Main title

• Anxiety, depression and psychosis can be identified via language in social media posts.
• With patient consent language can be monitored in posts, just like monitoring physical symptoms.

• Some conditions are better predicted through social media data, than through demographic data.
• People who used religious language like "pray" the most, were 15 times more likely to have diabetes than people who used these words the least.
• Hostile words and expletives were indicative of dug 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. 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 for medicine.” - Andrew Schwartz, PhD.

• Research has shown that computer model analysis of posts can predict depression three months earlier than clinic diagnosis.

Source: pennmedicine.org