Using natural language processing for identification of pneumonia cases from clinical records of patients with serologically proven influenza

The purpose of this study was to determine whether influenza vaccination protects against pneumonia in patients who develop influenza. By parsing a data set of records of 1455 patients with serologically proven influenza using SNOMED CT we found that of the vaccinated patients 19.3% developed pneumo...

Full description

Saved in:
Bibliographic Details
Published inAMIA ... Annual Symposium proceedings p. 1165
Main Authors Wahner-Roedler, Dietlind L, Welsh, Gail A, Trusko, Brett E, Froehling, David A, Froehling, David Arthur, Temesgen, Zelalem, Elkin, Peter L
Format Journal Article
LanguageEnglish
Published United States 06.11.2008
Subjects
Algorithms
Artificial Intelligence
Diagnosis, Computer-Assisted - methods
Humans
Influenza, Human - blood
Influenza, Human - complications
Influenza, Human - diagnosis
Medical Records Systems, Computerized - statistics & numerical data
Natural Language Processing
Pattern Recognition, Automated - methods
Pneumonia - blood
Pneumonia - complications
Pneumonia - diagnosis
Serologic Tests
United States
United States
Online AccessGet full text

Cover

More Information
Summary:The purpose of this study was to determine whether influenza vaccination protects against pneumonia in patients who develop influenza. By parsing a data set of records of 1455 patients with serologically proven influenza using SNOMED CT we found that of the vaccinated patients 19.3% developed pneumonia and of the unvaccinated 20.7%. These data suggest that influenza vaccine does not prevent pneumonias in patients who develop influenza despite immunization with influenza vaccine.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1559-4076