Citing Articles via Google Scholar Google Scholar Articles by Virtanen, A. Articles by Kranse, R. Search for Related Content PubMed PubMed Citation Articles by Virtanen, A. Articles by Kranse, R. Related Collections Laboratory Management Evidence Based Laboratory Medicine and Test Utilization Proteomics and Protein Markers

Estimation of Prostate Cancer Probability by Logistic Regression: Free and Total Prostate-specific Antigen, Digital Rectal Examination, and Heredity Are Significant Variables

Arja Virtanen^1,a, Mehran Gomari², Ries Kranse³ and Ulf-Hkan Stenman⁴

¹ Central Laboratory, University Central Hospital of Turku, Medical Informatics Research Centre in Turku (MIRCIT), FIN-20521 Turku, Finland.

² Turku Centre for Computer Science (TUCS), FIN-20520 Turku, Finland.

³ Department of Urology, Dijkzigt Academic Hospital Rotterdam, NL-3015 GD Rotterdam, The Netherlands.

⁴ Department of Clinical Chemistry, University Central Hospital of Helsinki, FIN-00100 Helsinki, Finland.
^a Author for correspondence. Fax 358-2-2613920; e-mail arja.virtanen{at}utu.fi

Background: Despite low specificity, serum prostate-specific antigen (PSA) is widely used in screening for prostate cancer. Specificity can be improved by measuring free and total PSA and by combining these results with clinical findings. Methods such as neural networks and logistic regression are alternatives to multistep algorithms for clinical use of the combined findings.

Methods: We compared multilayer perceptron (MLP) and logistic regression (LR) analysis for predicting prostate cancer in a screening population of 974 men, ages 55–66 years. The study sample comprised men with PSA values >3 µg/L. Explanatory variables considered were age, free and total PSA and their ratio, digital rectal examination (DRE), transrectal ultrasonography, and a family history of prostate cancer.

Results: When at least 90% sensitivity in the training sets was required, the mean sensitivity and specificity obtained were 87% and 41% with LR and 85% and 26% with MLP, respectively. The cancer specificity of an LR model comprising the proportion of free to total PSA, DRE, and heredity as explanatory variables was significantly better than that of total PSA and the proportion of free to total PSA (P <0.01, McNemar test). The proportion of free to total PSA, DRE, and heredity were used to prepare cancer probability curves.

Conclusion: The probability calculated by logistic regression provides better diagnostic accuracy for prostate cancer than the presently used multistep algorithms for estimation of the need to perform biopsy.© 1999 American Association for Clinical Chemistry

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

				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]

				M. Martinez, F. Espana, M. Royo, J. M. Alapont, S. Navarro, A. Estelles, J. Aznar, C. D. Vera, and J. F. Jimenez-Cruz The Proportion of Prostate-specific Antigen (PSA) Complexed to {alpha}1-Antichymotrypsin Improves the Discrimination between Prostate Cancer and Benign Prostatic Hyperplasia in Men with a Total PSA of 10 to 30 {micro}g/L Clin. Chem., August 1, 2002; 48(8): 1251 - 1256. [Abstract] [Full Text] [PDF]

				C. Stephan, H. Cammann, A. Semjonow, E. P. Diamandis, L. F.A. Wymenga, M. Lein, P. Sinha, S. A. Loening, and K. Jung Multicenter Evaluation of an Artificial Neural Network to Increase the Prostate Cancer Detection Rate and Reduce Unnecessary Biopsies Clin. Chem., August 1, 2002; 48(8): 1279 - 1287. [Abstract] [Full Text] [PDF]

				T. Makinen, T. L.J. Tammela, U.-H. Stenman, L. Maattanen, S. Rannikko, J. Aro, H. Juusela, M. Hakama, and A. Auvinen Family History and Prostate Cancer Screening With Prostate-Specific Antigen J. Clin. Oncol., June 1, 2002; 20(11): 2658 - 2663. [Abstract] [Full Text] [PDF]

				A. T. Baron, J. M. Lafky, V. J. Suman, D. W. Hillman, M. C. Buenafe, C. H. Boardman, K. C. Podratz, E. A. Perez, and N. J. Maihle A Preliminary Study of Serum Concentrations of Soluble Epidermal Growth Factor Receptor (sErbB1), Gonadotropins, and Steroid Hormones in Healthy Men and Women Cancer Epidemiol. Biomarkers Prev., November 1, 2001; 10(11): 1175 - 1185. [Abstract] [Full Text] [PDF]

				L. Zhao, Y. Chen, and D. W. Schaffner Comparison of Logistic Regression and Linear Regression in Modeling Percentage Data Appl. Envir. Microbiol., May 1, 2001; 67(5): 2129 - 2135. [Abstract] [Full Text]

				U.-H. Stenman Immunoassay Standardization: Is It Possible, Who Is Responsible, Who Is Capable? Clin. Chem., May 1, 2001; 47(5): 815 - 820. [Full Text] [PDF]

				C. Stephan, K. Jung, M. Lein, P. Sinha, D. Schnorr, and S. A. Loening Molecular Forms of Prostate-specific Antigen and Human Kallikrein 2 as Promising Tools for Early Diagnosis of Prostate Cancer Cancer Epidemiol. Biomarkers Prev., November 1, 2000; 9(11): 1133 - 1147. [Abstract] [Full Text]

				K. Jung, U. Elgeti, M. Lein, B. Brux, P. Sinha, B. Rudolph, S. Hauptmann, D. Schnorr, and S. A. Loening Ratio of Free or Complexed Prostate-specific Antigen (PSA) to Total PSA: Which Ratio Improves Differentiation between Benign Prostatic Hyperplasia and Prostate Cancer? Clin. Chem., January 1, 2000; 46(1): 55 - 62. [Abstract] [Full Text] [PDF]