According to new preliminary American research, healthcare professionals could potentially use Facebook as a means of diagnosing conditions such as depression and diabetes.
Carried out by researchers at the University of Pennsylvania and Stony Brook University, the new study analysed the complete Facebook post history of 999 patients – around 20 million words – who had agreed to have their electronic medical record data linked to their Facebook profiles.
The researchers built three models to analyse whether the posts could predict medical conditions across 21 broad categories. One model analysed the language used in the patient’s Facebook posts, another used demographics such as age and sex, and the last combined and analysed both sets of data.
The findings, published in the journal PLOS ONE, showed that all 21 medical conditions included in the study could be predicted by Facebook alone.
In fact, Facebook data was better at predicting 10 of the conditions than the demographic information, and was particularly effective at predicting diabetes and mental health conditions, including anxiety, depression and psychoses.
Certain words used in Facebook appeared to be fairly intuitive at predicting whether users have certain diseases, e.g. “drink” and “bottle” were shown to be more predictive of alcohol abuse.
However, other associations between words and diseases were less obvious. For example, those who used religious language the most, using words like “God” or “pray”, were 15 times more likely to have diabetes than those who used those words the least.
Negative and hostile words such as “dumb”, and some swear words, predicted drug abuse and psychoses.
“Our digital language captures powerful aspects of our lives that are likely quite different from what is captured through traditional medical data,” said study senior author Dr Andrew Schwartz.
“Many studies have now shown a link between language patterns and specific disease, such as language predictive of depression or language that gives insights into whether someone is living with cancer.
“However, by looking across many medical conditions, we get a view of how conditions relate to each other, which can enable new applications of AI (artificial intelligence) for medicine.”
“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,” added study lead author Dr Raina Merchant.
“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.” – AFP Relaxnews