Online Program Home
My Program

Abstract Details

Activity Number: 589 - Topics in Data Mining, Forecasting, and Bayesian Inference for National Security
Type: Contributed
Date/Time: Wednesday, August 1, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics in Defense and National Security
Abstract #329158
Title: Text Mining Unstructured Data in the Electronic Medical Record
Author(s): Edwin D'Souza* and James Zouris and Vern F Wing
Companies: Leidos and NHRC and Leidos
Keywords: text mining; electronic medical record; combat data repository; unstructured text

The electronic medical record (EMR) in combat medical data repositories can contain a vast amount of unstructured free text that record the history, diagnoses, and treatments of patients suffering injuries and illnesses on the battlefield. These unstructured data are typically recorded by clinicians at medical treatment facilities, or by experienced medical coders, summarizing patient diagnosis and treatment. Examples of unstructured data are the Subjective, Objective, Assessment, and Plan of Care fields that can contain up to 4,000 bytes of data in each EMR in the Theater Medical Data Store repository. To date, little or no analysis has been done on the unstructured data in the combat EMR. This presentation demonstrates the application of current, state-of-the-art text mining methods to extract useful information from free text data within the EMR.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program