Influenza surveillance and early warning system based on search engine data

With the continuous development of the Internet and improvement of the network coverage, search engine has become the main channel for information query. As query keywords directly reflect people´s intent and search data can be counted in real time, the network search data is considered the ideal data source for influenza surveillance. In the practical application, a surveillance and early warning system utilizing the search engine data and the official monitoring data, such as CDC, can perform early warning of major infectious diseases in time so as to take preventive measures, thus reducing the risk of disease transmission and the financial burden of the country and the people. Compared with the traditional disease monitor system, that based on the network search data has the characteristics of fast response, easy access, low cost and so on; however, it still faces many challenges, such as the uncertainty of the netizen’s behavior, the inaccuracy of the search keywords and the incomplete network coverage, etc. Therefore, future research should focus on improving the accuracy of Internet search data and explore the ways to use spatial and temporal data for infectious disease prediction and early warning through combining search engine data with geographic information system (GIS). Furthermore, they need to remove the barriers between data modules and collect data collectively and comprehensively, so as to realize the sharing of big data and improve the utilization of data and the accuracy of the monitoring and early warning system.