Identification of Associations between Clinical Signs and Hosts to Monitor the Web for Detection of Animal Disease Outbreaks

Abstract

In a context of intensification of international trade and travels, the transboundary spread of emerging human or animal pathogens represents a growing concern. One of the missions of the national veterinary services is to implement international epidemiological intelligence for a timely and accurate detection of emerging animal infectious diseases (EAID) worldwide, and take early actions to prevent their introduction on the national territory. For this purpose, an efficient use of the information published on the web is essential. The authors present a comprehensive method for identification of relevant associations between terms describing clinical signs and hosts to build queries to monitor the web for early detection of EAID. Using text and web mining approaches, they present statistical measures for automatic selection of relevant associations between terms. In addition, expert elicitation is used to highlight the most relevant terms and associations among those automatically selected. The authors assessed the performance of the combination of the automatic approach and expert elicitation to monitor the web for a list of selected animal pathogens.

Web monitoring of emerging animal infectious diseases integrated in the French Animal Health Epidemic Intelligence System

“…Moreover, our list of terms of disease names, hosts and clinical signs is derived from vocabulary describing outbreaks in a set of relevant news reports [ 14 ]. To obtain our list of terms, we use BioTex, a tool for automatic extraction of biomedical terms from free text [ 15 ].…”

“…A group of five disease specialists evaluates the terms highlighted by the veterinary epidemiologist and selects the most appropriate ones that describe a given disease. The final list includes the terms validated by the majority of specialists [ 14 ]. We also use this list of terms in the data processing and IE steps.…”

“…Diseases and hosts . Text fragments that match one of the names from the lists previously compiled in the Data collection step [ 14 , 16 ].…”

[Demo] Integration of Text- and Web-Mining Results in EpidVis

“…Epidemiologists also use external knowledge to build queries, e.g. knowledge transmitted from their colleagues, or data extracted with text-mining or statistical approaches [7].…”

“…Mutual Information and Cubic Mutual Information). This contribution is detailed in [7]. The values of association measures represent the input of suggestion view of EpidVis.…”