Facebook posts can be indicators of depression in patients
Facebook posts can be very telling, as one recent study revealed an algorithm could predict depression in patients based on their posts with a fair amount of accuracy.
The algorithm, built by a research team with the University of Pennsylvania, could potentially help identify more sufferers of depression, which remains underdiagnosed and undertreated despite being the most common mental illness, affecting between 7 percent and 26 percent of the U.S. population.
The study, which was published in the Proceedings of the National Academy of Sciences (PNAS), analyzed the Facebook posts from 683 patients that visited a large urban academic emergency department. Of those patients, 114 were diagnosed with depression.
Variables of Facebook posts, such as post length, frequency of posting, posting patterns and demographics, were built into a prediction model, or algorithm, that predicted the probability of depression.
Researchers compared the probability of depression estimated by the algorithm against the actual presence or absence of depression among consenting participants of the study.
Using the Facebook content, results revealed that researchers could predict a patient’s depression prior to being clinically diagnosed with fair accuracy, "approximately matching the accuracy of screening surveys benchmarked against medical records," according to the study. Using content limited to six months prior to being diagnosed, researchers could predict a patient’s depression with even higher accuracy.
Researchers specifically looked at language in Facebook posts, including posts about "emotional (sadness), interpersonal (loneliness, hostility), and cognitive (preoccupation with the self, rumination) processes."
“These results lend plausibility to the estimates of predictive power because one would expect just such a temporal trend,” the study said. “Although this prediction accuracy is relatively modest, it suggests that, perhaps in conjunction with other forms of unobtrusive digital screening, the potential exists to develop burdenless indicators of mental illness that precede the medical documentation of depression (which may often be delayed) and which, as a result, could reduce the total extent of functional impairment experienced during the depressive episode.”
Danielle covers Clinical Innovation & Technology as a senior news writer for TriMed Media. Previously, she worked as a news reporter in northeast Missouri and earned a journalism degree from the University of Illinois at Urbana-Champaign. She's also a huge fan of the Chicago Cubs, Bears and Bulls.