Twitter is proving its mettle in healthcare once again.
Researchers from Boston Children’s Hospital and pharmaceutical giant Merck are mining the microblogging site to produce a “digital phenotype” as a baseline for identifying people suffering from sleep disorders.
In an article published this week in the open-access Journal of Medical Internet Research, the researchers found that Twitter users with sleep issues were more likely to tweet during overnight hours and be more negative in their tweets than the general Twitter population. However, they also uncovered some evidence that goes against the conventional wisdom that increased social media usage can lead to insomnia.
With the Rise of AI, What IP Disputes in Healthcare Are Likely to Emerge?
Munck Wilson Mandala Partner Greg Howison shared his perspective on some of the legal ramifications around AI, IP, connected devices and the data they generate, in response to emailed questions.
By writing code through Twitter’s application programming interface, the research team searched Twitter every 15 minutes for keywords and hashtags that indicate sleep problems, such as: “can’t sleep”; “insomnia”; “melatonin”; “Ambien”; .
“This was not an exhaustive search across all possible search terms, but rather an exploratory approach to test the utility of this type of analysis,” they wrote.
The team then manually curated tweets to select only those in the U.S. and only those that suggested a possible sleep problem for a specific person; messages like “Ambien makes you sleepy” were excluded. They also analyzed times and sentiments expressed in each eligible tweet.
“[W]e found that users with sleep issues have significantly more negative sentiment in the tweets they are posting compared to others, which may indicate a tendency for individuals identified as having a sleep issue via social media to be at a greater risk of psychosocial issues,” the researchers found. They cautioned, however, that the results were preliminary and that the subject required further study.
A Personalized Approach to Medication Nonadherence
At the Abarca Forward conference earlier this year, George Van Antwerp, managing director at Deloitte, discussed how social determinants of health and a personalized member experience can improve medication adherence and health outcomes.
“Sleep deprivation and chronic sleep disorders are not well understood,” researcher John Brownstein, director of the Computational Epidemiology Group that covers several Boston healthcare institutions, said in a press release. “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.”
