This article is more than 5 years old. Information may no longer be current.

Linked social media–EMR databank may lead to better health outcomes

A linked electronic medical record and social media database could yield insights pertaining to a patient's health, according to research published in BMJ Quality & Safety.

Kevin Padrez, MD, a resident physician in the department of emergency medicine at the University of California, San Francisco, and colleagues conducted a study of 1,433 participants to assess such a database.

"We don't often think of our social media content as data, but the language we use and the information we post may offer valuable insights into the relationship between our everyday lives and our health," Raina M. Merchant, MD, MSHP, a co-author of the study and director of the social media and health innovation lab at Penn Medicine, said in a press release. "Finding ways to effectively harness and mine that data could prove to be a valuable source of information about how and why patients communicate about their health. There is a rich potential to identify health trends both in the general public and at the individual level, create education campaigns and interventions, and much more."

The study included data from patients seeking care in an ED between March and October 2014. Padrez and colleagues reported that 5,259 patients were screened and approached for enrollment. Of the actual 1,433 study participants, 1,008 agreed to share EMR and social media.

Patients who elected to share social media data completed a survey regarding their demographics and social media habits. Using a previously designed app that utilized Facebook's public app, the researchers collected content from profiles that included user information, “liked” items and status updates from January 2009 through enrollment. Twitter data were collected using provided usernames; data included number of tweets, content and follower data.

Padrez and colleagues used SAS V.9.1 (SAS Institute) or Python programming language to conduct statistical analyses. They used a sample population (n = 19,184) that visited the same ED during the same period of time to compare with the participants who elected to share their social media information.

Results showed that participants who shared social media content were younger than those elected not to share (29.1 vs. 31.9 years; P < .001). The researchers estimated that 7.5% of Facebook posts (95% CI, 4.8-10.2) were health-related.

Additionally, participants with a diagnosis in their EMR were more likely to use diagnosis-related terms on Facebook than participants without those diagnoses (P < .0008).

Padres and colleagues reported that, of nonsharers, the primary reason for not sharing their social media information was privacy.

"These findings suggest that social media is a promising avenue for exploring how patients conceptualize and communicate about their specific health issues," Lyle Ungar, PhD, a co-author of the study and a professor of computer and information science at the University of Pennsylvania, said in the release. "We see this as just the first of many studies to come examining the relationship between health and social media."

The researchers concluded that social media information could be valuable in investigations of policy, public health and clinical applications.

"It is evident that individuals with a given medical diagnosis are more likely to use language related to that diagnosis on Facebook than individuals without that diagnosis," Padrez and colleagues wrote. "A linked EMR-social media databank could provide valuable data about patients' day-to-day activities related to their health." – by Chelsea Frajerman Pardes

Disclosure: The researchers report no relevant financial disclosures.