Skip to main content

Cluster Detection

HealthMap, a team of researchers, epidemiologists and software developers at Boston Children's Hospital founded in 2006, is an established global leader in utilizing online informal sources for disease outbreak monitoring and real-time surveillance of emerging public health threats. The freely available Web site 'healthmap.org' and mobile app 'Outbreaks Near Me' deliver real-time intelligence on a broad range of emerging infectious diseases for a diverse audience including libraries, local health departments, governments, and international travelers.

Submitted by uysz on
Description

Biosurveillance systems commonly depend on free-text chief complaints (CC)s for timely situational awareness. However, diagnosis codes may not be available soon enough and may have uncertain value because they are assigned for billing purposes rather than for population monitoring. Existing systems use syndrome categories to classify records based on these free-text fields. A syndromic cluster determination method (TOA) based on patient arrival times has been implemented in versions of ESSENCE and in NCDETECT [1]. While effective for finding case clusters whose CC terms are classifiable into syndromes, TOA implementations do not find clusters whose CC terms share only uncategorized terms. 

Objective

Explain and demonstrate the performance of a statistical method for detection of anomalous terms in pooled, contiguous blocks of freetext chief complaints from a health facility with emergent or urgent care capability.

Submitted by rmathes on
Description

Currently, there is an abundance of data coming from most of the surveillance environments and applications. Identification and filtering of responsive messages from this big data ocean and then processing these informative datasets to gain knowledge are the two real challenges in today’s applications.

Use of Analytics has revolutionized many areas. At LongRiver Infotech, we have used various Machine Learning techniques (Regression, Classification, Text Analytics, Decision Trees, Clustering etc.) in different types of applications. These methodologies are abstracted in a generic platform, which can be put to use in many public health and surveillance applications, which are enumerated here.

Objective

To summarize ways in which Analytics, Machine Learning (ML) and Natural Language Processing (NLP) can improve accuracy and efficiency in bio surveillance and public health practices. We also discuss the use of this framework in typical surveillance applications (Integration with Devices/Sensors, Web/Mobile, Clinical Records, Internet queries, Social/News media).

Submitted by teresa.hamby@d… on
Description

Despite the steady increase in immunization coverage in Kenya, the most recent Kenya Demographic and Health Survey (KDHS) shows that there is still immunization inequality across the country. Nationally, 2 out of every 3 (66.67%) children has been fully immunized but only 2 out of every 5 (40%) children in the North Eastern region were fully vaccinated1. There is a need to identify the characteristics of the households with children who are not fully immunized for effective intervention.

Objective

Large scale surveys has been used extensively to monitor childhood immunization rates. The purpose of this research is to find measurable features that informs the state of immunization in Kenya.

Submitted by Magou on
Description

The CDC defines a foodborne outbreak as two or more people getting the same illness from the same contaminated food or drink. These illnesses are often characterized as gastroenteritis until the causative agent is identified (bacterial or viral). Due to the globally interconnected food distribution system, local foodborne disease outbreaks often have global impacts. Therefore, the rapid detection of a gastroenteritis outbreak is of utmost importance for effective control. Situational awareness is important for early warning or detection of a disease outbreak, and tools that provide such information facilitate mitigation actions by civil/military health professionals. We have developed the Surveillance Window app (SWAP), a web based tool that can be used to help understand an unfolding outbreak. The app matches user input information to a library of historical outbreak information and provides context. This presentation will describe our analysis of global civilian and military gastrointestinal outbreaks and the adaptation of the SWAP to enhance situational awareness in the event of such outbreaks.

Objective

The objectives of this project are to identify properties that influence the progression of an outbreak, evaluate the ability of a property-based algorithm to differentiate between military and civilian outbreaks and different pathogens, and develop a decision support tool to enhance situational awareness during an unfolding outbreak.

Submitted by teresa.hamby@d… on
Description

While results from syndromic surveillance systems are commonly presented in the literature, few systems appear to have been thoroughly evaluated to examine which events can and cannot be detected, the time to detection and the efficacy of different syndromic surveillance data streams. Such an evaluation framework is presented.

Objective

To devise a methodology for evaluating the effectiveness of syndromic surveillance systems

Submitted by teresa.hamby@d… on
Description

Emerging disease clusters must be detected in a timely manner so that necessary remedial action can be taken to prevent the spread of an outbreak. The Exponentially Weighted Moving Average method (EWMA) is a particularly popular method, and has been utilized for disease surveillance in the United States.

A spatio-temporal EWMA statistic is proposed for on-line disease surveillance over multiple geographic regions. To capture spatial association, disease counts of neighboring regions are pooled together, similar to a method originally proposed by Raubertas for a different control chart. Also to increase statistical power in testing multiple EWMA statistics simultaneously, false discovery rate (FDR) is used instead of the traditional family-wise error rate (FWER).

Objective

To propose a computationally simple and a fast algorithm to detect disease outbreaks in multiple regions

Submitted by teresa.hamby@d… on
Description

Mass gatherings can result in morbidity and mortality from communicable and non-communicable diseases, injury, and bioterrorism. Therefore, it is important to identify event-related visits as opposed to community-related visits when conducting public health surveillance. Previous mass gatherings in Virginia have demonstrated the importance of implementing enhanced surveillance to facilitate early detection of public health issues to allow for timelyresponse. Between June 2015 and September 2015, VDH coordinated with two healthcare entities representing six acute care hospitals to conduct enhanced surveillance for the 2015 World Police and Fire Games and 2015 Union Cycliste Internationale (UCI) RoadWorld Championships. VDH established initial communicationwith each healthcare entity between 1 week to 2 months before theevent start date to discuss functional requirements with technical,informatics, and clinical staff.

Objective

To describe the planning strategies and lessons learned by theVirginia Department of Health (VDH) when conducting enhancedsurveillance during mass gathering events and coordinating withhealthcare entities to distinguish event-related emergency department(ED) visits from community-related ED visits

Submitted by uysz on
Description

Shootings with multiple victims are a concern for public safety and public health. The precise impact of such events and the trends associated with them is dependent on which events are counted. Some reports only consider events with multiple deaths, typically four or more, while other reports also include events with multiple victims and at least one death. Underreporting is also a concern. Some commonly cited databases for these events are based on media reports of shootings which may or may not capture the complete set of events that meet whatever criteria are being considered. Many gunshot wounds are treated in the emergency department setting. Emergency department registrations routinely collected for syndromic surveillance will capture all of those visits. Analysis of that data may be useful as a supplement to mass shooting databases by identifying unreported events. In addition, clusters of gunshot wound incidents which are not the result of a single shooting event but still represent significant public safety and public health concerns may also be identified.

Objective

To determine whether mass casualty shooting events are captured via syndromic surveillance data.

Submitted by uysz on
Description

Neill’s fast subset scan2 detects significant spatial patterns of disease by efficiently maximizing a log-likelihood ratio statistic over subsets of locations, but may result in patterns that are not spatially compact. The penalized fast subset scan (PFSS)3 provides a flexible framework for adding soft constraints to the fast subset scan, rewarding or penalizing inclusion of individual points into a cluster with additive point-specific penalty terms. We propose the support vector subset scan (SVSS), a novel method that iteratively assigns penalties according to distance from the separating hyperplane learned by a kernel support vector machine (SVM). SVSS efficiently detects disease clusters that are geometrically compact and irregular.

Objective

We present the support vector subset scan (SVSS), a new method for detecting localized and irregularly shaped patterns in spatial data. SVSS integrates the penalized fast subset scan3 with a kernel support vector machine classifier to accurately detect disease clusters that are compact and irregular in shape.

Submitted by Magou on