Skip to main content
SpringerLink
Log in

Assay-specific artificial neural networks for five different PSA assays and populations with PSA 2–10 ng/ml in 4,480 men

  • Original Article
  • Published:
World Journal of Urology Aims and scope Submit manuscript

Abstract

Use of percent free PSA (%fPSA) and artificial neural networks (ANNs) can eliminate unnecessary prostate biopsies. In a total of 4,480 patients from five centers with PSA concentrations in the range of 2–10 ng/ml an IMMULITE PSA-based ANN (iANN) was compared with other PSA assay-adapted ANNs (nANNs) to investigate the impact of different PSA assays. ANN data were generated with PSA, fPSA (assays from Abbott, Beckman, DPC, Roche or Wallac), age, prostate volume, and DRE status. In 15 different ROC analyses, the area under the curve (AUC) in the PSA ranges 2–4, 2–10, and 4–10 ng/ml for the nANN was always significantly larger than the AUC for %fPSA or PSA. The nANN and logistic regression models mostly also performed better than the iANN. Therefore, for each patient population, PSA assay-specific ANNs should be used to optimize the ANN outcome in order to reduce the number of unnecessary biopsies.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Polascik TJ, Oesterling JE, Partin AW (1999) Prostate specific antigen: a decade of discovery—what we have learned and where we are going. J Urol 162:293–306

    Article  PubMed  CAS  Google Scholar 

  2. Thompson IM, Pauler DK, Goodman PJ, Tangen CM, Lucia MS, Parnes HL, Minasian LM, Ford LG, Lippman SM, Crawford ED, Crowley JJ, Coltman CA Jr (2004) Prevalence of prostate cancer among men with a prostate-specific antigen level < or = 4.0 ng per milliliter. N Engl J Med 350:2239–2246

    Article  PubMed  CAS  Google Scholar 

  3. Lilja H, Christensson A, Dahlen U, Matikainen MT, Nilsson O, Pettersson K, Lövgren T (1991) Prostate-specific antigen in serum occurs predominantly in complex with alpha 1–antichymotrypsin. Clin Chem 37:1618–1625

    PubMed  CAS  Google Scholar 

  4. Stenman UH, Leinonen J, Alfthan H, Rannikko S, Tuhkanen K, Alfthan O (1991) A complex between prostate-specific antigen and alpha 1–antichymotrypsin is the major form of prostate-specific antigen in serum of patients with prostatic cancer: assay of the complex improves clinical sensitivity for cancer. Cancer Res 51:222–226

    PubMed  CAS  Google Scholar 

  5. Catalona WJ, Partin AW, Slawin KM, Brawer MK, Flanigan RC, Patel A, Richie JP, deKernion JB, Walsh PC, Scardino PT, Lange PH, Subong EN, Parson RE, Gasior GH, Loveland KG, Southwick PC (1998) Use of the percentage of free prostate-specific antigen to enhance differentiation of prostate cancer from benign prostatic disease: a prospective multicenter clinical trial. JAMA 279:1542–1547

    Article  PubMed  CAS  Google Scholar 

  6. Partin AW, Catalona WJ, Southwick PC, Subong EN, Gasior GH, Chan DW (1996) Analysis of percent free prostate-specific antigen (PSA) for prostate cancer detection: influence of total PSA, prostate volume, and age. Urology 48:55–61

    Article  PubMed  CAS  Google Scholar 

  7. Stephan C, Stroebel G, Heinau M, Lenz A, Roemer A, Lein M, Schnorr D, Loening SA, Jung K (2005) The ratio of prostate-specific antigen (PSA) to prostate volume (PSA density) as a parameter to improve the detection of prostate carcinoma in PSA values in the range of <4 ng/mL. Cancer 104:993–1003

    Article  PubMed  Google Scholar 

  8. Catalona WJ, Partin AW, Finlay JA, Chan DW, Rittenhouse HG, Wolfert RL, Woodrum DL (1999) Use of percentage of free prostate-specific antigen to identify men at high risk of prostate cancer when PSA levels are 2.51 to 4 ng/mL and digital rectal examination is not suspicious for prostate cancer: an alternative model. Urology 54:220–224

