We conducted a retrospective study to ascertain the potential of free-text chief complaints collected in pediatric emergency

We conducted a retrospective study to ascertain the potential of free-text chief complaints collected in pediatric emergency departments to serve as surveillance data for early detection of outbreaks. detection from such data and both suffered from either methodological limitations or very small sample size. 4,5 The present study attempts to measure performance characteristics of a biosurveillance system based on free-text chief complaints, a type of data collected during emergency room visits. Currently the scientific evidence as to the value of free-text chief complaints for outbreak detection is limited to the results of one prior study. 6 In that study, we measured case detection accuracy of freetext chief complaint classifiers and demonstrated that a case of acute infectious gastrointestinal illness can be detected by automatic coding of a chief complaint with sensitivity 0.63 and specificity 0.94. The fact that the focus of the study was limited to case detection accuracy did not allow us to make any conclusions regarding the value of free-text chief complaints for outbreak detection. To our knowledge there are no studies that measured sensitivity, specificity and timeliness of outbreak detection from automatically coded free-text chief complaint data relative to other types of surveillance data. We determined that automatically coded chief complaint data provide a signal that reflects outbreaks in a population of children less than five years of age. Using the Exponentially Weighted Moving Average (EWMA) detection algorithm, we measured the timeliness, sensitivity, and specificity of free-text chief complaints for predicting outbreaks of pediatric respiratory and gastrointestinal illness. We found that time series of automatically coded free text-chief complaints in pediatric patients correlate well with hospital admissions and precede them by the mean of 10.3 days (95% CI -15.15, 35.5) for respiratory outbreaks and 29 days (95% CI 4.23, 53.7) for gastrointestinal outbreaks. We conclude that free-text chief complaints may play an important role as an early, sensitive and specific indicator of outbreaks of respiratory and gastrointestinal illness in children less than five years of age. The primary hypothesis in the present study is that automatically coded chief complaint data provide a signal that reflects an outbreak in a certain population. INTRODUCTION