Dept. of Veterans Affairs Taps IBM Watson for Help With PTSD

With many veterans suffering from posttraumatic stress disorder (PTSD), the U.S. Department of Veterans Affairs is looking to IBM's Watson for help.

IBM logo

IBM announced that the U.S. Department of Veterans Affairs (VA) is using Big Blue's Watson cognitive computing technology to help veterans with posttraumatic stress disorder (PTSD).

The VA is building a Clinical Reasoning System using IBM Watson that will assist physicians and accelerate the process of evidence-based medical decision making. With this multiyear contract, the VA joins leading health care organizations that are using IBM Watson to help improve the efficiency and quality of care being delivered.

According to the VA's National Center for PTSD, there are approximately 21.6 million veterans in the United States. As many as 20 percent of veterans who served in Operations Iraqi Freedom (OIF) and Enduring Freedom (OEF) are impacted with PTSD, the VA said. Additionally, 12 percent of Gulf War veterans and 15 percent of Vietnam veterans suffer from PTSD.

"IBM designed Watson to help solve some of the world's greatest challenges, and I'm humbled to be working with VA in helping them, including enhancing treatment efforts for PTSD," said Anne Altman, general manager for U.S. Federal at IBM, in a statement. "There's no more important challenge than improving healthcare for our veterans and we've seen how Watson can assist medical professionals and make it easier for them to capture insight from so many sources and make more informed decisions. VA is poised to join other key healthcare industry leaders who are already pioneering the use of cognitive computing in healthcare."

IBM noted that with the amount of medical data doubling every three years and the size and complexity associated with patient data in electronic medical records (EMRs), Watson will help Veterans Health Administration (VHA) clinicians quickly make sense of large amounts of data. Watson will make it possible for VHA physicians to interact with medical data in natural language, process millions of pages of patient information and medical literature to uncover patterns and insights, and learn from each interaction. By sifting through reams of clinical data, Watson is able to distill evidence and knowledge within seconds, IBM said.

Historically, the potential of EMRs has not been realized due to the discrepancies of how the data is recorded, collected and organized across health care systems and organizations, IBM said. Watson's cognitive capabilities provide a differentiated approach to understanding the dynamics of the EMR environment and correlate what is in the EMR with medical literature, research and articles—making data from EMRs more meaningful at the point of care.

To this end, in a separate effort, IBM also has been working with the Cleveland Clinic in applying Watson to EMR systems to help clinicians navigate and process medical records to uncover key information and unlock hidden insights within data. Using an evidence-based approach has the potential to help physicians make more informed decisions about patient care.

Meanwhile, the VA will use capabilities of the IBM Watson Discovery Advisor to analyze health care data. Available now as a cloud service, IBM's Watson Discovery Advisor is designed to scale and accelerate discoveries. It can reduce the time physicians need to test hypotheses and formulate conclusions that can advance their work from months to days and days to just hours, bringing new levels of speed and precision to research and development.

IBM is supporting VHA physicians and staff in setting up their Clinical Reasoning System at the department's data center in Austin, Texas. Watson will ingest hundreds of thousands of VHA documents, as well as medical records and research papers to help physicians improve patient care in the clinical environment. In this capacity, the VA is evaluating the system in simulated pre-visit, visit and post-visit situations where physicians will conduct technical, functional and usability assessments.