Health-Related Tweets could Help Predict Emergency Room Traffic

Twitter users who post personal health related information might be considered by some to be over-sharers, but University of Arizona study suggests that these health-related tweets may have the potential to be helpful for hospitals. Researchers have created a model that was able to predict with 75% accuracy how many emergency room visits a hospital could expect on a given day. The researchers looked specifically at the chronic condition of asthma and how asthma-related tweets, analyzed alongside other data, may help predict asthma-related emergency room visits. Lead author Sudha Ram said, "We realized that asthma is one of the biggest traffic generators in the emergency department and often what happens is that there are not the right people in the ED to treat these patients or not the right equipment and that causes a lot of unforeseen problems."

The researchers found that asthma related visits to the emergency room went up as certain air quality measures worsened, and also as the number of asthma-related tweets increased. The researchers additionally looked at asthma-related Google searches in the area. However, they found that it was not a good predictor for asthma emergency room visits.

Ram said, "The research highlights the important role that big data, including streams from social media and environmental sensors, could play in addressing health challenges. People can get a lot of interesting insights from social media that they cannot from electronic health records. People only go to the doctor once in a while and they do not always tell doctor how much they have been exercising or what they have been eating, but people share that information all the time on social media. We think that prediction models like this can be very useful, if we can combine various types of data, to address chronic diseases. We have got really good results and now we are working on building even more robust models to see if it can increase the accuracy level by using more types of datasets over a longer time period."

The study will appear in Journal of Biomedical and Health Informatics.

Source-Medindia