Pre-operative prediction of advanced prostatic cancer using clinical decision support systems: accuracy comparison between support vector machine and artificial neural network

• Published in: Korean journal of radiology Vol. 12; no. 5; pp. 588 - 594
• Main Authors: Kim, Sang Youn, Moon, Sung Kyoung, Jung, Dae Chul, Hwang, Sung Il, Sung, Chang Kyu, Cho, Jeong Yeon, Kim, Seung Hyup, Lee, Jiwon, Lee, Hak Jong
• Format: Journal Article
• Language: English
• Published: Korea (South) The Korean Society of Radiology 01.09.2011; 대한영상의학회
• Subjects: Accuracy; Adult; Aged; Aged, 80 and over; Area Under Curve; Back propagation; Biopsy; Biopsy, Needle; Classification; Clinical decision making; Decision support systems; Decision Support Systems, Clinical; Humans; Integrated software; Male; Middle Aged; Neural networks; Neural Networks (Computer); Original; Patients; Probability; Prostate cancer; Prostate-Specific Antigen - blood; Prostatectomy; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - pathology; Prostatic Neoplasms - surgery; ROC Curve; Sensitivity and Specificity; Support Vector Machine; Support vector machines; 방사선과학; United States > US; Medical order entry systems; Prostatic neoplasms; Decision support systems, clinical; Staging; Needle biopsy
• ISSN: 1229-6929; 2005-8330
• DOI: 10.3348/kjr.2011.12.5.588

The purpose of the current study was to develop support vector machine (SVM) and artificial neural network (ANN) models for the pre-operative prediction of advanced prostate cancer by using the parameters acquired from transrectal ultrasound (TRUS)-guided prostate biopsies, and to compare the accuracies between the two models. Five hundred thirty-two consecutive patients who underwent prostate biopsies and prostatectomies for prostate cancer were divided into the training and test groups (n = 300 versus n = 232). From the data in the training group, two clinical decision support systems (CDSSs-[SVM and ANN]) were constructed with input (age, prostate specific antigen level, digital rectal examination, and five biopsy parameters) and output data (the probability for advanced prostate cancer [> pT3a]). From the data of the test group, the accuracy of output data was evaluated. The areas under the receiver operating characteristic (ROC) curve (AUC) were calculated to summarize the overall performances, and a comparison of the ROC curves was performed (p < 0.05). The AUC of SVM and ANN is 0.805 and 0.719, respectively (p = 0.020), in the pre-operative prediction of advanced prostate cancer. The performance of SVM is superior to ANN in the pre-operative prediction of advanced prostate cancer.