Syndromes

Of critical importance to the success of syndromic surveillance systems is the ability to collect data in a timely manner and thus ensure rapid detection of disease outbreaks. Most emergency department-based syndromic surveillance systems use information rou-tinely collected in patient care including patient chief complaints and physician diagnostic coding. These sources of data have been shown to have only limited sensitivities for the identification of cer-tain syndromes. Another potential source of information, which has not been previously studied, is the patient. Studies have shown that patients as well as parents can accurately report information about their own or their child’s illness. The value of of patient and parent self-reported informa-tion for disease surveillance systems has not been measured.

Objective

To determine whether patients and their families can directly provide medical information that enables syndrome classification.

In order to detect influenza outbreaks, the New York State Department of Health emergency department (ED) syndromic surveillance system uses patients’ chief complaint (CC) to assign visits to respiratory and fever syndromes. Recently, the CDC developed a more specific set of “sub-syndromes” including one that included only patients with a CC of flu or having a final ICD9 diagnosis of flu. Our own experience was that although flu may be a common presentation in the ED during the flu season, it is not commonly diagnosed as such. Emergency physicians usually use a symptomatic diagnosis in preference, probably because rapid testing is generally unavailable or may not change treatment. The flu subsyndrome is based on a specific ICD9 code for influenza. It is unknown whether patient visits that meet these restrictive criteria are sufficiently common to be of use, or whether patients who identify themselves as having the flu are correct.

Objective

Our objective was to examine the CC and ICD9 classifiers for the influenza sub-syndrome to assess the frequency of visits and the agreement between the CC, ICD9 code and chart review for these patient visits.

Syndromic surveillance of emergency department (ED) visit data is often based on computer algorithms which assign patient chief complaints (CC) to syndromes. ICD9 code data may also be used to develop visit classifiers for syndromic surveillance but the ICD9 code is generally not available immediately, thus limiting its utility. However, ICD9 has the advantages that ICD9 classifiers may be created rapidly and precisely as a subset of existing ICD9 codes and that the ICD9 codes are independent of the spoken language. If a classifier based on ICD9 codes could be used to automatically create the code for a chief-complaint assignment algorithm then CC algorithms could be created and updated more rapidly and with less labor. They could also be created in multiple spoken languages. We had developed a method for doing this based on an “ngram” text processing program adapted from business research technology (AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 code are known. A computerized method is used to automatically generate a collection of CC substrings with associated probabilities, and then generate a CC classifier program. The method includes specialized selection techniques and model pruning to automatically create a compact and efficient classifier.

Objective

Our objective was to determine how closely the performance of an ngram CC classifier for the gastrointestinal syndrome matched the performance of the ICD9 classifier.

During influenza season, the Boston Public Health Commission uses syndromic surveillance to monitor Emergency Department visits for chief complaints indicative of influenza-like illness (ILI). We created three syndrome definitions for ILI to capture variable presentations of disease, and compared the trends with Boston pneumonia and influenza mortality data, and onset dates for reported cases of influenza.

Objective

To evaluate the impact of different syndrome definitions for ILI by comparing weekly trends with other data sources during the 2005-2006 influenza season in Boston.

We report here on the use of the North Carolina Bioterrorism and Emerging Infection Prevention System (NC BEIPS, www.ncbeips.org) to reverse engineer a syndrome definition of influenza for the purpose of influenza surveillance.

Syndromic surveillance may be suited for detection of emerging respiratory disease elevations that could pass undiagnosed. The syndromes under surveillance should then retrospectively reflect known respiratory pathogen activity. To validate this for respiratory syndromes we analyzed dutch medical registration data from 1999-2003 (national hospital discharge diagnoses and causes of death). We assume that syndromes with a good reflection of pathogen activity have the potential ability to reflect unexpected respiratory pathogen activity in prospective surveillance.

Objective

As a validation for syndromic surveillance we studied whether respiratory syndromes indeed reflect the activity of respiratory pathogens. Therefore we retrospectively estimated the temporal trend of two respiratory syndromes by the seasonal dynamics of common respiratory pathogens.

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 expand the usefulness of syndromic surveillance, but little data exists evaluating this approach. The overall performance of classifiers can differ significantly among syndromes, and presumably among subsyndromes as well. Also, we had previously found that the seasonal pattern of diarrhea was different for patients < 60 months of age (younger) and for patients > 60 months of age (older).

Objective

Using chart review as the criterion standard to estimate the sensitivity, specificity, positive predictive value and negative predictive value of New York State hospital emergency department CC classifiers for patients < 60 months of age and > 60 months of age for the gastrointestinal (GI) syndrome and the following GI sub-syndromes: “abdominal pain”, “nausea-vomiting” and “diarrhea”.

A number of different methods are currently used to classify patients into syndromic groups based on the patient’s chief complaint (CC). We previously reported results using an “Ngram” text processing program for building classifiers (adapted from business research technology at AT&T Labs). The method applies the ICD9 classifier to a training set of ED visits for which both the CC and ICD9 code are known. A computerized method is used to automatically generate a collection of CC substrings (or Ngrams), with associated probabilities, from the training data. We then generate a CC classifier from the collection of Ngrams and use it to find a classification probability for each patient. Previously, we presented data showing good correlation between daily volumes as measured by the Ngram and ICD9 classifiers.

Objective

Our objective was to determine the optimized values for the sensitivity and specificity of the Ngram CC classifier for individual visits using a ROC curve analysis. Points on the ROC curve correspond to different classification probability cutoffs.

Free-text emergency department triage chief complaints (CCs) are a popular data source used by many syndromic surveillance systems because of their timeliness, availability, and relevance. The lack of standardization of CC vocabulary poses a major technical challenge to any automatic CC classification approach. This challenge can be partially addressed by several methods, for example, medical thesaurus, spelling check, manually-created synonym list, and supervised machine learning techniques that directly operate on free text. Current approaches, however, ignore the fact that medical terms appearing in CCs are often semantically related. Our research exploits such semantic relations through a medical ontology in the context of automatic CC classification for syndromic surveillance.

Objective

This paper presents a novel approach of using a medical ontology to classify free-text CCs into syndrome categories.

There exists no standard set of syndromes for syndromic surveillance, and available syndromic case definitions demonstrate substantial heterogeneity of findings constituting the definition. Many syndromic case definitions require the presence of a syndromic finding (e.g., cough or diarrhea) and a fever.

 

Objective

Automated syndromic surveillance systems often use chief complaints as input. Our objective was to determine whether chief complaints accurately represent whether a patient has any of the following febrile syndromes: Febrile respiratory, febrile gastrointestinal, febrile rash, febrile neurological, or febrile hemorrhagic.