Influenza is an important cause of infectious disease morbidity and mortality. The pathogen accounts for 36,000 to 41,000 deaths annually and is one of the top 10 leading causes of death for people above 65 and below 4 years of age. Its annual cost to the U.S. economy is between $71 and $167 billion dollars. As part of a larger system that detects and characterizes influenza outbreaks in the Real-time Outbreak and Disease Surveillance Laboratory (RODS) at University of Pittsburgh, we developed a Bayesian Case Detector (BCD) that uses an natural language processor to extract the influenza-related findings from Emergency Department reports and a Bayesian Network classifier to compute the probability that a patient has influenza given the set of NLP extracted findings. In this talk, two questions will be discussed. First, how valuable the BCD could be for public health surveillance and for front line clinicians? Second, how to further improve BCD’s performance?