Skip to main content

Advertisement

SpringerLink
Log in

Predicting prostate biopsy outcome: artificial neural networks and polychotomous regression are equivalent models

  • Urology – Original Paper
  • Published:
International Urology and Nephrology Aims and scope Submit manuscript

Abstract

Introduction

Complex statistical models utilizing multiple inputs to derive a risk assessment may benefit prostate cancer (PC) detection where focus has been on prostate-specific antigen (PSA). This study develops a polychotomous logistic regression (PR) model and an artificial neural network (ANN) for predicting biopsy results, particularly for clinically significant PC.

Methods

There were 3,025 men undergoing TRUS-guided biopsy (BX) with PSA <10 ng/ml selected. BX outcome classified as benign, atypical small acinar proliferation or high-grade prostatic intraepithelial neoplasia (ASAP/PIN), non-significant (NSPC) or clinically significant PC (CSPC). PR and ANN models were developed to distinguish between BX categories. Predictors were age, PSA, abnormal digital rectal examination (DRE), positive transrectal ultrasound (TRUS) and prostate volume.

Results

Among the BXs, 44% were benign, 14% ASAP/PIN, 16% NSPC and 25% CSPC. Median age, PSA and volume were 64 years, 5.7 ng/ml and 50 cc. TRUS lesion was present in 47%, and DRE was abnormal in 39%. PR and ANN models did not differ on percentage BX outcomes correctly predicted (55, 57%, respectively) and were equally poor for both ASAP/PIN (0%) and NSPC (2%). For PR and ANN, 74–78% ASAP/PIN predicted benign, 2% NSPC and 20–24% CSPC. For NSPC, 69–71% predicted benign, 27–29% CSPC. Benign outcomes were well identified (86–88%), although 12–13% classified CSPC. CSPC was correctly identified in 65–66% with misclassifications largely benign (33% for PR and ANN).

Conclusions

Neither PR nor ANN was able to distinguish between the four biopsy outcomes: ASAP/PIN and NSPC were not distinguished from benign or CSPC. ANN did not perform better than PR. Inclusion of additional predictors may increase the performance of statistical models in predicting BX outcome.

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

Fig. 1
Fig. 2

Similar content being viewed by others

Abbreviations

ANN:

Artificial neural network

ASAP:

Atypical small acinar proliferation

BX:

TRUS guided prostate biopsy

CI:

Confidence intervals

DRE:

Digital rectal examination

OR:

Odds ratios

PC:

Prostate cancer

CSPC:

Clinically significant PC

NSPC:

Non-significant PC

PIN:

High-grade prostatic intraepithelial neoplasia

PR:

Polychotomous logistic regression

PSA:

Prostate-specific

TRUS:

Transrectal ultrasound

References

  1. Porcaro AB, Migliorini F, Romano M et al (2010) Investigative clinical study on prostate cancer: on the role of the pretreatment total PSA to free testosterone ratio in selecting different biology groups of prostate cancer patients. Int Urol Nephrol. doi:10.1007/s11255-009-9669-z

  2. Suardi N, Capitanio U, Chun FK et al (2008) Currently used criteria for active surveillance in men with low-risk prostate cancer: an analysis of pathologic features. Cancer 113:2068–2072

    Article  PubMed  Google Scholar 

  3. Schroder FH (2008) Screening for prostate cancer (PC)—an update on recent findings of the European Randomized Study of Screening for Prostate Cancer (ERSPC). Urol Oncol 26:533–541

    PubMed  Google Scholar 

  4. van Renterghem K, Van Koeveringe G, Achten R et al (2010) A new algorithm in patients with elevated and/or rising prostate-specific antigen level, minor lower urinary tract symptoms, and negative multisite prostate biopsies. Int Urol Nephrol 42(1):29–38

    Article  PubMed  Google Scholar 

  5. Partin AW, Kattan MW, Subong EN et al (1997) Combination of prostate-specific antigen, clinical stage, and Gleason score to predict pathological stage of localized prostate cancer. A multi-institutional update. JAMA 277:1445–1451

    Article  PubMed  CAS  Google Scholar 

  6. Kattan MW, Eastham JA, Stapleton AM et al (1998) A preoperative nomogram for disease recurrence following radical prostatectomy for prostate cancer. J Natl Cancer Inst 90:766–771

