[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
[Skip to Content Landing]
December 7, 2011

Natural Language Processing and Electronic Medical Records

Author Affiliations

Author Affiliation: Accenture, San Francisco, California (kip.webb@accenture.com).

JAMA. 2011;306(21):2325-2326. doi:10.1001/jama.2011.1780

To the Editor: As was shown in the study by Dr Murff and colleagues, natural language processing may augment the value of electronic medical records by helping hospitals identify adverse events after surgery.1 When compared with a gold standard of Veterans Affairs Surgical Quality Improvement Program nurse review, the authors demonstrated that natural language processing was more sensitive and only slightly less specific in detecting postsurgical complications when compared with the more widely used patient safety indicators based on diagnostic codes. The value of natural language processing, the authors noted, is that it may improve a hospital's ability to detect postsurgical complications, particularly while the patient is still in the hospital.