ML Algorithms Can Predict Suicide Risk More Readily Than Clinicians

> die by suicide

It's nice to see US publications move to different language.

> But a new study concludes that the science of suicide prediction is dismal, and the established warning signs about as accurate as tea leaves.

Yes. To be fair, that's not really new information. Current advice is to avoid suicide risk assessment scales because they're based on weak evidence.

http://bjp.rcpsych.org/content/209/4/277

One thing the submitted article doesn't talk about: You've identified someone at high risk of attempting suicide. What do you do? What intervention do you provide?