Detecting possible vaccine adverse events in clinical notes of the electronic medical record |
| |
Authors: | Brian Hazlehurst Allison NalewayJohn Mullooly |
| |
Affiliation: | Center for Health Research, Kaiser Permanente Northwest, 3800 N. Interstate Avenue, Portland, OR 97215, United States |
| |
Abstract: | The Vaccine Safety Datalink (VSD) is a collaboration between the CDC and eight large HMOs to investigate adverse events following immunization through analyses of clinical data. We modified an existing system, called MediClass, that uses natural language processing to identify clinical events recorded in electronic medical records (EMRs). We customized MediClass so it could detect possible vaccine adverse events (VAEs) generally, and gastrointestinal-related VAEs in particular, in the text clinical notes of encounters recorded in the EMR of a large HMO. Compared to methods that use diagnosis and utilization codes assigned to encounters by clinicians and administrators, the MediClass system can both find more adverse events and improve the positive predictive value for detecting possible VAEs. |
| |
Keywords: | Natural language processing Vaccine adverse events Electronic medical records |
本文献已被 ScienceDirect 等数据库收录! |
|