Natural language processing analysis of electronic medical records is more effective in identifying postoperative complications than patient safety indicators based on discharge coding, according to a study published in the Journal of the American Medical Association.
Researchers compared two approaches for identifying postoperative complications in medical records: natural language processing and patient safety indicators that use discharge coding. The postoperative complications included acute renal failure requiring dialysis, deep vein thrombosis, pulmonary embolism, sepsis, pneumonia and myocardial infarction.
The language processing had a higher percentage of correct identification for all postoperative complications that occurred. For example, natural language processing correctly identified 82 percent of acute renal failure cases, compared with 38 percent for patient safety indicators.
AMA Votes for Standardized EMR Interface
EMR Vendors Stress Usability When Targeting Physicians
The language processing had a higher percentage of correct identification for all postoperative complications that occurred. For example, natural language processing correctly identified 82 percent of acute renal failure cases, compared with 38 percent for patient safety indicators.
Related Articles on EMRs:
5 Considerations for Adding EMR to Your ASCAMA Votes for Standardized EMR Interface
EMR Vendors Stress Usability When Targeting Physicians