Outcome prediction for prostate cancer detection rate with artificial neural network (ANN) in daily routine.

BACKGROUND We evaluated the use of the artificial neural network (ANN) program "ProstataClass" of the Department of Urology and the Institute of Medical Informatics at the Charité-Universitätsmedizin Berlin in daily routine to increase prostate cancer (CaP) detection rate and to reduce unnecessary biopsies. MATERIALS AND METHODS From May 2005 to April 2007, a total of 204 patients were included in the study. The Beckman Access PSA assay was used, and pretreatment prostate specific antigen (PSA) was measured prior to digital rectal examination (DRE) and 12 core systematic transrectal ultrasound (TRUS) guided biopsies. The individual ANN predictions were generated with the use of the ANN application for the Beckman Access PSA and free PSA assays, which relies on age, PSA, percent free prostate specific antigen (%fPSA), prostate volume, and DRE. Diagnostic validity of total prostate specific antigen (tPSA), %fPSA, and the ANN was evaluated by ROC curve analysis. RESULTS PSA and %fPSA ranged from 4.01 to 9.91 ng/ml (median: 6.65) and 5% to 48% (median: 15%), respectively. Of all men, 46 (22.5%) demonstrated suspicious DRE findings. Total prostate volume ranged from 7.1 to 119.2 cc (median: 35). Overall, 71 (34.8%) CaP were detected. Of men with suspicious DRE, 28 (60.9%) had CaP on initial biopsy. The ANN was 78% accurate in the original report. The AUC of ROC curve analysis was 0.51 for PSA, 0.66 for %PSA, and 0.72 for the ANN-Output, respectively. CONCLUSIONS Our results in this independent cohort show that ANN is a very helpful parameter in daily routine to increase the CaP detection rate and reduce unnecessary biopsies.

[1]  C. Stephan,et al.  Receiver‐operating characteristic as a tool for evaluating the diagnostic performance of prostate‐specific antigen and its molecular forms—What has to be considered? , 2001, The Prostate.

[2]  J. Oesterling,et al.  The clinical usefulness of prostate specific antigen: update 1994. , 1994, The Journal of urology.

[3]  M. Terris,et al.  Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate. , 1989, The Journal of urology.

[4]  A W Partin,et al.  Use of the percentage of free prostate-specific antigen to enhance differentiation of prostate cancer from benign prostatic disease: a prospective multicenter clinical trial. , 1998, JAMA.

[5]  Dietmar Schnorr,et al.  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 , 2002, International journal of cancer.

[6]  H. Stricker,et al.  Detection of non-palpable prostate cancer. A mathematical and laboratory model. , 1993, British journal of urology.

[7]  M Bolla,et al.  EAU guidelines on prostate cancer. , 2001, European urology.

[8]  V Kairisto,et al.  Software for illustrative presentation of basic clinical characteristics of laboratory tests--GraphROC for Windows. , 1995, Scandinavian journal of clinical and laboratory investigation. Supplementum.

[9]  Z. Zhang,et al.  Performance of a neural network in detecting prostate cancer in the prostate-specific antigen reflex range of 2.5 to 4.0 ng/mL. , 2000, Urology.

[10]  H. Cammann,et al.  An artificial neural network for five different assay systems of prostate‐specific antigen in prostate cancer diagnostics , 2008, BJU international.

[11]  Dietmar Schnorr,et al.  Interchangeability of measurements of total and free prostate-specific antigen in serum with 5 frequently used assay combinations: an update. , 2006, Clinical chemistry.

[12]  W. Catalona,et al.  Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study. , 1994, The Journal of urology.

[13]  Pierre I Karakiewicz,et al.  Initial biopsy outcome prediction--head-to-head comparison of a logistic regression-based nomogram versus artificial neural network. , 2007, European urology.

[14]  P. Humphrey,et al.  Clinical and pathologic tumor characteristics of prostate cancer as a function of the number of biopsy cores: a retrospective study. , 1998, Urology.

[15]  C. Abbou,et al.  EAU guidelines on prostate cancer. , 2009, European urology.

[16]  G Bartsch,et al.  The problem of cutoff levels in a screened population , 2001, Cancer.

[17]  M. Kattan,et al.  Development and validation of a nomogram predicting the outcome of prostate biopsy based on patient age, digital rectal examination and serum prostate specific antigen. , 2005, The Journal of urology.

[18]  S. Loening,et al.  Molecular forms of prostate-specific antigen and human kallikrein 2 as promising tools for early diagnosis of prostate cancer. , 2000, Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.

[19]  D. Gleason,et al.  Histologic grading of prostate cancer: a perspective. , 1992, Human pathology.

[20]  T. Ecke,et al.  Complications and risk factors of transrectal ultrasound guided needle biopsies of the prostate evaluated by questionnaire. , 2008, Urologic oncology.

[21]  Jerome P. Richie,et al.  Use of the percentage of free prostate-specific antigen to enhance differentiation of prostate cancer from benign prostatic disease: a prospective multicenter clinical trial. , 1998, JAMA.

[22]  Mesut Remzi,et al.  Novel artificial neural network for early detection of prostate cancer. , 2002, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[23]  J. Oesterling,et al.  Prostate specific antigen: a decade of discovery--what we have learned and where we are going. , 1999, The Journal of urology.

[24]  E. Klein.  Can prostate specific antigen derivatives reduce the frequency of unnecessary prostate biopsies? , 1996, The Journal of urology.

[25]  P. Scardino,et al.  Percent free prostate-specific antigen for first-time prostate biopsy. , 2001, Urology.

[26]  Isabelle Meiers,et al.  Prostate biopsy and optimization of cancer yield. , 2006, European urology.

[27]  W. Catalona,et al.  Clinical use of prostate specific antigen in patients with prostate cancer. , 1989, The Journal of urology.

[28]  H. Cammann,et al.  PSA and new biomarkers within multivariate models to improve early detection of prostate cancer. , 2007, Cancer letters.

[29]  T. Stamey,et al.  Prostate-Specific Antigen as a Serum Marker for Adenocarcinoma of the Prostate , 1987 .

[30]  Yi-Ching Hsieh,et al.  Predictive modeling for the presence of prostate carcinoma using clinical, laboratory, and ultrasound parameters in patients with prostate specific antigen levels ≤ 10 ng/mL , 2003, Cancer.

[31]  P Finne,et al.  Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network. , 2000, Urology.

[32]  Klaus Jung,et al.  Multicenter evaluation of an artificial neural network to increase the prostate cancer detection rate and reduce unnecessary biopsies. , 2002, Clinical chemistry.

[33]  M M Elhilali,et al.  Outcome of sextant biopsy according to gland volume. , 1997, Urology.

[34]  M. Kattan,et al.  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. , 1999, Urology.

[35]  John T. Wei,et al.  Artificial neural networks for prostate carcinoma risk assessment , 2001 .

[36]  A W Partin,et al.  Analysis of percent free prostate-specific antigen (PSA) for prostate cancer detection: influence of total PSA, prostate volume, and age. , 1996, Urology.

[37]  J. Melamed,et al.  Two consecutive sets of transrectal ultrasound guided sextant biopsies of the prostate for the detection of prostate cancer. , 1998, The Journal of urology.

[38]  C. Tempany,et al.  Re: Endo-rectal coil magnetic resonance imaging in clinically localized prostate cancer: is it accurate? , 1997, The Journal of urology.

[39]  W. Catalona,et al.  Evaluation of percentage of free serum prostate-specific antigen to improve specificity of prostate cancer screening. , 1995, JAMA.