    Article  PubMed  CAS  Google Scholar 

  7. Karakiewicz PI, Benayoun S, Kattan MW et al (2005) Development and validation of a nomogram predicting the outcome of prostate biopsy based on patient age, digital rectal examination and serum prostate specific antigen. J Urol 173:1930–1934

    Article  PubMed  Google Scholar 

  8. Djavan B, Remzi M, Zlotta A et al (2002) Novel artificial neural network for early detection of prostate cancer. J Clin Oncol 20:921–929

    Article  PubMed  Google Scholar 

  9. Rodvold DM, McLeod DG, Brandt JM et al (2001) Introduction to artificial neural networks for physicians: taking the lid off the black box. Prostate 46:39–44

    Article  PubMed  CAS  Google Scholar 

  10. Stephan C, Cammann H, Jung K (2005) Artificial neural networks: has the time come for their use in prostate cancer patients? Nat Clin Pract Urol 2:262–263

    Article  PubMed  Google Scholar 

  11. Shariat SF, Karakiewicz PI, Suardi N et al (2008) Comparison of nomograms with other methods for predicting outcomes in prostate cancer: a critical analysis of the literature. Clin Cancer Res 14:4400–4407

    Article  PubMed  CAS  Google Scholar 

  12. Kranse R, Beemsterboer P, Rietbergen J et al (1999) Predictors for biopsy outcome in the European Randomized Study of Screening for Prostate Cancer (Rotterdam region). Prostate 39:316–322

    Article  PubMed  CAS  Google Scholar 

  13. Garzotto M, Beer TM, Hudson RG et al (2005) Improved detection of prostate cancer using classification and regression tree analysis. J Clin Oncol 23:4322–4329

    Article  PubMed  Google Scholar 

  14. Thompson IM, Pauler Ankerst D, Chi C et al (2007) Prediction of prostate cancer for patients receiving finasteride: results from the Prostate Cancer Prevention Trial. J Clin Oncol 25:3076–3081

    Article  PubMed  CAS  Google Scholar 

  15. Hekal IA, El-Tabey NA, Nabeeh MA et al (2010) Validation of Epstein criteria of insignificant prostate cancer in Middle East patients. Int Urol Nephrol. doi:10.1007/s11255-009-9670-6

  16. Al-Ghamdi AM, Lockwood G, Toi A et al (2008) Extended pattern prostate biopsy does not minimize the volume-grade bias in prostate cancer detection. J Urol 179:1332–1334

    Article  PubMed  Google Scholar 

  17. Neill MG, Toi A, Lockwood GA et al (2008) Systematic lateral prostate biopsy—are the benefits worth the costs? J Urol 179:1321–1326

    Article  PubMed  Google Scholar 

  18. Toi A, Neill MG, Lockwood GA et al (2007) The continuing importance of transrectal ultrasound identification of prostatic lesions. J Urol 177:516–520

    Article  PubMed  Google Scholar 

  19. Greene F, Page D, Fleming I (eds) (2002) American Joint Committee on Cancer staging manual, 6th edn. Springer, New York

    Google Scholar 

  20. Fleshner N, Gomella LG, Cookson MS et al (2007) Delay in the progression of low-risk prostate cancer: rationale and design of the Reduction by Dutasteride of Clinical Progression Events in Expectant Management (REDEEM) trial. Contemp Clin Trials 28:763–769

    Article  PubMed  CAS  Google Scholar 

  21. Schroder FH, Hugosson J, Roobol MJ et al (2009) Screening and prostate-cancer mortality in a randomized European study. N Engl J Med 360:1320–1328

    Article  PubMed  Google Scholar 

  22. Andriole GL, Grubb RL III, Buys SS et al (2009) Mortality results from a randomized prostate-cancer screening trial. N Engl J Med 360:1310–1319

    Article  PubMed  CAS  Google Scholar 

  23. Conti SL, Dall’era M, Fradet V et al (2009) Pathological outcomes of candidates for active surveillance of prostate cancer. J Urol 181:1628–1633 discussion 1633-1624

    Article  PubMed  Google Scholar 

  24. Snow PB, Smith DS, Catalona WJ (1994) Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study. J Urol 152:1923–1926

    PubMed  CAS  Google Scholar 

  25. Eastham JA, May R, Robertson JL et al (1999) Development of a nomogram that predicts the probability of a positive prostate biopsy in men with an abnormal digital rectal examination and a prostate-specific antigen between 0 and 4 ng/mL. Urology 54:709–713

