Lombardo Joseph

The Johns Hopkins Applied Physics Laboratory and the Armed Forces Health Surveillance Center have developed a hybrid processing engine that alerts monitors when a severe health condition exists based on corroboration among several sources of data. The system was designed to ingest a day's worth of recent data and provide results to monitors daily. In some theaters, the health of the US Forces must be determined at near-real time rates requiring a reassessment of current surveillance practices. Challenges exist in both acquiring data in real-time and in modifying automated alerting processes to re-evaluate as a new piece of evidence is received.

Objective

To develop a real-time surveillance capability that processes, fuses and assesses when data is received using a new fusion processing methodology and multiple sources health indicator data.

Every public health monitoring operation faces important decisions in its design phase. These include information sources to be used, the aggregation of data in space and time, the filtering of data records for required sensitivity, and the design of content delivery for users. Some of these decisions are dictated by available data limitations, others by objectives and resources of the organization doing the

surveillance. Most such decisions involve three characteristic tradeoffs: how much to monitor for exceptional vs customary health threats, the level of aggregation of the monitoring, and the degree of automation to be used.

The first tradeoff results from heightened concern for bioterrorism and pandemics, while everyday threats involve endemic disease events such as seasonal outbreaks. A system focused on bioterrorist attacks is scenario-based, concerned with unusual diagnoses or patient distributions, and likely to include attack hypothesis testing and tracking tools. A system at the other end of this continuum has broader syndrome groupings and is more concerned with general anomalous levels at manageable alert rates. 

Major aggregation tradeoffs are temporal, spatial, and syndromic. Bioterrorism fears have shortened the time scale of health monitoring from monthly or weekly to near-real-time. The spatial scale of monitoring is a function of the spatial resolution of data recorded and allowable for use as well as the monitoring institution’s purview and its capacity to collect, analyze and investigate localized outbreaks.

Automation tradeoffs involve the use of data processing to collect information, analyze it for anomalies, and make investigation and response decisions. The first of these uses has widespread acceptance, while in the latter two the degree of automation is a subject of ongoing controversy and research. To what degree can human judgment in alerting/response decisions be automated? What are the level and frequency of human inspection and adjustment? Should monitoring frequency change during elevated threat conditions?

All of these decisions affect monitoring tools and practices as well as funding for related research.

Objective

This purpose of this effort is to show how the goals and capabilities of health monitoring institutions can shape the selection, design, and usage of tools for automated disease surveillance systems.

On 27 April 2005, a simulated bioterrorist event—the aerosolized release of Francisella tularensis in the men’s room of luxury box seats at a sports stadium—was used to exercise the disease surveillance capability of the National Capital Region (NCR). The objective of this exercise was to permit all of the health departments in the NCR to exercise inter-jurisdictional epidemiological investigations using an advanced disease surveillance system. Actual system data could not be used for the exercise as it both is proprietary and contains protected, though de-identified, health information about real people; nor is there much historical data describing how such an outbreak would manifest itself in normal syndromic data. Thus, it was essential to develop methods to generate virtual health care records that met specific requirements and represented both ‘normal’ endemic visits (the background) as well as outbreak-specific records (the injects).

Objective

This paper describes a flexible modeling and simulation process that can create realistic, virtual syndromic data for exercising electronic biosurveillance systems.

One of the challenges facing developers and users of automated disease surveillance systems is being able to accurately evaluate the performance of their systems for the wide variety of public health threats that are possible. A variety of methods have been used in the past to create data sets for use in testing algorithm performance. Synthetic data has been created using agent-based simulations where data is created based on the hypothesized activity of individuals with contagious diseases. This data is only as accurate as the social models and variety of assumptions which must be made permit. Real data containing elevated levels of respiratory and gastrointestinal activity have been used to evaluate the ability of algorithms to detect the elevated levels. Routine unvalidated outbreaks are typically not public health emergencies and may not represent signals of interest. Another approach is to use real background data and inject a variety of different types of synthetic cases representing various types of outbreaks on top of that background.

With the introduction of the American Health Information Community (AHIC) Minimum Data Set (MDS), the public health surveillance community should have the potential to obtain greater specificity for alerts generated in automated systems. The introduction of these additional data elements increases the complexity of algorithms using linked data elements. Creating synthetic data sets that accurately estimate relationships among chief complaint, pharmacy, laboratory and radiology is an added complexity in creating synthetic outbreaks for performance evaluation.

