ABSTRACT
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.
Subject(s)
Diagnosis, Computer-Assisted/methods , Influenza, Human/diagnosis , Medical Records Systems, Computerized/statistics & numerical data , Natural Language Processing , Pattern Recognition, Automated/methods , Pneumonia/diagnosis , Serologic Tests , Algorithms , Artificial Intelligence , Humans , Influenza, Human/blood , Influenza, Human/complications , Pneumonia/blood , Pneumonia/complications , United StatesABSTRACT
Matched records of positive and negative influenza cases were parsed with a Natural Language Processor, the Multi-threaded Clinical Vocabulary Server (MCVS). Output was coded into SNOMED-CT reference terminology and compared to the SNOMED case definition of influenza. Odds ratios for each element of the influenza case definition by each section of the record were used to generate ROC curves. C-statistics showed that whole record surveillance was superior to chief complaint surveillance for predicting influenza.