Brian H. Feighner

A data-driven epidemiological prediction method for dengue outbreaks using local and remote sensing data

BackgroundDengue is the most common arboviral disease of humans, with more than one third of the world’s population at risk. Accurate prediction of dengue outbreaks may lead to public health interventions that mitigate the effect of the disease. Predicting infectious disease outbreaks is a challenging task; truly predictive methods are still in their infancy.MethodsWe describe a novel prediction method utilizing Fuzzy Association Rule Mining to extract relationships between clinical, meteorological, climatic, and socio-political data from Peru. These relationships are in the form of rules. The best set of rules is automatically chosen and forms a classifier. That classifier is then used to predict future dengue incidence as either HIGH (outbreak) or LOW (no outbreak), where these values are defined as being above and below the mean previous dengue incidence plus two standard deviations, respectively.ResultsOur automated method built three different fuzzy association rule models. Using the first two weekly models, we predicted dengue incidence three and four weeks in advance, respectively. The third prediction encompassed a four-week period, specifically four to seven weeks from time of prediction. Using previously unused test data for the period 4–7 weeks from time of prediction yielded a positive predictive value of 0.686, a negative predictive value of 0.976, a sensitivity of 0.615, and a specificity of 0.982.ConclusionsWe have developed a novel approach for dengue outbreak prediction. The method is general, could be extended for use in any geographical region, and has the potential to be extended to other environmentally influenced infections. The variables used in our method are widely available for most, if not all countries, enhancing the generalizability of our method.

SAGES: a suite of freely-available software tools for electronic disease surveillance in resource-limited settings.

Public health surveillance is undergoing a revolution driven by advances in the field of information technology. Many countries have experienced vast improvements in the collection, ingestion, analysis, visualization, and dissemination of public health data. Resource-limited countries have lagged behind due to challenges in information technology infrastructure, public health resources, and the costs of proprietary software. The Suite for Automated Global Electronic bioSurveillance (SAGES) is a collection of modular, flexible, freely-available software tools for electronic disease surveillance in resource-limited settings. One or more SAGES tools may be used in concert with existing surveillance applications or the SAGES tools may be used en masse for an end-to-end biosurveillance capability. This flexibility allows for the development of an inexpensive, customized, and sustainable disease surveillance system. The ability to rapidly assess anomalous disease activity may lead to more efficient use of limited resources and better compliance with World Health Organization International Health Regulations.

The pandemic influenza policy model: a planning tool for military public health officials.

The Pandemic Influenza Policy Model (PIPM) is a collaborative computer modeling effort between the U.S. Department of Defense (DoD) and the Johns Hopkins University Applied Physics Laboratory. Many helpful computer simulations exist for examining the propagation of pandemic influenza in civilian populations. We believe the mission-oriented nature and structured social composition of military installations may result in pandemic influenza intervention strategies that differ from those recommended for civilian populations. Intervention strategies may differ between military bases because of differences in mission, location, or composition of the population at risk. The PIPM is a web-accessible, user-configurable, installation-specific disease model allowing military planners to evaluate various intervention strategies. Innovations in the PIPM include expanding on the mathematics of prior stochastic models, using military-specific social network epidemiology, utilization of DoD personnel databases to more accurately characterize the population at risk, and the incorporation of possible interventions, e.g., pneumococcal vaccine, not examined in previous models.

Infectious disease modeling and military readiness.