    Article  PubMed  CAS  Google Scholar 

  9. Jung K, Stephan C, Elgeti U, Lein M, Brux B, Kristiansen G, Rudolph B, Hauptmann S, Schnorr D, Loening SA (2001) Molecular forms of prostate-specific antigen in serum with concentrations of total prostate-specific antigen <4 μg/l—are they useful tools for early detection and screening of prostate cancer? Int J Cancer 93:759–765

    Article  PubMed  CAS  Google Scholar 

  10. Lee CT, Scardino PT (2001) Percent free Prostate-specific antigen for first-time prostate biopsy. Urology 57:594–598

    Article  PubMed  CAS  Google Scholar 

  11. Stephan C, Lein M, Jung K, Schnorr D, Loening SA (1997) Can prostate specific antigen derivatives reduce the frequency of unnecessary prostate biopsies? [Letter]. J Urol 157:1371

    Article  PubMed  CAS  Google Scholar 

  12. Haese A, Graefen M, Noldus J, Hammerer P, Huland E, Huland H (1997) Prostatic volume and ratio of free-to-total prostate specific antigen in patients with prostatic cancer or benign prostatic hyperplasia. J Urol 158:2188–2192

    Article  PubMed  CAS  Google Scholar 

  13. Mettlin C, Chesley AE, Murphy GP, Bartsch G, Toi A, Bahnson R, Church P (1999) Association of free PSA percent, total PSA, age, and gland volume in the detection of prostate cancer. Prostate 39:153–158

    Article  PubMed  CAS  Google Scholar 

  14. Stephan C, Lein M, Jung K, Schnorr D, Loening SA (1997) The influence of prostate volume on the ratio of free to total prostate specific antigen in serum of patients with prostate carcinoma and benign prostate hyperplasia. Cancer 79:104–109

    Article  PubMed  CAS  Google Scholar 

  15. Lein M, Koenig F, Jung K, McGovern FJ, Skates SJ, Schnorr D, Loening SA (1998) The percentage of free prostate specific antigen is an age-independent tumour marker for prostate cancer: establishment of reference ranges in a large population of healthy men. Br J Urol 82:231–236

    PubMed  CAS  Google Scholar 

  16. Carlson GD, Calvanese CB, Partin AW (1998) An algorithm combining age, total prostate-specific antigen (PSA), and percent free PSA to predict prostate cancer: results on 4298 cases. Urology 52:455–461

    Article  PubMed  CAS  Google Scholar 

  17. Virtanen A, Gomari M, Kranse R, Stenman UH (1999) Estimation of prostate cancer probability by logistic regression: free and total prostate-specific antigen, digital rectal examination, and heredity are significant variables. Clin Chem 45:987–994

    PubMed  CAS  Google Scholar 

  18. Babaian RJ, Fritsche H, Ayala A, Bhadkamkar V, Johnston DA, Naccarato W, Zhang Z (2000) Performance of a neural network in detecting prostate cancer in the prostate-specific antigen reflex range of 2.5 to 4.0 ng/ml. Urology 56:1000–1006

    Article  PubMed  CAS  Google Scholar 

  19. Djavan B, Remzi M, Zlotta A, Seitz C, Snow P, Marberger M (2002) Novel artificial neural network for early detection of prostate cancer. J Clin Oncol 20:921–929

    Article  PubMed  Google Scholar 

  20. Finne P, Finne R, Auvinen A, Juusela H, Aro J, Maattanen L, Hakama M, Rannikko S, Tammela TL, Stenman U (2000) Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network. Urology 56:418–422

    Article  PubMed  CAS  Google Scholar 

  21. Remzi M, Anagnostou T, Ravery V, Zlotta A, Stephan C, Marberger M, Djavan B (2003) An artificial neural network to predict the outcome of repeat prostate biopsies. Urology 62:456–460

