Slashdot Mirror
Machine Learning Used To Predict Military Suicides
HughPickens.com (3830033) writes David Wagner writes that a predictive computer model using machine learning methods is helping to identify soldiers in the United States Army most likely to commit suicide. Computers combed through data on more than 40,000 soldiers who'd been hospitalized for mental health problems looking at 421 variables on each soldier drawn from 38 military data systems. Using a method known as "machine learning," the researchers identified roughly two dozen factors that are most important in predicting soldiers most likely to commit suicide. The soldiers most likely to take their own lives were men with past suicidal behavior and a history of psychiatric disorders and criminal offenses, including weapons possession and verbal assaults. Soldiers with hearing loss also faced heightened risk — a strong indicator that they had suffered a head injury. So did enlisting in the Army after age 27, most likely because those soldiers had already experienced trouble finding their way in life. "There's this group that comes to the Army later in life — they're smart, they have skills, they tend not to be married and they have no career or have left a career to join," Dr. Kessler said. "We don't know why they should be at higher risk, but they appear to be."
Murray Stein, co-author of the new study, found that among soldiers recently discharged from psychiatric hospitals, more than half of suicides were committed by just five percent of patients. "The most impressive thing is that they identified this high-risk group in the hospital, and by just focusing on one in 20 of them, you're really dramatically improving your ability to predict," says Dr. Mark Olfson, a professor of psychiatry at Columbia University who was not involved in the study. "Clinicians don't do a very good job predicting suicide risk, even though we think we do."
Murray Stein, co-author of the new study, found that among soldiers recently discharged from psychiatric hospitals, more than half of suicides were committed by just five percent of patients. "The most impressive thing is that they identified this high-risk group in the hospital, and by just focusing on one in 20 of them, you're really dramatically improving your ability to predict," says Dr. Mark Olfson, a professor of psychiatry at Columbia University who was not involved in the study. "Clinicians don't do a very good job predicting suicide risk, even though we think we do."
Stop speaking of machine learning as if it's a new kind of black magic. I know it sounds better than "using a mathematical algorithm" or "performed statistical analysis", but to me it sounds as ridiculous as the "quantum whatever" of the 90's. Seriously, ML is being hyped beyond reasonable.
Video of some good progressive thrash music
How to prevent many military suicides: ask your soldiers to kill other human beings and endure the horrors of war only for purposes of legitimate defense against a foreign nation that actually initiated hostilities without any sort of provocation. See that would be the difference between heroic defenders and murderers. Most people are not sociopaths and have a hard time living with knowing they murdered a bunch of people for no good reason.
As the justifications for our little undeclared wars gets flimsier and flimsier, the rates of soldier suicides and mental health issues goes up. War has always been hell, always involved PTSD (shellshock), etc, but the soldiers who stopped Hitler didn't have the rate of suicide found in the soldiers who wondered why the hell they're in Iraq blowing up people who aren't threatening the USA.
But the military-industrial-complex Eisenhower tried to warn us about, it cries out to be fed blood and treasure. Defense contractors have some real power in Washington. CIA funded and trained Al-Qaida (research this, then pass judgment, like an intelligent person) and just loves overthrowing democratically elected foreign governments. Eisenhower could see this coming over 50 years ago because he was informed and paid attention instead of drooling in front of a TV worrying about football and Taylor Swift. If you think the mass media cares about doing anything other than keeping you asleep so you vote for a major party and buy more frivolous shit you don't need, you haven't critically examined it at all.
Yeah, that was a very poorly written sentence. Your explanation is much better.
He was able to re-explain it because he did something that is declining in popularity on Slashdot: he comprehended what he read.
Good writing eliminates ambiguity. Good reading chooses the most likely interpretation in cases of ambiguity. It is immediately obvious that good reading can alleviate the effects of bad writing, but cannot eliminate the effects, as the most likely interpretation still has some chance of being wrong.
As it is written, the sentence "More than half of the suicides were committed by just five percent of patients." is as silly as "Sixty percent of the time, works every time."