Learning Outbreak Regions in Bayesian Spatial Scan Statistics

The problem of anomaly detection for bio- surveillance is typically approached in an un- supervised setting, due to the small amount of labeled training data with positive exam- ples of disease outbreaks. On the other hand, such model-based methods as the Bayesian scan statistic (BSS) naturally allow for adap- tation to the supervised learning setting, pro- vided that the models can be learned from a small number of training examples. We pro- pose modeling the spatial characteristics of outbreaks from a small amount of training data using a generative model of outbreaks with latent center. We present the model and the EM-based learning of its parameters, and we compare its performance to the standard BSS method on simulated outbreaks injected into real-world Emergency Department visits data from Allegheny County, Pennsylvania.