Social media often serves as a signal of medical distress that could be utilized to help hospitals determine when a patient might seek emergency care.

Previous research has analyzed clinical information to forecast readmissions but looking at digital signatures on social media can predict individuals’ behaviors, thoughts and motivations prior to a healthcare visit. A study published in the March 12 edition of Nature Scientific Reports found that people made Facebook posts that discussed family and health more than usual. They also included language that was more anxious, worrisome and depressed and had less informal language.

“The decrease in informal language seems to go hand-in-hand with an increase in anxiety-related language,” said H. Andrew Schwartz, an assistant professor of computer science at Stony Brook University. Schwartz collaborated with the Penn Medicine Center for Digital Health, part of the Perelman School of Medicine at the University of Pennsylvania. “While it is hard to say right now if this would be the same result across multiple social media platforms, people live a lot of their lives online and Facebook is that dominant platform right now."

Researchers recruited nearly 3,000 patients at an urban hospital who agreed to share their personal Facebook posts as well as their electronic health records. Of participants, 419 had a recent emergency department visit, which included things like chest pain and pregnancy complications. Researchers used a machine learning model to analyze posts from two-and-a-half months before the date of the ED visit. The model processed the language used to find identify changes over time.

Specifically, the study found people experienced a significant change in the language they used on Facebook prior to seeking care in an ED. For example, they didn't use as many words like "play," "fun" or "nap" and they wrote "you" instead of "u" and other types of common internet slang.

“The better we understand the context in which people are seeking care, the better they can be attended to,” said lead author and University of Pennsylvania research scientist Sharath Chandra Guntuku. “While this research is in a very early stage, it could potentially be used to both identify at-risk patients for immediate follow-up or facilitate more proactive messaging for patients reporting doubts about what to do before a specific procedure.”

Along with language, researchers also examined the context of the posts. Some posted about fasting for 24 hours prior to a surgery or about eating a fatty meal about a month before experiencing chest pains.

While this study looks at the specific type of language used, Schwartz and senior author Dr. Raina Merchant conducted a previous study showing a person's depression could be identify by looking at his or her posts on Facebook up to three months prior to an official diagnosis.

“How does life affect personal decisions to seek care? How does care affect life? These are the things I would hope that we could fully describe, how people’s everyday lives intermix with health care,” Schwartz said.