VA Researchers Use EMRs, Natural Language Processing to Identify Suicide Risks

Researchers at the U.S. Department of Veterans Affairs are using natural language processing on electronic medical records to help the VA identify patients at high risk for suicide.

According to the researchers, the best predictor of future suicide attempts is a previous suicide attempt, a predictor twice as accurate as the next-best indicator, major depression. Researchers are using natural language processing, a technology used by online search engines, to comb through clinical notes and summaries in EMRs to identify patients with a history of suicidal behavior.

"The EMR system stores a very large body of clinical notes," said researcher Ken Hammond, MD, in the report. "We've shown that we can use search engine technology to more easily identify those veterans who have attempted suicide at some point in their lives. That can help us prevent future attempts."

The automated text search developed by the researchers is about 80 percent accurate, as verified against individual psychiatric notes. The research team is also expanding the search to look for other indicators of future suicide attempts, such as childhood abuse.

More Articles on the VA:

VA Awards 5-Year, $29M Telehealth Contract to AMC Health
Federal HIT Vendor Systems Made Simple Announces 300% Revenue Increase, 40 Government Contracts
$656M Orlando VA Delayed Again 

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Content

Featured Webinars

Featured Whitepapers