Slashdot Mirror
Artificial Intelligence Can Now Predict Suicide With Remarkable Accuracy (qz.com)
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.
Not that I think this is a particularly useful bit of research but - the study's patients pretest probability of suicide was much higher than the general population. These are people who are ADMITTED TO A HOSPITAL with concerns of self harm. They've already passed a bunch of screens to separate them from everybody else.
So you are talking a group of people that the current system thinks is at some non trivial risk of suicide and trying to figure out which ones are at the highest risk.
So it's quite a bit more useful than some of the posters have been assuming. Still not sure how generalizable this will be, but give the researchers a bit of a break.
Faster! Faster! Faster would be better!
Suicide is a low probably event in the general population but their initial data set was not random, it was 5000 patients already exhibiting symptoms of self harm. Picking out the people in that group likely to kill themselves is a pretty impressive feat.