Displaying results 1 - 7 of 7
-
Building an automated Bayesian case detection system
Content Type: Abstract
Current practices of automated case detection fall into the extremes of diagnostic accuracy and timeliness. In regards to diagnostic accuracy, electronic laboratory reporting (ELR) is at one extreme and syndromic surveillance is at… read more… immediate, and ELR is delayed 7 days from initial patient visit. A plausible solution, a middle way, to the extremes … UT, USA, on 1–2 December 2010. References 1 Que J, Tsui FC, Wagner MM. Timeliness study of radiology and … Symp Proc 2006; 1068. 2 Friedman C, Shagina L, Lussier Y, Hripcsak G. Automated encoding of clinical documents … -
An automated influenza-like-illness reporting system using freetext emergency department reports
Content Type: Abstract
Current methods for influenza surveillance include laboratory confirmed case reporting, sentinel physician reporting of Influenza-Like-Illness (ILI) and chief-complaint monitoring from emergency departments (EDs). The current… read more… system using freetext emergency department reports F-C Tsui1, H Su1, J Dowling1, RE Voorhees2, JU Espino1, and … HK000063-01. References 1 Friedman C, Shagina L, Lussier Y, Hripcsak G. Automated encoding of clinical documents … area [online] 2009 cited. Available from: http://kdka.com/health/H1N1.flu.deaths. 2.1321133.html. Automated … -
Challenges in adapting an natural language processing system for real-time surveillance
Content Type: Abstract
We are developing a Bayesian surveillance system for realtime surveillance and characterization of outbreaks that incorporates a variety of data elements, including free-text clinical reports. An existing natural language processing (… read more… real-time surveillance WW Chapman, M Conway, JN Dowling, F-C Tsui, Q Li, LM Christensen, H Harkema, T Sriburadej, and … Pittsburgh, PA, USA E-mail: wendy.w.chapman@gmail.com Objective Adapt an existing natural language processing … made changes to the NLP system using a development set of 26 laboratory- verified Shigellosis cases and 20 … -
Modeling Clinician Detection Time of a Disease Outbreak Due to Inhalational Anthrax
Content Type: Abstract
We developed a probabilistic model of how clinicians are expected to detect a disease outbreak due to an outdoor release of anthrax spores, when the clinicians only have access to traditional clinical information (e.g., no computer-based alerts). We… read more… for clinicians to detect such an outbreak. Such estimates may be useful in planning for outbreaks and in assessing the … for clinicians to detect such an outbreak. Such estimates may be useful in planning for out- breaks and in assessing … is only seen by a health care provider once (no return visits) and each clinician diagnoses a given case of IA … -
A Comparison of Chief Complaints and Emergency Department Reports for Identifying Patients with Acute Lower Respiratory Syndrome
Content Type: Abstract
Automated syndromic surveillance systems often classify patients into syndromic categories based on free-text chief complaints. Chief complaints (CC) demonstrate low to moderate sensitivity in identifying syndromic cases. Emergency Department (ED)… read more… reports promise more detailed clinical information that may increase sensitivity of detection. Objective: Compare … a Random Forests Classifier. Gold Standard Classification com- prised majority vote of three physicians reading ED … classifiers by randomly split- ting the 272 cases into 70% train and 30% test sets and averaging performance over … -
SyCo: A Probabilistic Machine Learning Method for Classifying Chief Complaints into Symptom and Syndrome Categories
Content Type: Abstract
Scientists have utilized many chief complaint (CC) classification techniques in biosurveillance including keyword search, weighted keyword search, and naïve Bayes. These techniques may utilize CC-to-syndrome or CC-… read more… keyword search, and naïve Bayes. These techniques may utilize CC-to-syndrome or CC-to-symptom-to-syndrome … keyword search,3 and naïve Bayes.4 These techniques may utilize CC-to-syndrome or CC-to-symptom-to-syndrome … keyword search, and naïve Bayes. These techniques may utilize CC-to-syndrome or CC-to-symptom-to-syndrome … -
Identifying Respiratory-Related Clinical Conditions from ED Reports with Topaz
Content Type: Abstract
Case detection from chief complaints suffers from low to moderate sensitivity. Emergency Department (ED) reports contain detailed clinical information that could improve case detection ability and enhance outbreak… read more… FP FN Precision Recall Incorrect Condi- tion Name ^ 578 3 70 89% 99% 30 (5%) ^The number of conditions Topaz marked … absent based on the ED report. The resulting conditions may improve our ability to detect cases of lower respiratory …