ISDS Conference

The performance of even the most advanced syndromic surveillance systems can be undermined if the monitored data is delayed before it arrives into the system.  In such cases, an outbreak may be detected only after it is too late for appropriate public health response. Surveillance systems can experience delays in data availability for a number of reasons: The process of transmitting data from data sources to the surveillance system can involve delays, especially in large systems where data is first aggregated across a national network of data sources before being transmitted to the surveillance system. Delays can also arise in the course of care, where, for example, a diagnosis is not available for a few days after the healthcare encounter.  It is important to minimize delays in data availability in order to maintain timeliness of detection [1].  When this is not possible, it is desirable to compensate for these data delays to minimize their effects.

Objective

This paper describes an approach to improving the detection timeliness of real-time health surveillance systems by modeling and correcting for delays in data availability.

Syndromic surveillance of emergency department(ED) visit data is often based on computerized classifiers which assign patient chief complaints (CC) tosyndromes. These classifiers may need to be updatedperiodically to account for changes over time in the way the CC is recorded or because of the addition of new data sources. Little information is available as to whether more frequent updates would actually improve classifier performance significantly. It can be burdensome to update classifiers which are developed and maintained manually. We had available to us an automated method for creating classifiers thatallowed us to address this question more easily. The “Ngram” method, described previously, creates a CC classifier automatically based on a training set of patient visits for which both the CC and ICD9 are available. This method measures the associations of text fragments within the CC (e.g. 3 characters for a “3-gram”) with a syndromic group of ICD9 codes. It then automatically creates a new CC classifier based on these associations. The CC classifier thus created can then be deployed for daily syndromic surveillance.

Objective

Our objective was to determine if performance of the Ngram classifier for the GI syndrome was improved significantly by updating the classifier more frequently.

Schistosomiasis is a chronic infection caused by flukes belonging to the genus Schistosoma. At least 200 million people, in 74 countries, are infected with the disease and at least 600 million are at risk of infection [1]. Like the majority of the parasitic diseases, schistosomiasis is influenced by human behavior, mainly water use practices and indiscriminate urination and defecation, but also, failure to take advantage of available screening services.

Objective

The purpose of this study was to determine the impact of health education and treatment interventions on the prevalence, intensity and perception of urinary schistosomiasis among school children in three rural communities in Cameroon.

An N-gram is a sub-sequence of n items from a given sequence where n can be 1, 2,…, n and the items can be letters or words. N-gram models are widely used in statistical natural language processing [3]. In the syndromic surveillance context, N-grams can be used to cluster or classify natural language data.  They can also help in the design of kernels for machine learning algorithms such as support vector machines to learn from text data.  This work calculates the similarity percentages of ED or TH reasons to syndromic fingerprints using Ngrams. We define “reasons similarity” as the percentage of matched N-grams derived from the reasons field of an ED or TH record with the fingerprint of a syndrome. The fingerprint of a syndrome is a list of frequent N-grams related to this syndrome.  This fingerprint is constructed by collecting a large sample of classified reasons data for a particular syndrome, calculating all of the N-grams for this set and then selecting the most frequent N-grams to form a profile or fingerprint. N-gram generation may require extensive processing time especially for large files but this issue has been addressed by using parallel computation.

Objective

The objective of this work is to identify syndromic fingerprints in reasons for entering an emergency department (ED) or calling telehealth (TH). It also demonstrates that these fingerprints are valuable for classification.

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 characterization. We developed a text processing system called Topaz that could be used to answer questions from ED reports, such as: How many new patients have come to the ED with acute lower respiratory symptoms? Of the respiratory patients, how many had a productive cough or wheezing? How many of the respiratory patients have a past history of asthma?

Objective

To evaluate how well a text processing system called Topaz can identify acute episodes of 55 clinical conditions described in ED notes.

The purposes of this study are to validate a keyword-based text parsing algorithm for identifying fractures and compare radiology results with chief complaint and ICD-9 final diagnoses.

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 someone other than the patient, or described in templated text that is difficult to process.

The purposes of this study are to identify and characterize increases in emergency department (ED) visits for falls during the 2007-08 winter season.

A significant research topic in biosurveillance is how to group individual events—such as single emergency department (ED) visits and sales of over-thecounter healthcare (OTC) products—into counts of “similar” events. For OTC products, the goal is to find categories of individual products that have superior outbreak detection performance relative to categories that biosurveillance systems currently monitor. We have described a method to identify OTC categories that correlate more highly with disease activity than existing categories.1 However, it is an open question whether a category that correlates more highly—or according to some other model has a higher ‘association’—with disease activity than an existing category necessarily has superior detection performance. Here, we evaluate whether a linear regression procedure that clusters OTC products based on how well they ‘explain’ ED visits for influenzalike illness (ILI) can find categories with superior outbreak-detection performance for influenza.

Objective

To develop a procedure that identifies product categories with superior outbreak detection performance.

This paper describes the spatial pattern of New York City (NYC) heat-related emergency medical services (EMS) ambulance dispatches and emergency department visits (ED) and explores how this information can be used in planning for and response to heat-related health events.