Objective

The objectives of this presentation are to describe the need for synthetic data containing the elements of the AHIC MDS. Approaches for creating synthetic data with MDS data elements will be presented and methods for insuring maintenance of confidentiality will be discussed.

Early and reliable detection of anomalies is a critical challenge in disease surveillance. Most surveillance systems collect data from multiple data streams but the majority of monitoring is performed at univariate time series level. Purely statistical methods used in disease surveillance look at each time series separately and tend to generate a large number of false alarms. Support Vector Machines can be used to develop rich multivariate models that allow detecting abnormal relationships between different time series leading to greatly reduced number of false alarms.

Objective

This paper depicts a novel method for reliable detection of disease outbreaks. The methodology and initial results obtained on ESSENCE data are presented.

When the Chicago Bears met the Indianapolis Colts for Super Bowl XLI in Miami in January, 2007, fans from multiple regions visited South Florida for the game. In the past, public health departments have instituted heightened local surveillance during mass gatherings due to concerns about increased risk of disease outbreaks. For the first time, in 2007, health departments in all three Super Bowl-related regions already practiced daily disease surveillance using biosurveillance information systems (separate installations of the ESSENCE system, developed at JHUAPL). The situation provided an opportunity to explore ways in which separate surveillance systems could be coordinated for effective, short-term, multijurisdictional surveillance.

Objective

This paper describes an inter-jurisdictional surveillance data sharing effort carried out by public health departments in Miami, Chicago, and Indianapolis in conjunction with Super Bowl XLI.

The practice of real-time disease surveillance, sometimes called syndromic surveillance, is widespread at local, state, and national levels. Diseases ignore legal boundaries, so situations frequently arise where it is important to share surveillance information between public health jurisdictions. There are currently two fundamental ways for systems to share public health data and information related to disease outbreaks: sharing data, or sharing information. Data refers to patient level and aggregate counts of patients, and can be difficult to share legally because of privacy issues. Information refers to summaries, opinions or conclusions about data. There are few if any legal barriers to sharing information, and by definition it includes interpretation of data by knowledgeable local personnel which is vital during outbreak investigation. Currently most shared information is unstructured text, and this format makes it difficult for computers to use the information in any meaningful way. The only thing a system can do with this unstructured information is allow users to read each message.

Objectives

Alternate methods are needed to facilitate communication between jurisdictions during potential disease outbreaks. One alternative is to share structured information. Defined at the appropriate level, information sharing can avoid traditional data sharing barriers while capturing valuable local knowledge. The key is to identify the types of surveillance information that are neither so highly interpreted as to lose their value nor so loosely interpreted as to face traditional data sharing barriers. The objective of this work is to identify the level at which surveillance information sharing can be both feasible and beneficial, and to create a vocabulary standard that supports the exchange of structured information between diverse surveillance systems. 

Advanced surveillance systems require expertise from the fields of medicine, epidemiology, biostatistics, and information technology to develop a surveillance application that will automatically acquire, archive, process and present data to the user. Additionally, for a surveillance system to be most useful, it must adapt to the changing environment in which it operates to accommodate emerging public health events that could not be conceived of when the initial system was developed.

Objective

The objective of this presentation is to describe both within-discipline and across-discipline changes to standard methods and operating procedures that must be adopted to achieve automated systems that will be an effective complement and extension to traditional disease surveillance. This presentation describes adaptations already in place, as well as those still needed to rapidly recognize and respond to public health emergencies.

We evaluated several classifications of emergency department (ED) syndromic data to ascertain best syndrome classifications for ILI.

Automated disease surveillance systems that analyze data by syndrome categories have been used to look for outbreaks of disease for about 10 years. Most of these systems notify users of increases in the prevalence of reports in syndrome categories and allow users to view patient level data related to the increase. For most situations this level of investigation is sufficient, but occasionally a more dynamic level of control is required to properly understand an emerging illness in a community. During the SARS outbreak, for example, the respiratory syndrome was defined too broadly to allow users to track SARS. However, some systems, allowed users to build dynamic queries that allowed them to search their data by using the SARS case definition [1]. Users could perform free-text queries that identified records containing specific keywords in the chief complaint or specific combinations of ICD9 codes. This advanced querying capability has proven to be one of the most used features used by monitors of disease surveillance systems. Objective: The objective of this project is to build a new, more flexible query interface that allows users to define and build their query as if they were writing a logical expression for a mathematical computation. The interface is designed so that it can be easily adapted to fit into nearly any syndromic surveillance system.The interface will be evaluated in future versions of the ESSENCE and BioSense Systems.