Displaying results 1 - 6 of 6
-
Using clinician mental models to guide annotation of medically unexplained symptoms and syndromes found in VA clinical documents
Content Type: Abstract
Medically unexplained syndromes (MUS) are conditions that are diagnosed on the basis of symptom constellations and are characterized by a lack of well-defined pathogenic pathways. The three most common MUS are chronic fatigue … read more… of symptom constellations and are characterized by a lack of well-defined pathogenic pathways. The three most … of symptom constellations and are characterized by a lack of well-defined pathogenic path- ways.1 The three most … of symptom constellations and are characterized by a lack of well-defined pathogenic pathways. The three most … -
Classifying Supporting, Refuting, or Uncertain Evidence for Pneumonia Case Review
Content Type: Abstract
Characterizing mentions found in clinical texts that support, refute, or represent uncertainty for suspected pneumonia is one area where automated Natural Language Processing (NLP) screening algorithms could be improved. Mentions of uncertainty and… read more… in healthcare: 1) probability or risk; 2) ambiguity – lack of reliability, credibility or adequacy of the … in healthcare: 1) probability or risk; 2) ambiguity – lack of reliability, credibility or adequacy of the … -
Clinical decision support at the time of an e-prescription can sustainably decrease unwarranted use of antibiotics for acute respiratory infections
Content Type: Abstract
Microorganisms resistant to antibiotics (ABX) increase the mortality, morbidity and costs of infections. In the absence of a drug development pipeline that can keep pace with the emerging resistancemechanisms, these organisms are expected… read more… were then manu- ally abstracted on the day of each index visit for all information required to establish … of acute respiratory tract infections in adults: back- ground, specific aims, and methods. (2001). Ann Intern … -
Automated Detection of GI Syndrome using Structured and Non-Structured Data from the VA EMR
Content Type: Abstract
Objective We performed a gold-standard manual chart review for gastro-intestinal syndrome to evaluate automated detection models based on both structured and non-structured data extracted from the VA … read more… Additionally, we searched for documentation on the index visit day of fever > 37.8ºC. RESULTS The ESSENCE and … -
Automated Surveillance To Detect An Influenza Epidemic: Which Respiratory Syndrome Should We Monitor?
Content Type: Abstract
OBJECTIVE Syndromic surveillance systems (SSS) seek early detection of infectious diseases outbreaks by focusing on pre-diagnostic symptoms. We do not yet know which respiratory syndrome should be monitored for a SSS to discover… read more… week of the study year. To distinguish between true- and back- ground-positive alarms, the daily statistics were per- formed on paired background+injection vs. back- ground-only time series. We computed two bench- marks: … yet retained a sensitivity of 69-100% (Models 4 and 6). Com pared to the “respiratory” ICD-9 codeset used by CDC’s … -
Using Biosurveillance Whole-System Facsimiles To Compare Aberrancy-Detection Methods: Should BioSense Use SatScan?
Content Type: Abstract
OBJECTIVE A “whole-system facsimile” recreates a complex automated biosurveillance system running prospectively on real historical datasets. We systematized this approach to compare the performance of otherwise… read more… alarms, the daily sta- tistics were performed on paired back- ground+injection vs. background-only time series. For …