How to use open source data to assess infection disease risk: A framework and applications

Disease risk assessment plays an important role in controlling the diffusion of infectious diseases. It needs a large number of environmental, social, and economic development data in order to discover the pathogenic factors of a given disease. However, the conventional disease risk assessment is carried out mainly through the analysis of geographic data and non-geographic data released by officials. The assessment falls far behind the propagation of the diseases. To address the issue of government data lagging, we propose a disease risk assessment framework using the open source data. Our proposed framework includes five sections: Automatic Data Discovery, Data Organization, Computing resource calling, Model selection and Visualization. The process of data discovery and organization can be done automatically. Distributed computing resources are used and users can select the spatial analysis models interactively for prediction and visualization. The rabies disease example is implemented using the proposed framework and verifies the effectiveness and efficiency of our framework by good results.