Enter Your Email Address to Receive a
Copy of MedicExhange Member Demograhpics

Department of Radiology, Seoul National University College of Medicine, conducted a study for the comparison of multiple logistic regression, ANN, and SVM, and concluded that Image-based CDS for transrectal ultrasound can be used in the diagnosis of prostate cancer.

For the study, a multiple logistic regression model, an artificial neural network (ANN), and a support vector machine (SVM) model was first developed to predict the outcome of a prostate biopsy, and compared the accuracies of each model.

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.

The result was that, 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. Also, the 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.