Sleep insufficiency may be caused by many societal factors such as 24/7 access to technology and work schedules, but sleep disorders such as insomnia or obstructive sleep apnea also play an important role. The Centers for Disease Control and Prevention estimate 50-70 million US adults have sleep or wakefulness disorder. Such disorders affect our productivity, car accidents and risky behaviors, and they contribute to diabetes, cardiovascular disease and depression.

Researchers from Boston Children’s Hospital and Merck have discovered a way to collect data that represent sleep disorder symptoms by looking at the way people use Twitter. The researchers have created “digital phenotypes” that reflect behavior of someone with insomnia or another sleep disorder. A “digital phenotype” is simply an observable characteristic influenced by genetics or environment.

The research team used publically available data from Twitter to create a virtual test group of 896 active Twitter users whose tweets contained sleep-related words such as “can’t sleep,” “insomnia,” or hashtags  #cantsleep, #teamnosleep, or the names of common sleep aids or medications. They then compared data from that test group to those of a second group of 934 users who did not tweet using sleep-related terms. From these tweets, researchers were able to discover larger populations with some sort of sleep disorder.

The use of big data in healthcare has been increasingly effective in predicting diseases, treating them and even curing some. So it’s no surprise that this study was published in the Journal of Medical Internet Research. This timely study is one of the first to look at links between social media use and sleep disorders.

Another interesting aspect of this study is they were able to assess sentiments expressed in users’ tweets—the tweets were hints that patients with sleep disorders may be at a greater risk for psychosocial issues.

Historically, research on sleep disorders has relied on survey methods. Someone calling you and asking you a list questions would be an example. Such methods are expensive, time intensive and often do not represent the larger U.S. population.

John S. Brownstein, who directs the hospital’s Computational Epidemiology Group, said: “We wanted to see if we could use new forms of online data, such as Twitter, to characterize the sleep disordered individual and possibly uncover new, previously-undescribed populations of patients suffering sleep problems.”

“These findings are preliminary and observational only, and need to be studied further,” Brownstein cautioned. “But they suggest that social media can be a useful addition to our toolkit for studying the patient experience and behavioral epidemiology of sleep disorders.”

Sleep disorders are increasingly affecting society, and besides insomnia, one underdiagnosed disorder is sleep apnea. From this study, there is hope that we’ll be able to help more people who suffer from this treatable condition too.