In his recent publication, Respiratory Syncytial Virus Tracking using Internet Search Engine Data, published in BMC Infectious Diseases, Dr. Eyal Oren, Associate Professor within the division of Epidemiology and Biostatistics at SDSU, highlights the use of internet search engines to track the spread of Respiratory Syncytial Virus (RSV). Dr. Oren’s epidemiological interests include the behavioral aspects of infectious disease, with an emphasis in respiratory health. He strives to utilize and develop innovative tools and technologies to explore the links between the social, environmental, and spatial epidemiologic methods, and how they apply to health differences and disparities within a population. Dr. Oren demonstrates this interest in the article discussed here by utilizing a common internet practice to examine RSV rates and trends.
RSV is the leading cause of hospitalization in children less than 1 year of age in the United States. To lessen the impact of RSV, the utilization of internet search engine queries may provide high resolution temporal and spatial data that can estimate and predict disease activity. This study performed by Dr. Oren and his colleagues is the first time that RSV has been tracked using internet data results. Furthermore, it highlights the successful use of search filters and domain adaptation techniques by using data at multiple resolutions. Using predictive models, Google Trends search query data, and domain adaptation, they tracked the spread of RSV by observing the time of peak use of the search term in different states. These search result models were then evaluated against actual state-level case trend data.
In general, their results demonstrate that the RSV internet search engine peaks correlate well with actual case surveillance data, showing that viral activity begins in the south-east (Florida) and moves to the north-west of the U.S. According to Dr. Oren, “these results show that a model based on search engine data reaches a high observed correlation with national epidemiological test data.” Furthermore, their approach, “may assist in identifying the spread of both local and more widespread RSV transmission and may be applicable to other seasonal conditions where comprehensive epidemiological data is difficult to collect or obtain”.
You can read the article in full here.