External Link - Source: The Washington Post
Last year, more than 1 million Americans attempted suicide, and 47,000 succeeded. While some people display warning signs, many others do not, which makes suicide difficult to predict and leaves family members shocked — and anguished that they couldn’t do something.
Medical providers and tech companies, including the Department of Veterans Affairs and Facebook, are increasingly applying artificial intelligence to the problem of suicide prediction. Machine learning software, which excels at pattern recognition, can mine health records and online posts for words and behaviors linked to suicide and alert physicians or others to impending attempts. The potential upside of this effort is huge, because even small increases in predictive accuracy could save thousands of lives each year.