Advances in infectious disease modeling may offer opportunities to mitigate the effect of emerging infectious diseases upon military readiness (1–3). In August 2005, the US Department of Defense (DoD) Global Emerging Infections Surveillance and Response System (GEIS) sponsored a meeting on the epidemiologic applications of infectious disease modeling in support of DoD readiness. Several recommendations were made at this conference to include the identification of organizations with “…demonstrated expertise in model development and operation for collaboration with the DoD and civilian organizations that are developing simulation models or conducting exercises” (4). Despite this recommendation, infectious disease modeling efforts in support of DoD have remained somewhat disjointed. An infectious disease modeling collaboration between DoD-GEIS and The Johns Hopkins Applied Physics Laboratory, begun in 2007, again identified this issue. Concerned that opportunities for collaboration might be missed and that unintended redundancy might be occurring, DoD-GEIS sponsored a second conference on May 12–13, 2008, for infectious disease modelers engaged in DoD projects or on models useful to the DoD. n nOver 30 participants from 10 agencies met for a day and a half at the Infectious Disease Modeling Meeting on the campus of the Johns Hopkins University Applied Physics Laboratory, Laurel, Maryland, USA (Appendix). The first day consisted of presentations detailing past and current work by the participating organizations. These presentations are available on the secure DoD-GEIS website for governmental organizations, collaborators, and academic institutions (request access from http://www.AFHSC.mil/about_GEIS.asp). The second day consisted of a roundtable discussion of how to optimize DoD-relevant infectious disease modeling efforts; specifically, how to maximize opportunities for collaboration and coordination while minimizing unintended redundancy. n nThe roundtable discussion first turned to who was at the table, and importantly, who was not. Many participants had also attended the 2005 conference, although some had not, and some of the key attendees at the 2005 conference were not present for the 2008 meeting. A strong recommendation was again made to identify all key organizations involved in infectious disease modeling of use to DoD. Additionally, because of the blurred lines of responsibility among federal agencies, participants thought that many other non-DoD federal organizations should participate in these types of discussions. Some participants called for the creation of a formal organization or society of infectious disease modelers. The Models of Infectious Disease Agent Study (MIDAS; http://www.nigms.nih.gov/Initiatives/MIDAS/Background/Factsheet.htm) group was mentioned as already serving as a nexus for the modeling community, but the need for a larger, coordinating body was expressed. Representatives from the Armed Forces Health Surveillance Center (the parent organization of DoD-GEIS; http://afhsc.army.mil/About_AFHSC.asp) indicated a willingness to be involved in future efforts in a coordinating capacity. n nParticipants also addressed the ambiguity associated with the term modeling, even within the infectious disease modeling community. Models may be used to provide indicators or warnings, surveillance data, or casualty prediction or to assist with consequence management, resource allocation, or policy development. Many models provide various combinations of these functions. Some participants believed it was important to organize modeling efforts by the functionality of the models in question. A stimulating discussion centered on who should have access to infectious disease models. Some thought that models should remain only in the hands of the experts who create them and can manage and interpret them. Others believed that state and community officials, who presumably have much greater local knowledge but less mathematical acumen, should be allowed access to the models. n nThe conference ended by reiterating the recommendation that the entire community of those working on disease modeling of interest to DoD should not only be identified but also strongly encouraged to meet again within the year. In addition to sharing ideas and work, participants of the 2008 conference recommended the development of a format and plan for ongoing communication and collaboration. This plan could include the formation of productive work groups to address definitions, e.g., the meaning of modeling, and to develop recommendations on the use of infectious disease models. The creation of a professional society for federal disease modelers could facilitate these actions and was identified for serious consideration.

2010 Conference on Infectious Disease Modeling Sponsored by the U.S. Department of Defense

Abstract : Advances in infectious disease modeling may offer opportunities to mitigate the effect of emerging infectious diseases upon military readiness. Concerned that opportunities for collaboration might be missed and unintended redundancy might be occurring, the U.S. Defense Department (DoD) Global Emerging Infections Surveillance and Response System (GEIS) sponsored conferences in August 2005 and May 2008 for infectious disease modelers engaged in DoD projects or on models useful to the DoD. Several recommendations were made at these conferences, to include the identification of organizations with ...demonstrated expertise in model development and operation for collaboration with the DoD and civilian organizations that are developing simulation models or conducting exercises. Despite these recommendations, infectious disease modeling efforts in support of the DoD have remained somewhat disjointed.