An artificial intelligence tool that analyzed 28 physical and molecular measures—all but one taken from blood samples—confirmed with 77 percent accuracy a diagnosis of post-traumatic stress disorder (PTSD) in male combat veterans, according to a new study.

Led by NYU School of Medicine, the Harvard John A. Paulson School of Engineering and Applied Sciences, and the U.S. Army Medical Research and Development Command, the study describes for the first time a blood-based biomarker panel for diagnosing warzone-related PTSD. Published online September 9 in the journal Molecular Psychiatry, the measures included genomic, metabolic, and protein biomarkers.

“While work remains to further validate our panel, it holds tremendous promise as the first blood test that can screen for PTSD with a level of accuracy useful in the clinical setting,” says senior study author Charles R. Marmar, MD, the Lucius N. Littauer Professor and chair of the Department of Psychiatry at NYU School of Medicine. “If we are successful, this test would be one of the first of its kind—an objective blood test for a major psychiatric disorder.”

There are currently no U.S. Food and Drug Administration-approved blood tests, for instance, for depression or bipolar disorder, says Dr. Marmar. The new study embodies a longstanding goal in the field of psychiatry: to shift mental health toward standards like those used in cardiology or cancer, for instance, in which lab tests enable accurate diagnoses based on physical measures (biomarkers) instead of on self-reporting or interviews with inherent biases.

People with PTSD experience strong, persistent distress when reminded of a triggering, traumatic event. According to a World Health Organization survey, more than 70 percent of adults worldwide have experienced a traumatic event at some point in their lives, although not all develop the condition.

Narrowing Down the Biomarkers

For the current study, 83 male, warzone-exposed veterans of the Iraq and Afghanistan conflicts with confirmed PTSD, and another 82 warzone-deployed veterans serving as healthy controls, were recruited from the Manhattan, Bronx, and Brooklyn Veterans Affairs (VA) Medical Centers, as well as from other regional VA medical centers, veterans’ service organizations, and the community.

The researchers tested nearly 1 million features with current genomic and other molecular tests and narrowed them to 28 markers. By measuring a large number of unbiased quantities, the team sought to determine which of them were associated with an accurate PTSD symptom diagnosis.

Using a combination of statistical techniques, the study authors narrowed the best measures from 1 million to 343 to 77, and then finally to 28, with the final group outperforming the larger groups in prediction accuracy. Some of this winnowing was accomplished using machine learning—mathematical models trained with data to find patterns.

The team then applied their “PTSD blood test” to an independent group of veterans to see how well their new tool matched the diagnoses made previously using standard clinical questionnaires, such as the Clinician-Administered PTSD Scale for DSM-5 (CAPS-5). This comparison yielded the 77 percent accuracy figure.

“These molecular signatures will continue to be refined and adapted for commercialization,” says co-senior study author Marti Jett, PhD, chief scientist in systems biology for the U.S. Army Medical Research and Development Command, within the U.S. Army Center for Environmental Health Research. “The Department of Health Affairs within the Department of Defense is considering this approach as a potential screening tool that could identify service members before and after deployment with features of unresolved post-traumatic stress.”

Identified service members would be referred for their specific issues, such as sleep disruption or anger management—care that is available at most military bases, adds Dr. Jett.

The current study did not seek to explain the disease mechanisms related to the final markers, but rather to blindly pick those that did the best job of diagnosing PTSD. Nevertheless, the group of best performing markers included the activity levels of certain genes, the amounts of key proteins in the blood, the levels of metabolites involved in energy processing, as well as the levels of circulating microRNAs (miRNAs)—snippets of genetic material known to alter gene activity that are tied to heart diseases and features of PTSD. The one indicator not measured by the blood test was heart rate variability.

“These results point toward many biochemical pathways that may guide the future design of new drugs, and support the theory that PTSD is a systemic disease that causes genetic and cellular changes well beyond the brain,” says corresponding author Frank Doyle, PhD, dean of the Harvard John A. Paulson School of Engineering and Applied Sciences, one of the research study’s sites.

Previous studies of genetic predictors of PTSD risk have shown strong performance in younger, active duty populations, says author Kelsey Dean, PhD, a member of Dr. Doyle’s group at Harvard. This suggests that such biomarkers may be able to signal for PTSD at its earliest ages, and be useful in prevention. For future research, studies of populations beyond male veterans will be needed to better understand the clinical utility of the proposed biomarker panel.

Along with Dr. Marmar, study authors from the Department of Psychiatry at NYU School of Medicine included Duna Abu-Amara; Eugene M. Laska, PhD; Jennifer Newman, PhD; and Carole Siegel. Along with Dr. Doyle and Dr. Dean, study authors from the Harvard John A. Paulson School of Engineering and Applied Sciences at Harvard University included Burook Misganaw, Pramod R. Somvanshi, and Gunjan Thakur.

Along with Dr. Jett, study authors from the U.S. Army Medical Research and Development Command, within the U.S. Army Center for Environmental Health Research, at Fort Detrick in Frederick, Maryland, were co-first author Rasha Hammamieh and Aarti Gautam. Additional study authors from University of California, San Francisco included Synthia Mellon, in the Department of Obstetrics, Gynecology, and Reproductive Sciences, and F. Saverio Bersani, Victor I. Reus, Daniel Lindqvist, and Owen M. Wolkowitz, in the Department of Psychiatry. Study authors from the Department of Psychiatry at the James J. Peters VA Medical Center in the Bronx and the Icahn School of Medicine at Mount Sinai included Janine Flory and Rachel Yehuda. Study authors from the Department of Psychiatry at McLean Hospital in Belmont, Massachusetts, included Guia Guffanti and Kerry J. Ressler.

Additional study authors included Kai Wang, Inyoul Lee, Taek-Kyun Kim, Min Young Lee, Nathan Price, Shizhen Qin, Yong Zhou, and Leroy Hood at the Institute for Systems Biology in Seattle; along with Bernie Daigle Jr. and Liangqun Lu in the Departments of Biological Sciences and Computer Science at the University of Memphis; Ruoting Yang at the Advanced Biomedical Computing Center at Frederick National Laboratory for Cancer Research; and Lynn Almli, Kimberly Kerley, and Adriana Lori in the Department of Psychiatry and Behavioral Sciences at Emory University. Also participating in the study were authors Nabarun Chakraborty, Duncan Donohue, and Seid Muhie of the U.S. Army Center for Environmental Health Research, a research site of the Geneva Foundation, located in Frederick, Maryland.

This work was supported by funding from the U.S. Army Research Laboratory’s Army Research Office grant W911NF-17-2-0086, U.S. Army Research Laboratory grant W911NF-17-1-0069, and by U.S. Department of Defense grants W81XWH-10-1-0021, W81XWH-09-2-0044, and W81XWH-14-1-0043.

Media Inquiries

Greg Williams
Phone: 212-404-3533
gregory.williams@nyulangone.org