The computer modeling program was the focus of a new study published in the Journal of the American Medical Association, Psychiatry. For the study, researchers from Harvard University analyzed data from all 40,820 U.S. soldiers hospitalized for psychiatric problems over a six-year period from 2004 to 2009. At that time, the annual suicide rate in the Army was 18.5 suicides per 100,000 soldiers. The rate among soldiers hospitalized for psychiatric problems was more than 14 times that. Using computer modeling, researchers combed through 421 potential variables that might place a soldier at greater risk for suicide and identified roughly two dozen factors that proved most important.
The team then created an algorithm to identify some of the soldiers most likely to commit suicide. Sixty-eight of the soldiers killed themselves within a year of hospitalization. More than half of those soldiers had characteristics that when examined after the fact, placed them in a high-risk group for suicide risk. Of the remaining 1,921 soldiers who were also flagged as being high-risk for suicide, seven died in accidents and 555 attempted suicide within a year of hospitalization.
The new prediction program analyzes 30 factors that might predict a soldier's suicide risk, including age at enlistment, history of violence, type of injury, and prescription drug use. Hearing loss was another surprising factor that researchers found could identify soldiers who may be most likely to consider suicide — possibly due to the link between hearing loss and head injury.
The model, if it can be integrated smoothly military-wide, would allow doctors to follow high-risk soldiers closely after discharge, and to take preventive measures such as ordering a few weeks of mandatory outpatient therapy after discharge; facilitating a social support network of friends and family; and teaching soldiers coping mechanisms for dealing with stress and depression.
While the Army already has protocols in place to prevent suicide within its ranks, this new prediction program could help military doctors zero in on the soldiers who need the most help. If successful, it could prove to be the most rigorous suicide prediction tool available.
According to researchers, the new computer model could save four lives for every 100 soldiers treated. “This would be unparalleled, compared to almost any other intervention we could make in medicine,” said Lt. Gen. Eric B. Schoomaker, a former surgeon general of the Army and a professor of military and emergency medicine at the Uniformed Services University of the Health Sciences in Bethesda, Maryland
Related on MNN: