"People’s personality, mental state, and health behaviours are all reflected in their social media and all have tremendous impact on health," said the researchers.
Facebook posts can be used to spot health problems such as diabetes, anxiety, depression and psychosis, according to researchers at the University of Pennsylvania’s Perelman School of Medicine and Stony Brook University in New York.
The language used in the Facebook posts could be indicators of disease and, with patient consent, could be monitored just like physical symptoms.
“People’s personality, mental state, and health behaviours are all reflected in their social media and all have a tremendous impact on health. This is the first study to show that language on Facebook can predict diagnoses within people’s health record, revealing new opportunities to personalise care and understand how patients’ ordinary daily lives relate to their health,” the University of Pennsylvania School of Medicine and Stony Brook University researchers said in the published study.
The researchers, whose study was published in PLOS One, analysed the Facebook posts of about 1,000 patients.
“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,” lead author Dr Raina Merchant told Science Daily.
“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.”
Later this year, Dr Raina Merchant will conduct a large trial in which patients will be asked to directly share social media content with their health care provider.
Merchant’s team used an automated data collection technique to analyse the entire Facebook posting history of those who agreed to take part and to share their data. Participants also agreed to have electronic medical records linked to their profiles.
Three different models were then built to asses the data – one which focused on the Facebook data only, one which used demographics such as age and sex and a third which combined both datasets.
Looking into 21 different conditions, the researchers claim that all 21 were predictable from Facebook data alone.
Diagnoses Prediction Strength of Demographics and Facebook. Supplied: Raina Merchant, Andrew Schwartz, David A Asch
The regular use of words such as “drink” or “bottle” could be used to predict alcohol abuse, while the use of hostile language was found to be an indicator of drug abuse and psychoses, the researchers said. It follows a previous study carried out last year by some of the same team which suggested that social media posts could help predict a diagnosis of depression.
Merchant said the poor health data “could be valuable” for those who use social media on a regular basis.
“For instance, if someone is trying to lose weight and needs help understanding their food choices and exercise regimens, having a healthcare provider review their social media record might give them more insight into their usual patterns in order to help improve them,” she said.
Later this year, Merchant is due to lead a trial that will ask patients to directly share their social media content with their health care provider, which the researchers say will offer insight into how willing patients are to use their online posts as part of healthcare.