Sharad Kunduku, an assistant professor of computer science at the University of Pennsylvania who is not involved in the research, warns that although these methods have yielded interesting results, they are nowhere to be found in changing the role of physicians in diagnosing patients. “At least in my lifetime, I don’t think there will ever be a time when only social media data is used to find a person. It’s not going to happen,” says Burnham. , To use these as a complimentary data to see if more care or extra contact is needed from the doctor. “
Schwartz points out that diagnosing mental illness is a valid science that can be improved by adding more data sources. “The idea is, you triangulate mental health,” he says. “Assessing mental health is an exercise in trusting only one tool.” Because social media provides a continuous record of a person’s thoughts and actions over a considerable period of time, it can effectively complement the hourly medical interviews commonly used to make diagnoses. In one such interview, Swartz says, “You still rely on a patient to remember everything and remember things about themselves. The doctor has to decide when they are suffering from desirable dependencies ”- that is, they say what they think the patient wants to ask their doctor. Perhaps, social media information can give a lesser idea of a patient’s mental state.
Munmun de Chowdhury, a professor of interactive computing at Georgia Tech, has previously worked with Burnham, but has not been involved in this particular study, choosing a social media plugin that can alert users when they are suffering from mental illness. But such a plugin immediately raises privacy concerns a data about a person’s mental state, if leaked, could be misused by insurance companies or employers or force a person to disclose their mental state status before preparing to do so. To work, De Chaudhry says, plugin makers need to be completely transparent about how they handle and protect user data. But, if such a procedure can detect the symptoms of mental illness one and a half years before a patient is usually diagnosed, it can make a huge difference in people’s lives. “If we already see these symptoms, there may be other ways to alleviate these worries that do not require a trip to the doctor,” he says.
There is already a precedent for using social media to prevent mental crises. “Facebook and Google, they’re already doing this on some level,” says Bombay. If a user searches for words related to suicide on Google, the National Suicide Prevention Lifeline number will appear before all other results; Facebook uses artificial intelligence to detect posts that may indicate suicide risk and send them to human reviewers for review. If moderators agree that the post represents a real risk, Facebook may send suicide prevention resources to the user or contact law enforcement. But suicide presents a clear and immediate risk, while the process of obtaining a psychiatric diagnosis is often absent – social media users may be willing to sacrifice more privacy to prevent suicide shortly before starting schizophrenia. “Any public, large-scale psychiatric diagnosis, at the individual level, is very tricky and very ethically dangerous,” says Bombay.
For his part, Burnham sees a less grandiose, but nonetheless utility case for this research. As a physician, he believes that social media data not only helps clinicians triangulate diagnoses, but also monitor patients as they progress through long-term treatment. “Thoughts, feelings, actions – they change, they change all the time. Unfortunately, in psychiatry, we get a snapshot once a month, which is great, ”he says. “Combining this type of information really allows us to gain a comprehensive, contextual understanding of one’s life.”
Researchers still have a long way to go in designing these algorithms and figuring out how to implement them ethically. But in the next five to 10 years, Burnham believes that social media information may become a normal part of mental health practice. “One day, digital data and mental health will really come together,” he says. “It will be on the mind of one of our X-rays. It will be our blood test to support diagnoses and interventions we recommend.”
More great WIRED stories