VA, NIMH Develop Algorithm For Spotting Veterans Who May Commit Suicide

The New York Times reports that VA and NIMH researchers have “developed a database they say can identify veterans with a high likelihood of suicide, in much the same way consumer data is used to predict shopping habits.” The database, detailed in a study published June 11 in the American Journal of Public Health, uses a “computer algorithm using hundreds of variables” that has showed success in testing. While “many of the risk factors, such as being hospitalized for a psychiatric condition or making a previous suicide attempt, may seem obvious, said” Michael Schoenbaum, PhD, of the NIMH, one of the study’s authors, investigators “found that these high-risk patients, who should have been flagged by doctors and other health care staff under traditional suicide prevention protocols now in place, were not.” Schoenbaum said, “The database is so overwhelmingly better than just guessing, which is what we’ve been doing.”

USA Today (6/12, Zoroya) reports, “Using records from more than 3,000 patients who committed suicide between 2008 and 2011,” researchers “identified a range of factors from age, gender and race to service-connected disabilities, homelessness and hospitalizations that could be part of formula for singling out groups of veterans most at risk for suicide.” Next, investigators “used the formula to identify about 600 veterans whose suicide rates were 60 to 80 times higher than other VA patients, or only 1/100th of 1%.” The study revealed “a group – 1/10th of a percent of the veteran population – who were 30 to 39 times more likely to take their lives.”

Related Links:

— “Database May Help Identify Veterans on the Edge,” Dave Phillips, New York Times, June 11, 2015.

Posted in In The News.