Skip to main content

Displaying results 9 - 16 of 17
  • Talking Turkish: Using N-Grams for Syndromic Surveillance in a Turkish Emergency Department without the Need for English Translation

    Content Type: Abstract

    Previously we used an “N-Gram” classifier for syndromic surveillance of emergency department (ED) chief complaints (CC) in English for bioterrorism. The classifier is trained on a set of ED visits for which both the ICD diagnosis code and CC are… read more
    … bioterrorism. The classifier is trained on a set of ED visits for which both the ICD diagnosis code and CC are … bioterrorism. The classifier is trained on a set of ED visits for which both the ICD diagnosis code and CC are … CC classifier versus RESP ICD10 Grouping (Test Set) y = 0.642x + 3.0498 R = 0.88 0 5 10 15 20 25 30 35 0 5 10 15 …
  • ICD9 as a Surrogate for Chart Review in the Validation of a Chief Complaint Syndromic Surveillance System

    Content Type: Abstract

    The existing New York State Department of Health emergency department syndromic surveillance system has used patient’s chief complaint (CC) for assigning to six syndrome categories (Respiratory, Fever, Gastrointestinal, Neurological, Rash, Asthma… read more
    … process and allow us to survey a much larger sample of visits. Document … us O pe n w ou nd M ot or v eh ic le tra ffi c U rin ar y tra ct in fe ct io n Fe ve r N au se a an d vo m iti ng S … analyses that combine data across age categories may mask potentially important sub-syndrome activity among …
  • Performance of Sub-Syndrome Chief Complaint Classifiers for the GI Syndrome

    Content Type: Abstract

    The Centers for Disease Control and Prevention BioSense project has developed chief complaint (CC) and ICD9 sub-syndrome classifiers for the major syndromes for early event detection and situational awareness. This has the potential to… read more
    … a retrospective study of emergency department (ED) visits at four New York State hospitals from May 1, 2005 to April 30, 2007. These hospitals have annual ED visits ranging from 24,000 to 33,000 and have electronic … the older age groups. Three physicians then assigned the visits nonexclusively to the sub-syndromes by electronic …
  • A Case Manager Tool for Anomaly Investigation in BioSurveillance

    Content Type: Abstract

    Effective anomaly detection depends on the timely, asynchronous generation of anomalies from multiple data streams using multiple algorithms. Our objective is to describe the use of a case manager tool for combining anomalies into cases, and for… read more
    … of New Jersey include some 4.2 million records for ED visits to 24 hospitals in the New Jersey and New York, for … the meningitis scare, the “Clinton” chest pain effect, ED visits related to possible anthrax exposure around October … management system. The use of the case manager for ED visits and ELR supports our operational experience of data …
  • The Performance of Sub-Syndrome Chief Complaint Classifiers for the GI and RESP Syndromes

    Content Type: Abstract

    The Centers for Disease Control and Prevention BioSense has developed chief complaint (CC) and ICD9 sub syndrome classifiers for the major syndromes for early event detection and situational awareness. The prevalence of these sub… read more
    … of a CC classifier. Methods: A retrospective study of ED visits at four New York State hospitals from May 1, 2005 to … PPV NPV Chest Pain 6.71% 0.56 0.99 0.77 0.97 Dyspnea 6.70% 0.48 0.98 0.62 0.96 Asthma 2.22% 0.45 0.99 0.67 0.99 … 1.00 Pleurisy 0.22% 0.02 1.00 0.22 1.00 Resp Failure 0.26% 0.00 1.00 0.08 1.00 Table 2 – Gastrointestinal …
  • An Adaptive Anomaly Detection Algorithm

    Content Type: Abstract

    Ideal anomaly detection algorithms shoulddetect both sudden and gradual changes, while keeping the background false positive alert rate at a tolerable level. The algorithms should also be easy to use. Our objective was to develop an anomaly… read more
    … C2 or C3 alert. The test data were time series of daily visits from two emergency departments (ED) for two … with the usual 2.0 cut-off for two EDs. ORIGINAL GI DAILY VISITS, ~19 MONTHS, ED1 GI 4-DAY OUTBREAKS ROC COMPARISON …
  • The use of patient temperature data for biosurveillance in the emergency department

    Content Type: Abstract

    Biosurveillance systems commonly use emergency department (ED) patient chief complaint data (CC) for surveillance of influenza-like illness (ILI). Daily volumes are tracked using a computerized patient CC classifier for fever (CC… read more
    … the original work is properly cited. 0 10 20 30 40 50 60 70 80 90 100 10 /7 /0 7 1/ 7/ 08 4/ 7/ 08 7/ 7/ 08 10 /7 /0 … fever CC T>100 Combined Figure 1 14-day moving average of visits for fever CC, T4100 and combined fever CC and T4100 … Health Threats Journal. www.eht-journal.org 4 number of visits that were identified by adding T4100 to CC Fever. …
  • A Pilot Study of Aberration Detection Algorithms with Simulated Data

    Content Type: Abstract

    To evaluate four algorithms with varying baseline periods and adjustment for day of week for anomaly detection in syndromic surveillance data.   read more
    … for detecting anomalies in daily emergency depart- ment visit data for 130 hospitals with 6 syndrome categories. …