    Article  PubMed  CAS  Google Scholar 

  26. Stephan C, Cammann H, Semjonow A et al (2002) Multicenter evaluation of an artificial neural network to increase the prostate cancer detection rate and reduce unnecessary biopsies. Clin Chem 48:1279–1287

    PubMed  CAS  Google Scholar 

  27. Naito S, Kuroiwa K, Kinukawa N et al (2008) Validation of Partin tables and development of a preoperative nomogram for Japanese patients with clinically localized prostate cancer using 2005 International Society of Urological Pathology consensus on Gleason grading: data from the Clinicopathological Research Group for Localized Prostate Cancer. J Urol 180:904–909 discussion 909-910

    Article  PubMed  CAS  Google Scholar 

  28. Chun FK, Haese A, Ahyai SA et al (2008) Critical assessment of tools to predict clinically insignificant prostate cancer at radical prostatectomy in contemporary men. Cancer 113:701–709

    Article  PubMed  Google Scholar 

  29. Dubin N, Pasternack BS (1986) Risk assessment for case-control subgroups by polychotomous logistic regression. Am J Epidemiol 123:1101–1117

    PubMed  CAS  Google Scholar 

  30. Pinthus JH, Witkos M, Fleshner NE et al (2006) Prostate cancers scored as Gleason 6 on prostate biopsy are frequently Gleason 7 tumors at radical prostatectomy: implication on outcome. J Urol 176:979–984 discussion 984

    Article  PubMed  Google Scholar 

  31. Egevad L, Allsbrook WC, Epstein JI (2006) Current practice of diagnosis and reporting of prostatic intraepithelial neoplasia and glandular atypia among genitourinary pathologists. Mod Pathol 19:180–185

    Article  PubMed  Google Scholar 

  32. Moore CK, Karikehalli S, Nazeer T et al (2005) Prognostic significance of high grade prostatic intraepithelial neoplasia and atypical small acinar proliferation in the contemporary era. J Urol 173:70–72

    Article  PubMed  Google Scholar 

  33. Netto GJ, Epstein JI (2006) Widespread high-grade prostatic intraepithelial neoplasia on prostatic needle biopsy: a significant likelihood of subsequently diagnosed adenocarcinoma. Am J Surg Pathol 30:1184–1188

    PubMed  Google Scholar 

  34. Kattan M (2002) Statistical prediction models, artificial neural networks, and the sophism “I am a patient, not a statistic”. J Clin Oncol 20:885–887

    Article  PubMed  Google Scholar 

  35. Kulkarni GS, Al-Azab R, Lockwood G et al (2006) Evidence for a biopsy derived grade artifact among larger prostate glands. J Urol 175:505–509

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

We would like to acknowledge the generous support of the Prostate Cancer Research Foundation of Canada in conducting this study.

Author information

Authors and Affiliations

  1. Department of Urology, University of Toronto, University Health Network, Toronto, ON, Canada

    Nathan Lawrentschuk & Neil E. Fleshner

  2. Canadian Partnership Against Cancer, Toronto, ON, Canada

    Gina Lockwood

  3. Department of Biostatistics, University of Toronto, University Health Network, Toronto, ON, Canada

    Peter Davies

  4. Department of Pathology, University of Toronto, University Health Network, Toronto, ON, Canada

    Andy Evans & Joan Sweet

  5. Department of Radiology, University of Toronto, University Health Network, Toronto, ON, Canada

    Ants Toi

  6. Division of Urology, Department of Surgical Oncology, Princess Margaret Hospital, 610 University Ave 3-130, Toronto, ON, M5G 2M9, Canada

    Nathan Lawrentschuk

Authors
  1. Nathan Lawrentschuk
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gina Lockwood
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peter Davies
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andy Evans
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Joan Sweet
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ants Toi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Neil E. Fleshner
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nathan Lawrentschuk.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lawrentschuk, N., Lockwood, G., Davies, P. et al. Predicting prostate biopsy outcome: artificial neural networks and polychotomous regression are equivalent models. Int Urol Nephrol 43, 23–30 (2011). https://doi.org/10.1007/s11255-010-9750-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11255-010-9750-7

Keywords

Search

Navigation