Medical Express September 16, 2020
Researchers at the University of Georgia used computer simulations to train a supervised learning algorithm to detect the dynamical footprints of (re-)emergence present in epidemiological data. They challenged their algorithm to forecast the slowly manifesting, spatially replicated reemergence of mumps in England in the mid-2000s and pertussis post-1980 in the United States. Their method successfully anticipated mumps reemergence 4 years in advance, during which time mitigation efforts could have been implemented. From 1980 onwards, the model identified resurgent states with increasing accuracy, leading to reliable classification starting in 1992. They successfully applied the detection algorithm to 2 vector-transmitted case studies, namely, outbreaks of dengue serotypes in Puerto Rico and a rapidly unfolding outbreak of plague in 2017 in Madagascar. Taken together, these findings illustrate the power of theoretically informed machine learning techniques to develop early warning systems for the (re-)emergence of infectious diseases…read more. Open Access TECHNICAL ARTICLE
Simulation of an emerging disease in a population of 100,000 susceptible individuals… Credit: PLOS Biology, May 20, 2020