Skip to main content

Displaying results 1 - 8 of 9
  • Can Chief Complaints Identify Patients with Febrile Syndromes?

    Content Type: Abstract

     Syndromic surveillance systems often classify patients into syndromic categories based on emergency department (ED) chief complaints. There exists no standard set of syndromes for syndromic surveillance, and the available syndromic case… read more
    … database since 1990, including free-text triage chief com- plaints, dictated and transcribed ED reports, and coded … AJ, Fraser H, Trigg LJ, Mandl KD, Espino JU, Tsui FC. Round- table on bioterrorism detection: information … Pavlin JA, Mansfield JL, O’Brien S, Boomsma LG, Elbert Y, Kelley PW. Disease outbreak detection system using …
  • 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 …
  • 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 …
  • Using NLP on VA Electronic Medical Records to Facilitate Epidemiologic Case Investigations

    Content Type: Abstract

    A major goal of biosurveillance is the timely detection of an infectious disease outbreak. Once a disease has been identified, another very important goal is to find all known cases of the disease to assist public health… read more
    … investigators. Natural language processing (NLP) systems may be able to assist in identifying epidemiological … to assist public health investigators. NLP systems may be able to assist in identifying epidemiological … asking us to assist them in identifying patients that may have been ill from respiratory illnesses circulating in …
  • Evaluation of Preprocessing Techniques for Chief Complaint Classification

    Content Type: Abstract

    The Real-time Outbreak and Disease Surveillance system collects chief complaints as free text and uses a naïve Bayesian classifier called CoCo to classify the complaints into syndromic categories. CoCo 3.0 has been trained on 28,990 manually clas-… read more
    … clas-sified chief complaints. The free text chief com-plaints are challenging to work with, due to problems … errors. Failure to correct these word variations may result in missed cases, thereby decreasing sensitivity … Constitutional 0.47 0.57 0.99 0.98 Gastrointestinal 0.70 0.67 0.99 0.99 Hemorrhagic 0.65 0.68 0.99 0.99 …
  • A web-based platform to support text mining of clinical reports for public health surveillance

    Content Type: Abstract

    PyConTextKit is a web-based platform that extracts entities from clinical text and provides relevant metadata - for example, whether the entity is negated or hypothetical - using simple lexical clues occurring in the window of text surrounding the… read more
    … a report based on the modifiers. For example, the user may only want to extract symptoms that occurred recently and … modifiers specified by the user. For instance, the user may want to identify documents with recent and nonnegated … ehtj11115 ehtj11120 ehtj11024 ehtj11060 ehtj11110 26-50 ehtj11034 ehtj11198 ehtj11174 ehtj11048 ehtj11154 …
  • 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 …
  • Identifying Contextual Features to Improve the Performance of an Influenza-Like Illness Text Classifier

    Content Type: Abstract

    To understand the types of false positive cases identified by an Influenza-like illness (ILI) text classifier by measuring the prevalence of ILI-related concepts that are negated, hypothetical, include explicit mention of temporality, experienced by… read more
    … electronic note documents. False positive extractions may be due to concepts in the text being assigned to the …