Tweets may help predict asthma-related hospitalisations

Keeping tabs on tweets may be an effective tool to help prepare for - and prevent - increases in asthma-related emergencies, researchers, including one of Indian-origin, have found.

The study suggests that to predict and possibly prevent severe asthma attacks in a community, physicians can look for clues in social media.

Researchers collected tweets posted between October 2013 and June 2014 and narrowed them down to the 3,810 that mentioned asthma attacks and that originated in the Dallas-Fort Worth area in the US.

During the same time period, incidence of asthma-related emergency department visits and hospitalisations across the region area were recorded.

When the number of asthma-related tweets increased in a given week, the researchers found, the number of asthma emergency department visits or hospitalisations increased proportionally during the following week.

“If the number of asthma-related tweets increased by 20 in a given week, for example, we would expect asthma-related emergency department visits or hospitalisations to increase by 12 in the following week,” said lead researcher Yolande Mfondoum Pengetnze, medical director at Parkland Centre for Clinical Innovation (PCCI), a non-profit research and development corporation in the US.

“This is an important finding that can change the way health departments and other healthcare stakeholders monitor asthma activity in a community,” said Pengetnze.

She said asthma activity in a community is usually measured after emergency department visits or hospitalisations already have occurred.

“By using real-time Twitter activity health departments could actually anticipate asthma ED visits or hospitalisations in the following days and possibly intervene before some of them occur,” she said.

“For instance, a notification might be sent by the health department when there is an increase in asthma-related tweets in the community, giving people with asthma a heads-up to take necessary precautions, like avoiding exposure to asthma triggers or being more assiduous in taking their asthma medications,” said Pengetnze.

In turn, she said, this could help prevent some asthma flare-ups, improve people’s health and decrease the number of asthma-related emergency department visits and hospitalisations.

“We live in the era of Big Data,” said study co-author Sudha Ram, referring to increasingly immense sets of information that lends itself well to analysis revealing patterns of human behaviour.

“Our research is innovative and unique because it harnesses the power of Big Data from social media and other sources to address the problem of anticipating emergency department visits for a chronic condition, in this case asthma, in close to real-time conditions,” Ram said.