A computer model may be able to predict post-traumatic stress disorder on an individual level.
A proof of concept paper published in BMC Psychiatry identified the risk patterns that make people more vulnerable to post-traumatic stress disorder (PTSD).
The World Health Organiztion (WHO) reported that the majority of adults will experience at least one traumatic event in their lifetime — five to 10% of which can develop PTSD. Arieh Y. Shalev, MD, and colleagues from NYU Langone Medical Center and New York University School of Medicine analyzed the records and early symptoms of nearly 1,000 trauma survivors within 10 days of emergency department admissions in order to identify interchangeable sets of risk indicators that would increase the efficiency of early risk assessment. The researchers used a Target Information Equivalence Algorithm they previously developed for cancer research to predict PTSD symptom trajectories throughout the subsequent 15 months of observation.
“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,” Shalev, the Barbara Wilson Professor in the Department of Psychiatry at NYU Langone and a co-director of NYU's Steven and Alexandra Cohen Veterans Center, explained in a press release.
The model can handle the input of a variety of data, including type of event, early symptoms, and emergency department findings. An individualized model to predict PTSD can go a long way in specializing prevention methods before patients develop the condition, the researchers said.
“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,” Shalev explained.
The current model for clinicians calculates the average risk for entire groups of survivors, but is insufficient in surmising data and risk calculators for a specific individual. The new algorithm, the researchers believe, will predict PTSD.
“Until recently, we mainly used early symptoms to predict PTSD, and it had its drawbacks,” Shalev continued. “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.”
In order to make this proof of concept paper into a more accurate study, the researchers have partnered with more than 20 universities worldwide to analyze their data sets and create a comprehensive model of predictions.
“In the future, we hope that we will be better able to tailor treatment approaches based on more personalized risk assessment,” Shalev concluded. “PTSD exacts a heavy toll on affected individuals and society.”