Syndromic Surveillance protects the public by detecting disease outbreaks early. Public health officials are interested in methods that will provide earlier and more accurate detections. Back Propagation has been demonstrated to be an accurate, robust, and scalable detection technique for disease outbreaks in over-the-counter pharmaceutical sales, and Support Vector Machines have been proven to be valuable in prediction. The purpose of this study was to determine whether Support Vector Machines are comparable to Back Propagation in the context of Syndromic Surveillance. This study used Back Propagation and Support Vector Machines to detect outbreaks based on Emergency Department and Telehealth data. We utilized a data simulation methodology to produce sufficient quantities of realistic data to perform this study. The results demonstrated that Support Vector Machines with polynomial kernel are superior to Back Propagation for detecting disease outbreaks based on data from Emergency Department. In addition, Support Vector Machines with linear kernel are comparable to Back Propagation for detecting outbreaks based on data from Telehealth.