The language that people use in their postings on Facebook is effective in predicting diabetes and mental health conditions, including anxiety, depression and psychoses.
That’s the conclusion of a new study from Penn Medicine and Stony Brook University researchers.
Published on Monday in PLOS ONE, they evaluated whether consenting patients’ Facebook posts could be used to predict their diagnoses documented in their electronic medical records.
Researchers analyzed Facebook postings from almost 1,000 patients who agreed to have their EMR data linked to their profiles.
“We found that the language people use in Facebook is predictive of their health conditions reported in an EMR, often more so than typically available demographic data,” state the authors, who note that 10 of 21 conditions included in the study were better predicted through the use of Facebook data vs. demographic information.
“Although some early research has linked social media language use with health, this is the first study to the best of our understanding to do so at the level of the patient with EMR data,” contend researchers.
“Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors,” states the article. “Analogous to the genome, social media data linked to medical diagnoses can be banked with patients’ consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool and elucidate disease epidemiology.”
Researchers see potential for clinicians to analyze patients’ social media data through an “opt- in system” in order to determine disease risk and conduct health interventions.
“This work is early, but our hope is that the insights gleaned from these posts could be used to better inform patients and providers about their health,” says Raina Merchant, MD, lead author and the director of Penn Medicine’s Center for Digital Health. “As social media posts are often about someone’s lifestyle choices and experiences or how they’re feeling, this information could provide additional information about disease management and exacerbation.”
Merchant plans to conduct a large trial later this year in which patients will be asked to share social media posts with their provider to determine whether the management and application of the data is feasible, as well as how many patients would actually consent.
“One challenge with this is that there is so much data and we, as providers, aren’t trained to interpret it ourselves—or make clinical decisions based on it,” adds Merchant. “To address this, we will explore how to condense and summarize social media data.”
For reprint and licensing requests for this article, click here.