Stochasticity and spatial heterogeneity are of great interest recently in studying the spread of an infectious disease. Populations in a combination of epidemiological compartment models and a meta-population network model are described by stochastic differential equations. This study addresses a node discovery problem. Solving the problem means discriminating between neighboring nodes which are connected to and directly influenced by (and influence as well) a missing influential spreader node, and non-neighboring nodes in a given dataset. The dataset is the time sequence data on the number of patients in the early growth phase of an infectious disease outbreak. Two statistical discriminators are presented. One is founded on the Kolmogorov-Smirnov test for estimating the minimal distance between two cumulative probability density distributions. The other is founded on the Chauvenet rejection test for detecting an outlier in a given dataset. The performance of the discriminators is tested with a number of computationally synthesized datasets and the World Health Organization (WHO) dataset on Severe Acute Respiratory Syndrome (SARS) outbreak.
View on arXiv