Computational tool identifies 800 risk factors for PTSD

The aim of the new study was to find predictive sets of early risk indicators that could be used to construct an algorithm similar to one previously developed for molecular and cancer research. The researchers used data from the Jerusalem Trauma Outreach and Prevention Study, for 4,743 participants admitted to emergency departments following potentially traumatic events.

When applied to data collected within 10 days of a traumatic event, the algorithm demonstrated that it could more accurately predict which individuals were most likely to develop PTSD, even taking into account the huge variety of ways in which traumatic events can occur.

“This study extends our ability to predict effectively,” states Dr. Shalev. “For example, it shows that features like the occurrence of head trauma, duration of stay in the emergency department, or survivors’ expressing a need for help, can be integrated into a predictive tool and improve the prediction.”

Dr. Shalev states that the study is merely a “proof of concept,” and that further testing is required to refine the algorithm. He states that it will need to be used with more data collected from other patient populations and traumatic events in order for it to be able to provide robust predictions in all circumstances.