Abstract
Purpose
We developed a multiple logistic regression model, an artificial neural network (ANN), and a support vector machine (SVM) model to predict the outcome of a prostate biopsy, and compared the accuracies of each model.
Method
One thousand and seventy-seven consecutive patients who had undergone transrectal ultrasound (TRUS)-guided prostate biopsy were enrolled in the study. Clinical decision models were constructed from the input data of age, digital rectal examination findings, prostate-specific antigen (PSA), PSA density (PSAD), PSAD in transitional zone, and TRUS findings. The patients were divided into the training and test groups in a randomized fashion. Areas under the receiver operating characteristic (ROC) curve (AUC, Az) were calculated to summarize the overall performance of each decision model for the task of prostate cancer prediction.
Results
The Az values of the ROC curves for the use of multiple logistic regression analysis, ANN, and the SVM were 0.768, 0.778, and 0.847, respectively. Pairwise comparison of the ROC curves determined that the performance of the SVM was superior to that of the ANN or the multiple logistic regression model.
Conclusion
Image-based clinical decision support models allow patients to be informed of the actual probability of having a prostate cancer.
Similar content being viewed by others
References
Stephan C, Jung K, Cammann H et al (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
Catalona WJ, Richie JP, Ahmann FR et al (1994) Comparison of digital rectal examination and serum prostate specific antigen in the early detection of prostate cancer: results of a multicenter clinical trial of 6,630 men. J Urol 151:1283–1290
Woolf SH (1995) Screening for prostate cancer with prostate-specific antigen. An examination of the evidence. N Engl J Med 333:1401–1405
Catalona WJ, Smith DS, Ratliff TL et al (1991) Measurement of prostate-specific antigen in serum as a screening test for prostate cancer. N Engl J Med 324:1156–1161
Arcangeli CG, Ornstein DK, Keetch DW, Andriole GL (1997) Prostate-specific antigen as a screening test for prostate cancer. The United States experience. Urol Clin North Am 24:299–306
Richie JP, Catalona WJ, Ahmann FR et al (1993) Effect of patient age on early detection of prostate cancer with serum prostate-specific antigen and digital rectal examination. Urology 42:365–374
Catalona WJ, Smith DS, Ornstein DK (1997) 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. Jama 277:1452–1455
Lawrentschuk N, Fleshner n (2009) the role of magnetic resonance imaging in targeting prostate cancer in patients with previous negative biopsies and elevated prostate-specific antigen levels. BJU Int 103:730–733
Suzuki H, Komiya A, Kamiya N et al (2006) Development of a nomogram to predict probability of positive initial prostate biopsy among Japanese patients. Urology 67:131–136
Kamoi K, Babaian RJ (1999) Advances in the application of prostate-specific antigen in the detection of early-stage prostate cancer. Semin Oncol 26:140–149
Catalona WJ, Partin AW, Slawin KM et al (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
Suzuki H, Akakura K, Igarashi T et al (2004) Clinical usefulness of serum antip53 antibodies for prostate cancer detection: a comparative study with prostate specific antigen parameters. J Urol 171:182–186
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
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
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
Chun FK, Briganti A, Graefen M et al (2007) Development and external validation of an extended 10-core biopsy nomogram. Eur Urol 52:436–444
Finne P, Finne R, Bangma C et al (2004) Algorithms based on prostate-specific antigen (PSA), free PSA, digital rectal examination and prostate volume reduce false-positive PSA results in prostate cancer screening. Int J Cancer 111:310–315
Walz J, Graefen M, Chun FK et al (2006) High incidence of prostate cancer detected by saturation biopsy after previous negative biopsy series. Eur Urol 50:498–505
Nam RK, Toi A, Klotz LH et al (2007) Assessing individual risk for prostate cancer. J Clin Oncol 25:3582–3588
Bianco FJ Jr (2006) Nomograms and medicine. Eur Urol 50:884–886
Loch T, Leuschner I, Genberg C et al (1999) Artificial neural network analysis (ANNA) of prostatic transrectal ultrasound. Prostate 39:198–204
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:173–297
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
Eastham JA, May R, Robertson JL, Sartor O, Kattan MW (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
Potter SR, Horniger W, Tinzl M, Bartsch G, Partin AW (2001) Age, prostate-specific antigen, and digital rectal examination as determinants of the probability of having prostate cancer. Urology 57:1100–1104
Ohori M, Swindle P (2002) Nomograms and instruments for the initial prostate evaluation: the ability to estimate the likelihood of identifying prostate cancer. Semin Urol Oncol 20:116–122
Jiang L, Manry MT (2008) Nonlinear networks for classification. ftp://ftp.simtel.net/pub/simtelnet/msdos/calculte. Accessed 13 Mar 2008
Comak E, Arslan A, Turkoglu I (2007) A decision support system based on support vector machines for diagnosis of the heart valve diseases. Comput Biol Med 37:21–27
Chang C-C, Lin C-J (2008) LIBSVM–A library for support vector machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm. Accessed 1 Jul 2008
Kattan MW (2002) Nomograms. Introduction. Semin Urol Oncol 20:79–81
Porter CR, Gamito EJ, Crawford ED et al (2005) Model to predict prostate biopsy outcome in large screening population with independent validation in referral setting. Urology 65:937–941
Oesterling JE, Cooner WH, Jacobsen SJ, Guess HA, Lieber MM (1993) Influence of patient age on the serum PSA concentration. An important clinical observation. Urol Clin North Am 20:671–680
Carter HB, Pearson JD, Metter EJ et al (1992) Longitudinal evaluation of prostate-specific antigen levels in men with and without prostate disease. Jama 267:2215–2220
Richardson TD, Oesterling JE (1997) Age-specific reference ranges for serum prostate-specific antigen. Urol Clin North Am 24:339–351
Benson MC, Whang IS, Olsson CA, McMahon DJ, Cooner WH (1992) The use of prostate specific antigen density to enhance the predictive value of intermediate levels of serum prostate specific antigen. J Urol 147:817–821
Kattan MW, Eastham JA, Wheeler TM et al (2003) Counseling men with prostate cancer: a nomogram for predicting the presence of small, moderately differentiated, confined tumors. J Urol 170:1792–1797
Steyerberg EW, Roobol MJ, Kattan MW, van der Kwast TH, de Koning HJ, Schroder FH (2007) Prediction of indolent prostate cancer: validation and updating of a prognostic nomogram. J Urol 177:107–112 discussion 112
Errejon A, Crawford ED, Dayhoff J et al (2001) Use of artificial neural networks in prostate cancer. Mol Urol 5:153–158
Anagnostou T, Remzi M, Djavan B (2003) Artificial neural networks for decision-making in urologic oncology. Rev Urol 5:15–21
Babaian RJ, Miyashita H, Evans RB, Ramirez EI (1992) The distribution of prostate specific antigen in men without clinical or pathological evidence of prostate cancer: relationship to gland volume and age. J Urol 147:837–840
Babaian RJ, Fritsche H, Ayala A et al (2000) Performance of a neural network in detectong prostate cancer in the prostate-specific antigen reflex range of 2.5 to 4.0 ng/mL. Urology 56:1000–1006
Remzi M, Anagnostou T, Ravery V et al (2003) An artificial neural network to predict the outcome of repeat prostate biopsies. Urology 62:456–460
Remzi M, Djavan B, Hruby S et al (2001) Use of anewly developed artificial neural network(ANN) to select patients for repeat prostatic biopsies. Eur Urol 39:A106
Han M, Snow PB, Brandt JM, Partin AW (2001) Evaluation of artificial neural networks for the prediction of pathologic stage in prostate carcinoma. Cancer 91:1661–1666
Byvatov E, Fechner U, Sadowski J, Schneider G (2003) Comparison of support vector machine and artificial neural network systems for drug/nondrug classification. J Chem Inf Comput Sci 43:1882–1889
Giiler NF, Kocer S (2005) Use of support vector machines and neural network in diagnosis of neuromuscular disorders. J Med Syst 29:271–284. doi:10.1007/s10916-005-5187-4
Chu A, Ahn h, Halwan B et al (2008) A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Artif Intell Med 42:247–259
Mavroforakis ME, Georgiou HV, Dimitropoulos N, Cavouras D, Theodoridis S (2006) Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artif Intell Med 37:145–162
Veltri RW, Chaudhari M, Miller MC, Poole EC, O’Dowd GJ, Partin AW (2002) Comparison of logistic regression and neural net modeling for prediction of prostate cancer pathologic stage. Clin Chem 48:1828–1834
Cho J, Kim S, Lee S (2000) Peripheral hypoechoic lesions of the prostate: evaluation with color and power Doppler ultrasound. Eur Urol 37:443–448
Lee HJ, Kim KG, Lee SE et al (2006) Role of transrectal ultrasonography in the prediction of prostate cancer: artificial neural network analysis. J Ultrasound Med 25:815–821 quiz 822–814
Rabbani F, Stroumbakis N, Kava B, Cookson M, Fair W (1998) Incidence et clinical significance of false-negative sextant prostate biopsies. J Urol 159:1247–1250
Acknowledgements
This work was supported by the Interdisciplinary Research Initiatives Program by College of Engineering and College of Medicine, Seoul National University (2007, 800–20070086).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, H.J., Hwang, S.I., Han, Sm. et al. Image-based clinical decision support for transrectal ultrasound in the diagnosis of prostate cancer: comparison of multiple logistic regression, artificial neural network, and support vector machine. Eur Radiol 20, 1476–1484 (2010). https://doi.org/10.1007/s00330-009-1686-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-009-1686-x