Twitter may help predict ED visits for chronic conditions
by
Lauren Dubinsky, Senior Reporter | April 20, 2015
Analyzing big data generated from Twitter may help hospitals predict how many asthma sufferers will visit their emergency department on a given day, according to a new research led by the University of Arizona (UA).
"We realized that asthma is one of the biggest traffic generators in the emergency department," Sudha Ram, a professor at UA, said in a statement. "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."
Ram and her fellow researchers gathered air quality data from environmental sensors that were nearby the Dallas hospital. In addition, they analyzed tweets that contained the keywords ‘asthma,’ ‘inhaler,’ and ‘wheezing.’
The researchers used EMR data to find out where most of the hospital’s patients live and then used text-mining techniques to focus on the most relevant tweets in those areas. After compiling all of that data, they found that when the air quality measures got worse and there were more asthma-related tweets, there was an increase in patients visiting the ED.
The machine learning algorithms that the researchers used were able to predict whether the ED would experience a low, medium or high amount of asthma patients on a given day with 75 percent accuracy. This research highlights the fact that big data from social media and environmental sensors could play a big role in predicting ED visits for chronic conditions, including diabetes, according to the researchers.
This model for predicting ED visits for chronic conditions may lead to significant cost savings. As a result of asthma, there are about 2 million ED visits, half a million hospitalizations and 3,500 deaths per year, which equates to over $50 billion in costs, according to the researchers.
Right now, hospitals are able to make risk predictions about when individual asthma patients might visit the ED based on medical histories but this new model is able to predict that on a population level. "The CDC gets reports of emergency department visits several weeks after the fact, and then they put out surveillance maps," Ram said in a statement. "With our new model, we can now do this in almost real time, so that's an important public health surveillance implication."
|
|
You Must Be Logged In To Post A Comment
|