CDC outlined an objective for the BioSense program to develop technologies for automated detection of suspected cases of infection with bioterrorism relevant agents from clinical data. To enhance the value of BioSense, it is important to evaluate each case comprising alerts and to assess whether each patient comprising the alert has a presentation compatible with infection by bioterrorism agents.
Disease diagnosis codes were less likely to predict infection with a potential bioterrorism infectious agent than the patient's chief complaints, largely due to inclusion of incorrect ICD9 codes. (ICD9 codes classify diseases and a wide variety of signs, symptoms, abnormal findings, complaints, social circumstances and external causes of injury or disease.) Removing these codes may permit improved specificity and an increase in the predictability of anomalies, resulting in an increase in the value of BioSense.
Federal Contact: Taha Kass-Hout, 404-498-2014
Performer: Johns Hopkins University
Record ID: 9413 (Report issued January 1, 2010)