Slashdot Mirror

← Back to Stories (view on slashdot.org)

Artificial Intelligence Can Now Predict Suicide With Remarkable Accuracy (qz.com)

Posted by ryuzaki0 on from the AI-for-good dept.

An anonymous reader writes: Colin Walsh, data scientist at Vanderbilt University Medical Center, and his colleagues have created machine-learning algorithms that predict, with unnerving accuracy, the likelihood that a patient will attempt suicide. In trials, results have been 80-90% accurate when predicting whether someone will attempt suicide within the next two years, and 92% accurate in predicting whether someone will attempt suicide within the next week. The prediction is based on data that's widely available from all hospital admissions, including age, gender, zip codes, medications, and prior diagnoses. Walsh and his team gathered data on 5,167 patients from Vanderbilt University Medical Center that had been admitted with signs of self-harm or suicidal ideation. They read each of these cases to identify the 3,250 instances of suicide attempts. This set of more than 5,000 cases was used to train the machine to identify those at risk of attempted suicide compared to those who committed self-harm but showed no evidence of suicidal intent.

9 of 161 comments (clear)

  1. An Algorithm.... by Luthair · · Score: 3, Insightful

    not artificial intelligence.

    1. Re:An Algorithm.... by Rick+Schumann · · Score: 3, Insightful

      That AC you're responding to is far from being a 'fuckwit', they actually understand what's going on. You on the other hand keep sipping the media hype-supplied Kool-Aid and don't know the difference between the ersatz and the real thing when it comes to so-called 'AI'. Go educate yourself.

    2. Re:An Algorithm.... by hey! · · Score: 3, Insightful

      This story is about machine learning. Whether you consider machine learning to be "artificial intelligence" probably says more about your definition of "artificial intelligence" than it does about machine learning.

      Machine learning definitely replaces human judgment at certain tasks -- in this case classifying a thing by its attributes -- however it does it in ways that an unaided human brain cannot duplicate. For example it might examine the goodness of fit of a large number of alternative (although structurally similar) algorithms against a vast body of training data.

      Many years ago, when I was a college student, AI enthusiasts used to say things like, "The best way to understand the human mind is to duplicate its functions." I believe that after three decades that has proven to be true, but not in the way people thought it would be true. It turns out the human way of doing things is just one possible way.

      I think that's a pretty significant discovery. But is it "AI"? It's certainly not what people are expecting. On the plus side, methods like classification and regression trees produce algorithms that can be examined and critiqued analytically.

      --
      Post may contain irony: discontinue use if experiencing mood swings, nausea or elevated blood pressure.
  2. Simple solution by Opportunist · · Score: 4, Insightful

    Give people a reason to not kill themselves and you'll see rates drop.

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  3. Re:92% accuracy! by iggymanz · · Score: 4, Insightful

    your are correct, these morons used a group of suicidal patients for their case study and now are claiming great success.

  4. Percentages are misleading by gman003 · · Score: 4, Insightful

    Simple accuracy percentages are misleading when applied to low-probability events. An "AI" that always returned "No" to the query "Will this person commit suicide within the next two years?" would be 97.2% accurate (and 99.975% accurate for the next-week variant). And yet, that "AI" would be absolutely useless for any practical purpose.

    Not to mention, with suicides, access to means has been a better statistical predictor than anything else, even mental illness. A person with no personal or family history of mental illness, but with a gun and a gas oven in their house, is at higher risk of killing themselves than a bipolar alcoholic with neither.

  5. Re:False positive rate by barbariccow · · Score: 4, Insightful

    It's probably mostly meaningless. I mean, they scanned for features of people who are suicidal. They were in the hospital because they inflicted self harm, and were on medications specifically prescribed to make people not do that. So as far as I can tell, this doesn't predict anything, it juts measures that "80-90% of the time doctors do the same thing for folks who would hurt themselves".

    It's not like they randomly picked a bunch of people off the street and determined from THAT. Like basically every single other artificial intelligence or machine learning story, it's a bunch of dumb hype, eventually to get folks investing in stupid startups.

  6. Involuntary commitment? by Theaetetus · · Score: 4, Insightful

    So, once the computer diagnoses someone as highly likely to kill themselves in the next week, then does it (or the user) call the men in white coats to give the subject the coat with the funny sleeves? Therapists frequently have a statutory or license requirement to report potential suicides.
    We don't know what the rate of false positives are, but with our current state of health insurance, getting locked up for a week and then getting a $50k bill would probably drive most people to suicide.

  7. Wrong title by nospam007 · · Score: 3, Insightful

    The title speaks of suicides while the article only of _attempted_ suicides, checking admissions to hospitals
    Real suicides get admitted to the morgue instead.