Detection of infectious symptoms from VA emergency department and primary care clinical documentation

Highlights ► Infectious symptoms can be successfully detected within outpatient and emergency department Veteran's Administration notes. ► Assertion detection was critically important, as a majority of clinical symptom assertions were negative. ► Rule algorithms that incorporate negation with S...

Full description

Saved in:
Bibliographic Details
Published in:International journal of medical informatics (Shannon, Ireland) Ireland), 2012-03, Vol.81 (3), p.143-156
Main Authors: Matheny, Michael E, FitzHenry, Fern, Speroff, Theodore, Green, Jennifer K, Griffith, Michelle L, Vasilevskis, Eduard E, Fielstein, Elliot M, Elkin, Peter L, Brown, Steven H
Format: Article
Language:English
Subjects:
Algorithms
Communicable Diseases - diagnosis
Decision Support Systems, Clinical - organization & administration
Diagnosis, Computer-Assisted
Emergency Service, Hospital
Hospitals, Veterans
Humans
Infection - diagnosis
Infectious symptoms
Internal Medicine
Medical Records Systems, Computerized - organization & administration
Natural language processing
Negation
Other
Population Surveillance
Primary Health Care
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights ► Infectious symptoms can be successfully detected within outpatient and emergency department Veteran's Administration notes. ► Assertion detection was critically important, as a majority of clinical symptom assertions were negative. ► Rule algorithms that incorporate negation with SNOMED-CT ontology encoding and keyword matching can improve NLP detection.
ISSN:1386-5056
1872-8243
DOI:10.1016/j.ijmedinf.2011.11.005