    Article  PubMed  Google Scholar 

  22. Stephan C, Jung K, Cammann H, Vogel B, Brux B, Kristiansen G, Rudolph B, Hauptmann S, Lein M, Schnorr D, Sinha P, Loening SA (2002) An artificial neural network considerably improves the diagnostic power of percent free prostate-specific antigen in prostate cancer diagnosis: results of a 5-year investigation. Int J Cancer 99:466–473

    Article  PubMed  CAS  Google Scholar 

  23. Kalra P, Togami J, Bansal BSG, Partin AW, Brawer MK, Babaian RJ, Ross LS, Niederberger CS (2003) A neurocomputational model for prostate carcinoma detection. Cancer 98:1849–1854

    Article  PubMed  Google Scholar 

  24. Partin AW, Murphy GP, Brawer MK (2000) Report on prostate cancer tumor marker workshop 1999. Cancer 88:955–963

    Article  PubMed  CAS  Google Scholar 

  25. Jung K, Stephan C, Lein M, Henke W, Schnorr D, Brux B, Schürenkämper P, Loening SA (1996) Analytical performance and clinical validity of two free prostate-specific antigen assays compared. Clin Chem 42:1026–1033

    PubMed  CAS  Google Scholar 

  26. Oberpenning F, Weining C, Brandt B, De Angelis G, Heinecke A, Hamm M, Stieber P, Hertle L, Schmid HP, Semjonow A (2002) Combining free and total prostate specific antigen assays from different manufacturers: the pitfalls. Eur Urol 42:577–582

    Article  PubMed  CAS  Google Scholar 

  27. Patel D, White PA, Milford WA (2000) A comparison of six commercial assays for total and free prostate specific antigen (PSA): the predictive value of the ratio of free to total PSA. BJU Int 85:686–689

    Article  PubMed  CAS  Google Scholar 

  28. Semjonow A, Oberpenning F, Brandt B, Zechel C, Brandau W, Hertle L (1996) Impact of free prostate-specific antigen on discordant measurement results of assays for total prostate-specific antigen. Urology 48(Suppl):10–15

    Article  PubMed  CAS  Google Scholar 

  29. Yurdakul G, Bangma C, Blijenberg B, van Zelst B, Wildhagen M, van der KT, Schroder F (2002) Different PSA assays lead to detection of prostate cancers with identical histological features. Eur Urol 42:154–158

    Article  PubMed  CAS  Google Scholar 

  30. Stephan C, Cammann H, Semjonow A, Diamandis EP, Wymenga LFA, Lein M, Sinha P, Loening SA, Jung K (2002) Multicenter evaluation of an artificial neural network to increase prostate cancer detection rate and reduce unnecessary biopsies. Clin Chem 48:1279–1287

    PubMed  CAS  Google Scholar 

  31. Hodge KK, McNeal JE, Terris MK, Stamey TA (1989) Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate. J Urol 142:71–74

    PubMed  CAS  Google Scholar 

  32. Romics I (2004) The technique of ultrasound guided prostate biopsy. World J Urol 22:353–356

    Article  PubMed  Google Scholar 

  33. Woodrum D, York L (1998) Two-year stability of free and total PSA in frozen serum samples. Urology 52:247–251

    Article  PubMed  CAS  Google Scholar 

  34. Blijenberg BG, Yurdakul G, Van Zelst BD, Bangma CH, Wildhagen MF, Schroder FH (2001) Discordant performance of assays for free and total prostate-specific antigen in relation to the early detection of prostate cancer. BJU Int 88:545–550

    Article  PubMed  CAS  Google Scholar 

  35. Jung K, Stephan C, Lein M, Brux B, Sinha P, Schnorr D, Loening SA (2001) Receiver-operating characteristic as a tool for evaluating the diagnostic performance of prostate-specific antigen and its molecular forms—What has to be considered? Prostate 46:307–310

