According to the National Center for PTSD, approximately 6.8 percent of Americans aged 18 years and older suffer a lifetime prevalence of post-traumatic stress disorder, or PTSD. Data from the National Comorbidity Survey, originally conducted in the early 1990s, women are nearly twice as likely to suffer PTSD than are men, with over 10 percent of all women having at least one bought with PTSD over their lifetimes. Predicting who will develop PTSD aids in preventive efforts, but making these predictions in individuals has proven difficult.
To address this difficulty and to improve targeted intervention strategies, researchers at the New York University Langone Medical Center developed and tested a computer algorithm intended to identify interchangeable sets of patient characteristics that predict PTSD risk. The results were published online Monday in the journal BMC Psychiatry.
“Our study shows that high-risk individuals who have experienced a traumatic event can be identified less than two weeks after they are first seen in the emergency department,” said Arieh Y. Shalev, of NYU Langone and the Steven and Alexandra Cohen Veterans Center, in a statement. “Until now, we have not had a tool—in this case a computational algorithm—that can weigh the many different ways in which trauma occurs to individuals and provides a personalized risk estimate.”
The scientists considered data on traumatic event characteristics, emergency room records, and early symptoms gathered from 957 trauma patients within 10 days of their ER admissions. With these data, they constructed a “Target Information Equivalence Algorithm” to assemble all of the smallest sets of variables possible that have meaningful predictive value. Not all data is available from each patient, so the ability to predict who will develop PTSD from a variety of data subsets is powerful.
“Until recently, we mainly used early symptoms to predict PTSD, and it had its drawbacks,” said Shalev. “This study extends our ability to predict effectively. 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.”
Shalev and coworkers are collaborating with researchers at Harvard and Columbia Universities to generalize their model with data from 19 emergency centers worldwide so that experts can anticipate and prevent PTSD more effectively than ever before.
“In the future, we hope that we will be better able to tailor treatment approaches based on more personalized risk assessment,” Dr. Shalev said. “PTSD exacts a heavy toll on affected individuals and society.”