Skip to main content

Cooper Gregory

Description

Our laboratory previously established the value of over-the-counter (OTC) sales data for the early detection of disease outbreaks. We found that thermometer sales (TS) increased significantly and early during influenza (flu) season. Recently, the 2009 H1N1 outbreak has highlighted the need for developing methods that not only detect an outbreak but also estimate incidence so that public-health decision makers can allocate appropriate resources in response to an outbreak. Although a few studies have tried to estimate the H1N1 incidence in the 2009 outbreak, these were done months afterward and were based on data that are either not easy to collect or not available in a timely fashion (for example, surveys or confirmed laboratory cases).

Here, we explore the hypothesis that OTC sales data can also be used for predicting a disease activity. Towards that end, we developed a model to predict the number of Emergency Departments (ED) flu cases in a region based on TS. We obtain sales information from the National Retail Data Monitor (NRDM) project. NRDM collects daily sales data of 18 OTC categories across the US.

 

Objective

We developed a model that predicts the incidence of flu cases that present to ED in a given region based on TS.

Submitted by hparton on
Description

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-to-symptom-to-syndrome classification approaches. In the former approach, we classify a CC directly into syndrome categories. In the latter approach, we first classify a CC into symptom categories. Then, we use a syndrome definition, a combination of one or more symptoms, to determine whether or not a chief complaint belongs in a particular syndrome category. One approach to CC-to-symptom-to-syndrome classification uses manually weighted keyword search and Boolean operations to build syndrome classifiers. A limitation to this approach is that it does not address uncertainty in the data and the system is manually parameterized. A CC-tosymptom-to-syndrome approach that is both probabilistic and utilizes machine learning addresses these limitations.

 

Objective

Design, build and evaluate a symptom-based probabilistic chief complaint classifier for the Real-time Outbreak and Disease Surveillance System.

Submitted by elamb on
Description

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 used this model to estimate an upper bound on the amount of time expected for clinicians to detect such an outbreak. Such estimates may be useful in planning for outbreaks and in assessing the usefulness of various computer-based outbreak detection algorithms.

Submitted by elamb on
Description

Many disease-outbreak detection algorithms, such as control chart methods, use frequentist statistical techniques. We describe a Bayesian algorithm that uses data D consisting of current day counts of some event (e.g., emergency department (ED) chief complaints of respiratory disease) that are tallied according to demographic area (e.g., zip codes).

Objective

We introduce a disease-outbreak detection algorithm that performs complete Bayesian Model Averaging (BMA) over all possible spatial distributions of disease, yet runs in polynomial time.

Submitted by elamb on
Description

Non-temporal Bayesian network outbreak detection methods only look at data from the most recent day. For example, PANDA-CDCA (PC) only looks at data from the last 24 hours to determine how likely an outbreak is occurring. PC is a Bayesian network disease outbreak detection system that models 12 diseases. A system that looks only at each day's data might signal an outbreak one day and not signal it the next. Cooper et al. obtained such results when evaluating the ability of PC to detect a laboratory validated outbreak of influenza. We hypothesized that temporal modeling would attenuate this problem.

 

Objective

A temporal method for outbreak detection using a Bayesian network is presented and evaluated.

Submitted by elamb on
Description

The Activity Monitoring Operating Characteristic (AMOC) curve is a useful and popular method for assessing the performance of algorithms that detect outbreaks of disease [1]. As it is typically applied in biosurveillance, the AMOC curve plots the expected time to detection (since the outbreak began) as a function of the false alert rate. An ideal algorithm has zero false alerts and a detection time of zero. An al-ternative, conceptually equivalent version of the AMOC curve plots (T – detection_time) as a function of the false alert rate, where T is a maximum mean-ingful detection time. We focus on this version. 

Objective

We introduce a new measure for evaluating alerting algorithms, which is a generalization of the AMOC curve [1]. For a given rate of false positives alerts, the new measure estimates the time between when an alert is raised and when clinicians are expected to detect the outbreak on their own. We call this measure the Expected Warning Time (EWT).

Referenced File
Submitted by elamb on
Description

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) reports promise more detailed clinical information that may increase sensitivity of detection. Objective: Compare classification of patients based on chief complaints against classification from clinical data described in ED reports for identifying patients with an acute lower respiratory syndrome.

Submitted by elamb on