An artificial neural network for prostate cancer staging when serum prostate specific antigen is 10 ng./ml. or less.

PURPOSE An artificial neural network was developed to improve the prediction of pathological stage before radical prostatectomy based on variables available at biopsy and clinical parameters. MATERIALS AND METHODS We used the prospectively accrued European prostate cancer detection data base to train an artificial neural network to predict pathological stage in 200 men with serum prostate specific antigen (PSA) 10 ng./ml. or less who underwent radical prostatectomy. Variables included in the artificial neural network were patient age, serum PSA, free-to-total PSA ratio, PSA velocity, transrectal ultrasound calculated total and transition zone volumes with their associated PSA parameters (transition zone PSA density and PSA density), digital rectal examination and Gleason score on biopsy. Two multilayer perceptron neural networks were trained on the remaining variables. Data on the 200 patients were divided randomly into a training set, a test set and a validation or prospective set. RESULTS Overall classification accuracy of the artificial neural network was 92.7% and 84.2% for organ confined and advanced prostate cancer staging, respectively. For preoperatively predicting local versus advanced stage the area under the ROC curve for the artificial neural network was significantly larger (0.91) compared with logistic regression analysis (0.83), Gleason score (0.69), PSA density (0.68), prostate transition zone volume (0.63) and serum PSA (0.62) (all p <0.01). CONCLUSIONS The artificial neural network outperformed logistic regression analysis and correctly predicted pathological stage in more than 90% of the validation patients with serum PSA 10 ng./ml. or less based on clinical, biochemical and biopsy data. In the future artificial neural networks may represent a significant step for improved staging of prostate cancer when counseling patients referred for radical prostatectomy or other curative treatments.

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

[2]  E. Crawford,et al.  Impact of different variables on the outcome of patients with clinically confined prostate carcinoma: prediction of pathologic stage and biochemical failure using an artificial neural network. , 2001, Cancer.

[3]  D. Bostwick,et al.  Prediction of extraprostatic extension of prostate cancer based on needle biopsy findings: perineural invasion lacks significance on multivariate analysis. , 1997, The American journal of surgical pathology.

[4]  A W Partin,et al.  Contemporary update of prostate cancer staging nomograms (Partin Tables) for the new millennium. , 2002, Urology.

[5]  F. Hamdy,et al.  State‐of‐the‐art staging in prostate cancer , 2001, BJU international.

[6]  A W Partin,et al.  Validation of Partin tables for predicting pathological stage of clinically localized prostate cancer. , 2000, The Journal of urology.

[7]  A. Zlotta,et al.  Prostate specific antigen density of the transition zone for predicting pathological stage of localized prostate cancer in patients with serum prostate specific antigen less than 10 ng./ml. , 1998, The Journal of urology.

[8]  J W Moul,et al.  Applications of neural networks in urologic oncology. , 1998, Seminars in urologic oncology.

[9]  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.

[10]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[11]  D. Bostwick.  Staging prostate cancer--1997: current methods and limitations. , 1997, European urology.

[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]  A. Partin,et al.  Evaluation of artificial neural networks for the prediction of pathologic stage in prostate carcinoma , 2001, Cancer.

[14]  C. Roehrborn,et al.  Gleason Scores from Prostate Biopsies Obtained with 18-Gauge Biopsy Needles Poorly Predict Gleason Scores of Radical Prostatectomy Specimens , 1998, European Urology.

[15]  A. Haese*,et al.  Human glandular kallikrein 2 levels in serum for discrimination of pathologically organ‐confined from locally‐advanced prostate cancer in total PSA‐levels below 10 ng/ml , 2001, The Prostate.

[16]  A. Partin,et al.  Long-term biochemical disease-free and cancer-specific survival following anatomic radical retropubic prostatectomy. The 15-year Johns Hopkins experience. , 2001, The Urologic clinics of North America.

[17]  A W Partin,et al.  Combination of prostate-specific antigen, clinical stage, and Gleason score to predict pathological stage of localized prostate cancer. A multi-institutional update. , 1997, JAMA.

[18]  H. Schmid,et al.  Is the percentage of cancer in biopsy cores predictive of extracapsular disease in T1‐T2 prostate carcinoma? , 1996 .

[19]  J. Moul,et al.  The role of imaging studies and molecular markers for selecting candidates for radical prostatectomy. , 2001, The Urologic clinics of North America.