Twitter helps predict ED visits for asthma

Twitter is emerging as another tool for predictive analytics in healthcare.

By collecting and mapping the location of tweets with keywords such as “asthma,” “inhaler” and “wheezing,” mining the EHR at Parkland Memorial Hospital, then comparing to air-quality reports in the Dallas area, researchers were able to predict asthma-related emergency department traffic with 75 percent accuracy.

Twitter is emerging as another tool for predictive analytics in healthcare.

By collecting and mapping the location of tweets with keywords such as “asthma,” “inhaler” and “wheezing,” mining the EHR at Parkland Memorial Hospital, then comparing to air-quality reports in the Dallas area, researchers were able to predict asthma-related emergency department traffic with 75 percent accuracy, according to a new study. The results will appear the IEEE Journal of Biomedical and Health Informatics’ upcoming special issue on big data, but the report is available online in prepublication format now.

“We realized that asthma is one of the biggest traffic generators in the emergency department,” primary researcher Sudha Ram, director of the Advanced Database Research Group at the University of Arizona, and co-director of the school’s INSITE Center for Business Intelligence and Analytics, 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 collaborated with Dr. Yolande Pengetnze of the Parkland Center for Clinical Innovation in Dallas and two others to build machine-learning algorithms that could analyze tweets, air-quality data and patient data to estimate whether ED traffic for respiratory issues would be low, medium or high on any given day.

While 75 percent may not seem like a high rate of accuracy, it is enough to introduce predictive analytics in place of retrospective analysis, the researchers suggested. “The CDC gets reports of emergency department visits several weeks after the fact, and then they put out surveillance maps,” Ram said. “With our new model, we can now do this in almost real time, so that’s an important public health surveillance implication.”

Ram said that she hopes this work can lead to predictive models for other chronic diseases to estimate a greater range of ED traffic based on tweets.

“You can get a lot of interesting insights from social media that you can’t from electronic health records,” Ram said. “You only go to the doctor once in a while, and you don’t always tell your doctor how much you’ve been exercising or what you’ve 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.”

[Image from University of Arizona.]