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

Our study was performed to evaluate the diagnostic usefulness of %fPSA alone and combined with an ANN at different PSA concentration ranges, including the low range 2–4 ng/ml, to improve the risk assessment of prostate cancer. A total of 928 men with prostate cancer and BPH without any pretreatment of the prostate in the PSA range 2–20 ng/ml were enrolled in the study between 1996 and 2001. An ANN with input data of PSA, %fPSA, patient's age, prostate volume and DRE status was developed to calculate the individual's risk before performing a prostate biopsy within the different PSA ranges 2–4, 4.1–10 and 10.1–20 ng/ml. ROC analysis and cut‐off calculations were used to estimate the diagnostic improvement of %fPSA and ANN in comparison to PSA. At the 90% sensitivity level, %fPSA and ANN performed better than PSA in all ranges, enhancing the specificity by 15–28% and 32–44%, respectively. For the low PSA range 2–4 ng/mL, we recommend a first‐time biopsy at an ANN specificity level of 90%. For PSA 4–10 ng/mL, we recommend a first‐time biopsy based on the ANN at the 90% sensitivity level. Use of an ANN enhances the %fPSA performance to further reduce the number of unnecessary biopsies within the PSA range 2–10 ng/ml. © 2002 Wiley‐Liss, Inc.

[1]  S. Loening,et al.  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? , 2001, International journal of cancer.

[2]  H. Lilja,et al.  Variation in percentage‐free prostate‐specific antigen (PSA) with prostate volume, age and total PSA level , 2001, BJU international.

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

[4]  D. Sargent,et al.  Comparison of artificial neural networks with other statistical approaches , 2001, Cancer.

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

[6]  S. Loening,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.

[7]  U Pichlmeier,et al.  A validated strategy for side specific prediction of organ confined prostate cancer: a tool to select for nerve sparing radical prostatectomy. , 2001, The Journal of urology.

[8]  A. Haese*,et al.  Ratio free/total PSA (%f-PSA) in men with total PSA 0.5–3 ng/ml: improvement for prostate cancer detection? , 2000, Prostate Cancer and Prostatic Diseases.

[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]  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.

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

[12]  J. Trachtenberg,et al.  Serum human glandular kallikrein-2 protease levels predict the presence of prostate cancer among men with elevated prostate-specific antigen. , 2000, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[13]  A. Partin,et al.  Report on Prostate Cancer Tumor Marker Workshop 1999 , 2000, Cancer.

[14]  K. Groenier,et al.  Clinical implications of free-to-total immunoreactive prostate-specific antigen ratios , 2000, Scandinavian journal of urology and nephrology.

[15]  D. Tindall,et al.  Use of human glandular kallikrein 2 for the detection of prostate cancer: preliminary analysis. , 1999, Urology.

[16]  J. Richie,et al.  Prediction of post-radical prostatectomy pathological outcome for stage T1c prostate cancer with percent free prostate specific antigen: a prospective multicenter clinical trial. , 1999, The Journal of urology.

[17]  C C Schulman,et al.  PSA, PSA density, PSA density of transition zone, free/total PSA ratio, and PSA velocity for early detection of prostate cancer in men with serum PSA 2.5 to 4.0 ng/mL. , 1999, Urology.

[18]  D. Tindall,et al.  Identification of a novel complex between human kallikrein 2 and protease inhibitor-6 in prostate cancer tissue. , 1999, Cancer research.

[19]  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.

[20]  A. A. Reilly,et al.  Effect of the ratio of free to total prostate-specific antigen on interassay variability in proficiency test samples. , 1999, Clinical chemistry.

[21]  D. Chan,et al.  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. , 1999, Urology.

[22]  U. Stenman,et al.  Estimation of prostate cancer probability by logistic regression: free and total prostate-specific antigen, digital rectal examination, and heredity are significant variables. , 1999, Clinical chemistry.

[23]  G. Bartsch,et al.  Association of free PSA percent, total PSA, age, and gland volume in the detection of prostate cancer , 1999, The Prostate.

[24]  J. Adolfsson,et al.  Diagnostic value of percent free prostate-specific antigen: retrospective analysis of a population-based screening study with emphasis on men with PSA levels less than 3.0 ng/mL. , 1999, Urology.

[25]  P. Wong,et al.  Prostate-specific antigen ratio correlates with aggressiveness of histology grades of prostate cancer. , 1999, Clinical biochemistry.

[26]  A. Partin,et al.  An algorithm combining age, total prostate-specific antigen (PSA), and percent free PSA to predict prostate cancer: results on 4298 cases. , 1998, Urology.

[27]  S. Childs,et al.  The appropriate lower limit for the percent free prostate-specific antigen reflex range. , 1998, Urology.

[28]  J. Wei,et al.  Understanding artificial neural networks and exploring their potential applications for the practicing urologist. , 1998, Urology.

[29]  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.

[30]  J. Oesterling,et al.  Serum percent-free PSA does not predict extraprostatic spread of prostate cancer. , 1998, American journal of clinical pathology.

[31]  P. Humphrey,et al.  Percentage of free serum prostate-specific antigen as a predictor of pathologic features of prostate cancer in a screening population. , 1998, Urology.

[32]  J. Pannek,et al.  The use of percent free prostate specific antigen for staging clinically localized prostate cancer. , 1998, The Journal of urology.

[33]  K. Jung,et al.  Factors influencing the ratio of free to total prostate‐specific antigen in serum , 1997, International journal of cancer.

[34]  R. Wolfert,et al.  A precursor form of PSA (pPSA) is a component of the free PSA in prostate cancer serum. , 1997, Urology.

[35]  D. Ornstein,et al.  Prostate cancer detection in men with serum PSA concentrations of 2.6 to 4.0 ng/mL and benign prostate examination. Enhancement of specificity with free PSA measurements. , 1997, JAMA.

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

[37]  B. G. Blijenberg,et al.  The free-to-total serum prostate specific antigen ratio for staging prostate carcinoma. , 1997, The Journal of urology.

[38]  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.

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

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

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

[42]  O. Nilsson,et al.  Prostate-specific antigen in serum occurs predominantly in complex with alpha 1-antichymotrypsin. , 1991, Clinical chemistry.

[43]  M. Kattan,et al.  Percentage of free PSA (%FPSA) is not an independent predictor of pathologic stage or psa recurrence in patients with localised prostate cancer treated with Radical Prostatectomy (RP) , 2002 .

[44]  S. Loening,et al.  Relation of free PSA/total PSA in serum for differentiating between patients with prostatic cancer and benign hyperplasia of the prostate: which cutoff should be used? , 1998, Cancer investigation.

[45]  S. Loening,et al.  COMMENT ON: CAN PROSTATE SPECIFIC ANTIGEN DERIVATIVES REDUCE THE FREQUENCYOF UNNECESSARY PROSTATE BIOPSIES BY PRESTIGIACOMO ET AL , 1997 .

[46]  S. Loening,et al.  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 , 1997, Cancer.

[47]  A. Semjonow,et al.  Discordance of assay methods creates pitfalls for the interpretation of prostate‐specific antigen values , 1996, The Prostate. Supplement.

[48]  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.

[49]  U. Stenman,et al.  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. , 1991, Cancer research.