<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-1311">
  <Title>Lyudmila</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> At the New York Presbyterian Hospital, a general NLP system in the clinical domain, called MedLEE (Medical Language Extraction and Encoding System) (Friedman et al., 1994), is routinely used to parse and encode clinical reports. It has been satisfactorily evaluated for clinical applications that require encoded data that is found in discharge summaries and radiology reports (Friedman et al., 1999b) (Friedman and Hripcsak, 1998; Friedman et al., 1999a). Hripcsak et al showed that, for particular clinical conditions found in chest radiographs, which included pneumonia, the performance of MedLEE was the same as that of physicians, and was significantly superior to that of lay persons and alternative automated methods (Hripcsak et al., 1995). In another study to evaluate a clinical guideline and an automated computer protocol for detection and isolation of patients with tuberculosis, Knirsch et al (Knirsch et al., 1998) demonstrated that automated surveillance is a useful adjunct to clinical management and an effective tool for infection control practitioners. That detection system monitored radiology reports encoded by MedLEE for evidence of radiographic abnormalities suggestive of tuberculosis along with other data in the patient repository that was already coded, such as the patient's hospital location (for isolation status), laboratory and pharmacy data for immunological compromised status. Most importantly, the system detected patients who should be isolated that were not detected using the normal protocol (i.e. manual detection). MedLEE has also been extended to process pathology reports, echocardiograms, and electrocardiograms, but evaluations of performance in these areas have not yet been undertaken because evaluation is very costly in terms of time and personnel.</Paragraph>
  </Section>
class="xml-element"></Paper>