    Article  PubMed  CAS  Google Scholar 

  36. Stephan C, Jung K, Lein M, Sinha P, Schnorr D, Loening SA (2000) Molecular forms of prostate-specific antigen and human kallikrein 2 as promising tools for early diagnosis of prostate cancer. Cancer Epidemiol Biomarkers Prev 9:1133–1147

    PubMed  CAS  Google Scholar 

  37. Schroder FH, Kranse R (2003) Verification bias and the prostate-specific antigen test—is there a case for a lower threshold for biopsy? N Engl J Med 349:393–395

    Article  PubMed  Google Scholar 

  38. Roehl KA, Antenor JA, Catalona WJ (2002) Robustness of free prostate specific antigen measurements to reduce unnecessary biopsies in the 2.6 to 4.0 ng./ml. range. J Urol 168:922–925

    Article  PubMed  Google Scholar 

  39. Semjonow A, Brandt B, Oberpenning F, Roth S, Hertle L (1996) Discordance of assay methods creates pitfalls for the interpretation of prostate-specific antigen values. Prostate Suppl 7:3–16

    Article  PubMed  CAS  Google Scholar 

  40. Sargent DJ (2001) Comparison of artificial neural networks with other statistical approaches. Cancer 91:1636–1642

    Article  PubMed  CAS  Google Scholar 

Download references

Acknowledgments

We gratefully acknowledge Paul E. C. Sibley for his helpful corrections. We thank S. Kreuzer, C. Wülfing, and J. Chun for helpful database support. This work was partly supported by the Mildred-Scheel-Foundation (Grant 70-3295-ST1 to C.S., H.C., K.J.), the Berliner Sparkassenstiftung Medizin (to C.S., H.C.), and the Monika-Kutzner-Stiftung (to C.S., K.J., H.C.).

Author information

Authors and Affiliations

  1. Department of Urology, Charité—Universitätsmedizin Berlin, CCM, Charitéplatz 1, 10098, Berlin, Germany

    Carsten Stephan, Chuanliang Xu, Klaus Jung & Hellmuth-Alexander Meyer

  2. Institute of Medical Informatics, Charité—Universitätsmedizin Berlin, Berlin, Germany

    Henning Cammann

  3. Department of Urology, Changhai Hospital, Second Military Medical University, Shanghai, China

    Chuanliang Xu

  4. Department of Urology, University Hospital Hamburg-Eppendorf, University Hamburg, Hamburg, Germany

    Markus Graefen, Alexander Haese & Hartwig Huland

  5. Prostate Center, University Hospital, University Münster, Münster, Germany

    Axel Semjonow

  6. Department of Pathology and Laboratory Medicine, Mount Sinai Hospital, Toronto, Canada

    Eleftherios P. Diamandis

  7. Department of Urology, University Hospital of Vienna, Vienna, Austria

    Mesut Remzi & Bob Djavan

  8. Department of Urology, University Hospital Rotterdam, Rotterdam, The Netherlands

    Mark F. Wildhagen

  9. Department of Clinical Chemistry, University Hospital Rotterdam, Rotterdam, The Netherlands

    Bert G. Blijenberg

  10. Department of Clinical Chemistry, Helsinki University Central Hospital, Helsinki, Finland

    Patrik Finne & Ulf-Hakan Stenman

Authors
  1. Carsten Stephan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chuanliang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Henning Cammann
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Markus Graefen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Alexander Haese
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hartwig Huland
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Axel Semjonow
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Eleftherios P. Diamandis
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Mesut Remzi
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Bob Djavan
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Mark F. Wildhagen
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Bert G. Blijenberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Patrik Finne
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Ulf-Hakan Stenman
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Klaus Jung
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Hellmuth-Alexander Meyer
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Carsten Stephan.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Stephan, C., Xu, C., Cammann, H. et al. Assay-specific artificial neural networks for five different PSA assays and populations with PSA 2–10 ng/ml in 4,480 men. World J Urol 25, 95–103 (2007). https://doi.org/10.1007/s00345-006-0132-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00345-006-0132-9

Keywords

Search

Navigation