Machines can spot mental health issues—if you hand over your personal data

MansBrand.com Articles Provided as noted by attribution.

When Neguine Rezaii first moved to the United States a decade ago, she hesitated to tell people she was Iranian. Instead, she would use Persian. “I figured that people probably wouldn’t know what that was,” she says. 

The linguistic ambiguity was useful: she could conceal her embarrassment at the regime of Mahmoud Ahmadinejad while still being true to herself. “They just used to smile and go away,” she says. These days she’s happy to say Iranian again. 

We don’t all choose to use language as consciously as Rezaii did—but the words we use matter. Poets, detectives, and lawyers have long sifted through people’s language for clues to look for their motives and inner truths. Psychiatrists, too: perhaps psychiatrists especially. After all, while medicine now has a battery of tests and technical tools for diagnosing physical ailments, the chief tool of psychiatry is the same one employed centuries ago: the question “So how do you feel today?” Simple to ask, maybe—but not to answer.  

“In psychiatry we don’t even have a stethoscope,” says Rezaii, who is now a neuropsychiatry fellow at Massachusetts General Hospital. “It’s 45 minutes of talking with a patient and then making a diagnosis on the basis of that conversation. There are no objective measures. No numbers.” 

There’s no blood test to diagnose depression, no brain scan that can pinpoint anxiety before it happens. Suicidal thoughts cannot be diagnosed by a biopsy, and even if psychiatrists are deeply concerned that the covid-19 pandemic will have severe impacts on mental health, they have no easy way to track that. In the language of medicine, there is not a single reliable biomarker that can be used to help diagnose any psychiatric condition. The search for shortcuts to finding corruption of thought keeps coming up empty—keeping much of psychiatry in the past and blocking the road to progress. It makes diagnosis a slow, difficult, subjective process and stops researchers from understanding the true nature and causes of the spectrum of mental maladies or developing better treatments.

But what if there were other ways? What if we didn’t just listen to words but measure them? Could that help psychiatrists follow the verbal clues that could lead back to our state of mind?

“That is basically what we’re after,” Rezaii says. “Finding some behavioral features that we can assign some numbers to. To be able to track them in a reliable manner and to use them for potential detection or diagnosis of mental disorders.”

In June 2019, Rezaii published a paper about a radical new approach that did exactly that. Her research showed that the way we speak and write can reveal early indications of psychosis, and that computers can help us spot those signs with unnerving accuracy. She followed the breadcrumbs of language to see where they led. 

Rezaii found that language analysis could predict with more than 90% accuracy which patients

Read More

————

By: Bobbie Johnson
Title: Machines can spot mental health issues—if you hand over your personal data
Sourced From: www.technologyreview.com/2020/08/13/1006573/digital-psychiatry-phenotyping-schizophrenia-bipolar-privacy/
Published Date: Thu, 13 Aug 2020 10:00:00 +0000

The post Machines can spot mental health issues—if you hand over your personal data appeared first on MansBrand.

from MansBrand https://www.mansbrand.com/machines-can-spot-mental-health-issuesif-you-hand-over-your-personal-data/?utm_source=rss&utm_medium=rss&utm_campaign=machines-can-spot-mental-health-issuesif-you-hand-over-your-personal-data
via IFTTT